| Introducing EG-IPT and ipt~: a novel electric guitar dataset and a new Max/MSP object for real-time classification of instrumental playing techniques |
GitHub, GitHub |
This paper presents two key contributions to the real-time classification of Instrumental Playing Techniques (IPTs) in the context of NIME and human-machine interactive systems: the EG-IPT dataset and the ipt∼ Max/MSP object. The EG-IPT dataset, specifically designed for electric guitar, encompasses a broad range of IPTs captured across six distinct audio sources (five microphones and one direct input) and three pickup configurations. This diversity in recording conditions provides a robust foundation for training accurate models. We evaluate the dataset by employing a Convolutional Neural Network-based classifier (CNN), achieving state-of-the-art performance across a wide array of IPT classes, thereby validating the dataset's efficacy. The ipt∼ object is a new Max/MSP external enabling real-time classification of IPTs via pre-trained CNN models. While in this paper it's demonstrated with the EG-IPT dataset, the ipt∼ object is adaptable to models trained on various instruments. By integrating EG-IPT and ipt∼, we introduce a novel, end-to-end workflow that spans from data collection, model training to real-time classification and humancomputer interaction. This workflow exemplifies the entanglement of diverse components (data acquisition, machine learning, real-time processing, and interactive control) within a unified system, advancing the potential for dynamic, real-time music performance and human-computer interaction in the context of NIME. |
|
| ConciseHint: Boosting Efficient Reasoning via Continuous Concise Hints during Generation |
GitHub |
Recent advancements in large reasoning models (LRMs) like DeepSeek-R1 and OpenAI o1 series have achieved notable performance enhancements on complex reasoning tasks by scaling up the generation length by Chain-of-Thought (CoT). However, an emerging issue is their inclination to produce excessively verbose reasoning processes, leading to the inefficiency problem. Existing literature on improving efficiency mainly adheres to the before-reasoning paradigms such as prompting and reasoning or fine-tuning and reasoning, but ignores the promising direction of directly encouraging the model to speak concisely by intervening during the generation of reasoning. In order to fill the blank, we propose a framework dubbed ConciseHint, which continuously encourages the reasoning model to speak concisely by injecting the textual hint (manually designed or trained on the concise data) during the token generation of the reasoning process. Besides, ConciseHint is adaptive to the complexity of the query by adaptively adjusting the hint intensity, which ensures it will not undermine model performance. Experiments on the state-of-the-art LRMs, including DeepSeek-R1 and Qwen-3 series, demonstrate that our method can effectively produce concise reasoning processes while maintaining performance well. For instance, we achieve a reduction ratio of 65\% for the reasoning length on GSM8K benchmark with Qwen-3 4B with nearly no accuracy loss. |
|
| Multi-modal Anchor Gated Transformer with Knowledge Distillation for Emotion Recognition in Conversation |
GitHub |
Emotion Recognition in Conversation (ERC) aims to detect the emotions of individual utterances within a conversation. Generating efficient and modality-specific representations for each utterance remains a significant challenge. Previous studies have proposed various models to integrate features extracted using different modality-specific encoders. However, they neglect the varying contributions of modalities to this task and introduce high complexity by aligning modalities at the frame level. To address these challenges, we propose the Multi-modal Anchor Gated Transformer with Knowledge Distillation (MAGTKD) for the ERC task. Specifically, prompt learning is employed to enhance textual modality representations, while knowledge distillation is utilized to strengthen representations of weaker modalities. Furthermore, we introduce a multi-modal anchor gated transformer to effectively integrate utterance-level representations across modalities. Extensive experiments on the IEMOCAP and MELD datasets demonstrate the effectiveness of knowledge distillation in enhancing modality representations and achieve state-of-the-art performance in emotion recognition. Our code is available at: https://github.com/JieLi-dd/MAGTKD. |
|
| Cloud-Aware SAR Fusion for Enhanced Optical Sensing in Space Missions |
GitHub |
Cloud contamination significantly impairs the usability of optical satellite imagery, affecting critical applications such as environmental monitoring, disaster response, and land-use analysis. This research presents a Cloud-Attentive Reconstruction Framework that integrates SAR-optical feature fusion with deep learning-based image reconstruction to generate cloud-free optical imagery. The proposed framework employs an attention-driven feature fusion mechanism to align complementary structural information from Synthetic Aperture Radar (SAR) with spectral characteristics from optical data. Furthermore, a cloud-aware model update strategy introduces adaptive loss weighting to prioritize cloud-occluded regions, enhancing reconstruction accuracy. Experimental results demonstrate that the proposed method outperforms existing approaches, achieving a PSNR of 31.01 dB, SSIM of 0.918, and MAE of 0.017. These outcomes highlight the framework's effectiveness in producing high-fidelity, spatially and spectrally consistent cloud-free optical images. |
|
| UniFork: Exploring Modality Alignment for Unified Multimodal Understanding and Generation |
GitHub |
Unified image understanding and generation has emerged as a promising paradigm in multimodal artificial intelligence. Despite recent progress, the optimal architectural design for such unified models remains an open challenge. In this work, we start by analyzing the modality alignment behaviors of task-specific expert models for understanding and generation, as well as current unified models. Our analysis reveals a crucial observation: understanding tasks benefit from a progressively increasing modality alignment across network depth, which helps build up semantic information for better comprehension; In contrast, generation tasks follow a different trend: modality alignment increases in the early layers but decreases in the deep layers to recover spatial details. These divergent alignment patterns create a fundamental conflict in fully shared Transformer backbones, where a uniform representational flow often leads to performance compromises across two tasks. Motivated by this finding, we introduce UniFork, a novel Y-shaped architecture that shares the shallow layers for cross-task representation learning, while employing task-specific branches in deeper layers to avoid task interference. This design effectively balances shared learning and task specialization. Through extensive ablation experiments, we demonstrate that Unifork consistently outperforms conventional fully shared Transformer architectures, and achieves performance on par with or better than task-specific models. |
|
| Acquiring and Accumulating Knowledge from Diverse Datasets for Multi-label Driving Scene Classification |
GitHub |
Driving scene identification, which assigns multiple non-exclusive class labels to a scene, provides the contextual awareness necessary for enhancing autonomous vehicles' ability to understand, reason about, and interact with the complex driving environment. As a multi-label classification problem, it is better tackled via multitasking learning. However, directly training a multi-label classification model for driving scene identification through multitask learning presents two main challenges: acquiring a balanced, comprehensively annotated multi-label dataset and balancing learning across different tasks. This paper introduces a novel learning system that synergizes knowledge acquisition and accumulation (KAA) with consistency-based active learning (CAL) to address those challenges. KAA acquires and accumulates knowledge about scene identification from various single-label datasets via monotask learning. Subsequently, CAL effectively resolves the knowledge gap caused by the discrepancy between the marginal distributions of individual attributes and their joint distribution. An ablation study on our Driving Scene Identification (DSI) dataset demonstrates a 56.1% performance increase over the baseline model pretrained on ImageNet. Of this, KAA accounts for 31.3% of the gain, and CAL contributes 24.8%. Moreover, KAA-CAL stands out as the best performer when compared to state-of-the-art (SOTA) multi-label models on two public datasets, BDD100K and HSD, achieving this while using 85% less data. The DSI dataset and the implementation code for KAA-CAL are available at https://github.com/KELISBU/KAA-CAL . |
|
| From Data to Knowledge: Evaluating How Efficiently Language Models Learn Facts |
GitHub |
Sample efficiency is a crucial property of language models with practical implications for training efficiency. In real-world text, information follows a long-tailed distribution. Yet, we expect models to learn and recall frequent and infrequent facts. Sample-efficient models are better equipped to handle this challenge of learning and retaining rare information without requiring excessive exposure. This study analyzes multiple models of varying architectures and sizes, all trained on the same pre-training data. By annotating relational facts with their frequencies in the training corpus, we examine how model performance varies with fact frequency. Our findings show that most models perform similarly on high-frequency facts but differ notably on low-frequency facts. This analysis provides new insights into the relationship between model architecture, size, and factual learning efficiency. |
|
| From Generality to Mastery: Composer-Style Symbolic Music Generation via Large-Scale Pre-training |
GitHub |
Despite progress in controllable symbolic music generation, data scarcity remains a challenge for certain control modalities. Composer-style music generation is a prime example, as only a few pieces per composer are available, limiting the modeling of both styles and fundamental music elements (e.g., melody, chord, rhythm). In this paper, we investigate how general music knowledge learned from a broad corpus can enhance the mastery of specific composer styles, with a focus on piano piece generation. Our approach follows a two-stage training paradigm. First, we pre-train a REMI-based music generation model on a large corpus of pop, folk, and classical music. Then, we fine-tune it on a small, human-verified dataset from four renowned composers, namely Bach, Mozart, Beethoven, and Chopin, using a lightweight adapter module to condition the model on style indicators. To evaluate the effectiveness of our approach, we conduct both objective and subjective evaluations on style accuracy and musicality. Experimental results demonstrate that our method outperforms ablations and baselines, achieving more precise composer-style modeling and better musical aesthetics. Additionally, we provide observations on how the model builds music concepts from the generality pre-training and refines its stylistic understanding through the mastery fine-tuning. |
|
| MEXA: Towards General Multimodal Reasoning with Dynamic Multi-Expert Aggregation |
GitHub |
Combining pre-trained expert models offers substantial potential for scalable multimodal reasoning, but building a unified framework remains challenging due to the increasing diversity of input modalities and task complexity. For instance, medical diagnosis requires precise reasoning over structured clinical tables, while financial forecasting depends on interpreting plot-based data to make informed predictions. To tackle this challenge, we introduce MEXA, a training-free framework that performs modality- and task-aware aggregation of multiple expert models to enable effective multimodal reasoning across diverse and distinct domains. MEXA dynamically selects expert models based on the input modality and the task-specific reasoning demands (i.e., skills). Each expert model, specialized in a modality task pair, generates interpretable textual reasoning outputs. MEXA then aggregates and reasons over these outputs using a Large Reasoning Model (LRM) to produce the final answer. This modular design allows flexible and transparent multimodal reasoning across diverse domains without additional training overhead. We extensively evaluate our approach on diverse multimodal benchmarks, including Video Reasoning, Audio Reasoning, 3D Understanding, and Medical QA. MEXA consistently delivers performance improvements over strong multimodal baselines, highlighting the effectiveness and broad applicability of our expert-driven selection and aggregation in diverse multimodal reasoning tasks. |
|
| Instituto de Telecomunicações at IWSLT 2025: Aligning Small-Scale Speech and Language Models for Speech-to-Text Learning |
GitHub |
This paper presents the IT-IST submission to the IWSLT 2025 Shared Task on Instruction Following Speech Processing. We submit results for the Short Track, i.e., speech recognition, translation, and spoken question answering. Our model is a unified speech-to-text model that integrates a pre-trained continuous speech encoder and text decoder through a first phase of modality alignment and a second phase of instruction fine-tuning. Crucially, we focus on using small-scale language model backbones (< 2B) and restrict to high-quality, CC-BY data along with synthetic data generation to supplement existing resources. |
|
| TeXpert: A Multi-Level Benchmark for Evaluating LaTeX Code Generation by LLMs |
GitHub |
LaTeX's precision and flexibility in typesetting have made it the gold standard for the preparation of scientific documentation. Large Language Models (LLMs) present a promising opportunity for researchers to produce publication-ready material using LaTeX with natural language instructions, yet current benchmarks completely lack evaluation of this ability. By introducing TeXpert, our benchmark dataset with natural language prompts for generating LaTeX code focused on components of scientific documents across multiple difficulty levels, we conduct an in-depth analysis of LLM performance in this regard and identify frequent error types. Our evaluation across open and closed-source LLMs highlights multiple key findings: LLMs excelling on standard benchmarks perform poorly in LaTeX generation with a significant accuracy drop-off as the complexity of tasks increases; open-source models like DeepSeek v3 and DeepSeek Coder strongly rival closed-source counterparts in LaTeX tasks; and formatting and package errors are unexpectedly prevalent, suggesting a lack of diverse LaTeX examples in the training datasets of most LLMs. Our dataset, code, and model evaluations are available at https://github.com/knowledge-verse-ai/TeXpert. |
|
| Co-Seg++: Mutual Prompt-Guided Collaborative Learning for Versatile Medical Segmentation |
GitHub |
Medical image analysis is critical yet challenged by the need of jointly segmenting organs or tissues, and numerous instances for anatomical structures and tumor microenvironment analysis. Existing studies typically formulated different segmentation tasks in isolation, which overlooks the fundamental interdependencies between these tasks, leading to suboptimal segmentation performance and insufficient medical image understanding. To address this issue, we propose a Co-Seg++ framework for versatile medical segmentation. Specifically, we introduce a novel co-segmentation paradigm, allowing semantic and instance segmentation tasks to mutually enhance each other. We first devise a spatio-temporal prompt encoder (STP-Encoder) to capture long-range spatial and temporal relationships between segmentation regions and image embeddings as prior spatial constraints. Moreover, we devise a multi-task collaborative decoder (MTC-Decoder) that leverages cross-guidance to strengthen the contextual consistency of both tasks, jointly computing semantic and instance segmentation masks. Extensive experiments on diverse CT and histopathology datasets demonstrate that the proposed Co-Seg++ outperforms state-of-the-arts in the semantic, instance, and panoptic segmentation of dental anatomical structures, histopathology tissues, and nuclei instances. The source code is available at https://github.com/xq141839/Co-Seg-Plus. |
|
| Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens |
GitHub |
Vision-language models (VLMs) excel at multimodal understanding, yet their text-only decoding forces them to verbalize visual reasoning, limiting performance on tasks that demand visual imagination. Recent attempts train VLMs to render explicit images, but the heavy image-generation pre-training often hinders the reasoning ability. Inspired by the way humans reason with mental imagery-the internal construction and manipulation of visual cues-we investigate whether VLMs can reason through interleaved multimodal trajectories without producing explicit images. To this end, we present a Machine Mental Imagery framework, dubbed as Mirage, which augments VLM decoding with latent visual tokens alongside ordinary text. Concretely, whenever the model chooses to ``think visually'', it recasts its hidden states as next tokens, thereby continuing a multimodal trajectory without generating pixel-level images. Begin by supervising the latent tokens through distillation from ground-truth image embeddings, we then switch to text-only supervision to make the latent trajectory align tightly with the task objective. A subsequent reinforcement learning stage further enhances the multimodal reasoning capability. Experiments on diverse benchmarks demonstrate that Mirage unlocks stronger multimodal reasoning without explicit image generation. |
|
| YASMOT: Yet another stereo image multi-object tracker |
GitHub |
There now exists many popular object detectors based on deep learning that can analyze images and extract locations and class labels for occurrences of objects. For image time series (i.e., video or sequences of stills), tracking objects over time and preserving object identity can help to improve object detection performance, and is necessary for many downstream tasks, including classifying and predicting behaviors, and estimating total abundances. Here we present yasmot, a lightweight and flexible object tracker that can process the output from popular object detectors and track objects over time from either monoscopic or stereoscopic camera configurations. In addition, it includes functionality to generate consensus detections from ensembles of object detectors. |
|
| Emergent Temporal Correspondences from Video Diffusion Transformers |
GitHub |
Recent advancements in video diffusion models based on Diffusion Transformers (DiTs) have achieved remarkable success in generating temporally coherent videos. Yet, a fundamental question persists: how do these models internally establish and represent temporal correspondences across frames? We introduce DiffTrack, the first quantitative analysis framework designed to answer this question. DiffTrack constructs a dataset of prompt-generated video with pseudo ground-truth tracking annotations and proposes novel evaluation metrics to systematically analyze how each component within the full 3D attention mechanism of DiTs (e.g., representations, layers, and timesteps) contributes to establishing temporal correspondences. Our analysis reveals that query-key similarities in specific, but not all, layers play a critical role in temporal matching, and that this matching becomes increasingly prominent during the denoising process. We demonstrate practical applications of DiffTrack in zero-shot point tracking, where it achieves state-of-the-art performance compared to existing vision foundation and self-supervised video models. Further, we extend our findings to motion-enhanced video generation with a novel guidance method that improves temporal consistency of generated videos without additional training. We believe our work offers crucial insights into the inner workings of video DiTs and establishes a foundation for further research and applications leveraging their temporal understanding. |
|
| A Minimalist Optimizer Design for LLM Pretraining |
GitHub |
Training large language models (LLMs) typically relies on adaptive optimizers such as Adam, which require significant memory to maintain first- and second-moment matrices, known as optimizer states. While recent works such as GaLore, Fira, and APOLLO have proposed state-compressed variants to reduce memory consumption, a fundamental question remains: What is the minimal amount of optimizer state that is truly necessary to retain state-of-the-art performance in LLM pretraining? In this work, we systematically investigate this question using a bottom-up approach. We find that two memory- and compute-efficient optimization techniques are particularly effective: (1) column-wise gradient normalization significantly boosts the performance of plain SGD without requiring momentum; and (2) adding first-order momentum only to the output layer - where gradient variance is highest - yields performance competitive with fully adaptive methods such as Muon. Based on these insights, we propose SCALE (Stochastic Column-normalized Last-layer Momentum), a new optimizer that combines column-normalized SGD with last-layer momentum, where column normalization refers to normalizing the gradient along the output dimension. Across multiple LLaMA models (60M-1B), SCALE matches or exceeds the performance of Adam while using only 35-45% of the total memory. It also consistently outperforms memory-efficient optimizers such as GaLore, Fira, and APOLLO, making it a strong candidate for large-scale pretraining under memory constraints. For the LLaMA 7B model, SCALE outperforms the state-of-the-art method APOLLO in terms of both perplexity and memory consumption. In addition, our method serves as a minimalist baseline for more sophisticated optimizer design. |
|
| LunarLoc: Segment-Based Global Localization on the Moon |
GitHub |
Global localization is necessary for autonomous operations on the lunar surface where traditional Earth-based navigation infrastructure, such as GPS, is unavailable. As NASA advances toward sustained lunar presence under the Artemis program, autonomous operations will be an essential component of tasks such as robotic exploration and infrastructure deployment. Tasks such as excavation and transport of regolith require precise pose estimation, but proposed approaches such as visual-inertial odometry (VIO) accumulate odometry drift over long traverses. Precise pose estimation is particularly important for upcoming missions such as the ISRU Pilot Excavator (IPEx) that rely on autonomous agents to operate over extended timescales and varied terrain. To help overcome odometry drift over long traverses, we propose LunarLoc, an approach to global localization that leverages instance segmentation for zero-shot extraction of boulder landmarks from onboard stereo imagery. Segment detections are used to construct a graph-based representation of the terrain, which is then aligned with a reference map of the environment captured during a previous session using graph-theoretic data association. This method enables accurate and drift-free global localization in visually ambiguous settings. LunarLoc achieves sub-cm level accuracy in multi-session global localization experiments, significantly outperforming the state of the art in lunar global localization. To encourage the development of further methods for global localization on the Moon, we release our datasets publicly with a playback module: https://github.com/mit-acl/lunarloc-data. |
|
| LLM-Generated Feedback Supports Learning If Learners Choose to Use It |
GitHub |
Large language models (LLMs) are increasingly used to generate feedback, yet their impact on learning remains underexplored, especially compared to existing feedback methods. This study investigates how on-demand LLM-generated explanatory feedback influences learning in seven scenario-based tutor training lessons. Analyzing over 2,600 lesson completions from 885 tutor learners, we compare posttest performance among learners across three groups: learners who received feedback generated by gpt-3.5-turbo, those who declined it, and those without access. All groups received non-LLM corrective feedback. To address potential selection bias-where higher-performing learners may be more inclined to use LLM feedback-we applied propensity scoring. Learners with a higher predicted likelihood of engaging with LLM feedback scored significantly higher at posttest than those with lower propensity. After adjusting for this effect, two out of seven lessons showed statistically significant learning benefits from LLM feedback with standardized effect sizes of 0.28 and 0.33. These moderate effects suggest that the effectiveness of LLM feedback depends on the learners' tendency to seek support. Importantly, LLM feedback did not significantly increase completion time, and learners overwhelmingly rated it as helpful. These findings highlight LLM feedback's potential as a low-cost and scalable way to improve learning on open-ended tasks, particularly in existing systems already providing feedback without LLMs. This work contributes open datasets, LLM prompts, and rubrics to support reproducibility. |
|
| MAWIFlow Benchmark: Realistic Flow-Based Evaluation for Network Intrusion Detection |
GitHub |
Benchmark datasets for network intrusion detection commonly rely on synthetically generated traffic, which fails to reflect the statistical variability and temporal drift encountered in operational environments. This paper introduces MAWIFlow, a flow-based benchmark derived from the MAWILAB v1.1 dataset, designed to enable realistic and reproducible evaluation of anomaly detection methods. A reproducible preprocessing pipeline is presented that transforms raw packet captures into flow representations conforming to the CICFlowMeter format, while preserving MAWILab's original anomaly labels. The resulting datasets comprise temporally distinct samples from January 2011, 2016, and 2021, drawn from trans-Pacific backbone traffic. To establish reference baselines, traditional machine learning methods, including Decision Trees, Random Forests, XGBoost, and Logistic Regression, are compared to a deep learning model based on a CNN-BiLSTM architecture. Empirical results demonstrate that tree-based classifiers perform well on temporally static data but experience significant performance degradation over time. In contrast, the CNN-BiLSTM model maintains better performance, thus showing improved generalization. These findings underscore the limitations of synthetic benchmarks and static models, and motivate the adoption of realistic datasets with explicit temporal structure. All datasets, pipeline code, and model implementations are made publicly available to foster transparency and reproducibility. |
|
| Universal Music Representations? Evaluating Foundation Models on World Music Corpora |
GitHub, GitHub |
Foundation models have revolutionized music information retrieval, but questions remain about their ability to generalize across diverse musical traditions. This paper presents a comprehensive evaluation of five state-of-the-art audio foundation models across six musical corpora spanning Western popular, Greek, Turkish, and Indian classical traditions. We employ three complementary methodologies to investigate these models' cross-cultural capabilities: probing to assess inherent representations, targeted supervised fine-tuning of 1-2 layers, and multi-label few-shot learning for low-resource scenarios. Our analysis shows varying cross-cultural generalization, with larger models typically outperforming on non-Western music, though results decline for culturally distant traditions. Notably, our approaches achieve state-of-the-art performance on five out of six evaluated datasets, demonstrating the effectiveness of foundation models for world music understanding. We also find that our targeted fine-tuning approach does not consistently outperform probing across all settings, suggesting foundation models already encode substantial musical knowledge. Our evaluation framework and benchmarking results contribute to understanding how far current models are from achieving universal music representations while establishing metrics for future progress. |
|
| FedFitTech: A Baseline in Federated Learning for Fitness Tracking |
GitHub |
Rapid evolution of sensors and resource-efficient machine learning models have spurred the widespread adoption of wearable fitness tracking devices. Equipped with inertial sensors, such devices can continuously capture physical movements for fitness technology (FitTech), enabling applications from sports optimization to preventive healthcare. Traditional centralized learning approaches to detect fitness activities struggle with privacy concerns, regulatory constraints, and communication inefficiencies. In contrast, Federated Learning (FL) enables a decentralized model training by communicating model updates rather than private wearable sensor data. Applying FL to FitTech presents unique challenges, such as data imbalance, lack of labelled data, heterogeneous user activity patterns, and trade-offs between personalization and generalization. To simplify research on FitTech in FL, we present the FedFitTech baseline, under the Flower framework, which is publicly available and widely used by both industry and academic researchers. Additionally, to illustrate its usage, this paper presents a case study that implements a system based on the FedFitTech baseline, incorporating a client-side early stopping strategy and comparing the results. For instance, this system allows wearable devices to optimize the trade-off between capturing common fitness activity patterns and preserving individuals' nuances, thereby enhancing both the scalability and efficiency of privacy-aware fitness tracking applications. Results show that this reduces overall redundant communications by 13 percent, while maintaining the overall recognition performance at a negligible recognition cost by 1 percent. Thus, FedFitTech baseline creates a foundation for a wide range of new research and development opportunities in FitTech, and it is available as open-source at: https://github.com/adap/flower/tree/main/baselines/fedfittech |
|
| RAGentA: Multi-Agent Retrieval-Augmented Generation for Attributed Question Answering |
GitHub |
We present RAGentA, a multi-agent retrieval-augmented generation (RAG) framework for attributed question answering (QA). With the goal of trustworthy answer generation, RAGentA focuses on optimizing answer correctness, defined by coverage and relevance to the question and faithfulness, which measures the extent to which answers are grounded in retrieved documents. RAGentA uses a multi-agent architecture that iteratively filters retrieved documents, generates attributed answers with in-line citations, and verifies completeness through dynamic refinement. Central to the framework is a hybrid retrieval strategy that combines sparse and dense methods, improving Recall@20 by 12.5% compared to the best single retrieval model, resulting in more correct and well-supported answers. Evaluated on a synthetic QA dataset derived from the FineWeb index, RAGentA outperforms standard RAG baselines, achieving gains of 1.09% in correctness and 10.72% in faithfulness. These results demonstrate the effectiveness of the multi-agent architecture and hybrid retrieval in advancing trustworthy QA. |
|
| Efficient and faithful reconstruction of dynamical attractors using homogeneous differentiators |
GitHub |
Reconstructing the attractors of complex nonlinear dynamical systems from available measurements is key to analyse and predict their time evolution. Existing attractor reconstruction methods typically rely on topological embedding and may produce poor reconstructions, which differ significantly from the actual attractor, because measurements are corrupted by noise and often available only for some of the state variables and/or their combinations, and the time series are often relatively short. Here, we propose the use of Homogeneous Differentiators (HD) to effectively de-noise measurements and more faithfully reconstruct attractors of nonlinear systems. Homogeneous Differentiators are supported by rigorous theoretical guarantees about their de-noising capabilities, and their results can be fruitfully combined with time-delay embedding, differential embedding and functional observability. We apply our proposed HD-based methodology to simulated dynamical models of increasing complexity, from the Lorenz system to the Hindmarsh-Rose model and the Epileptor model for neural dynamics, as well as to empirical data of EEG recordings. In the presence of corrupting noise of various types, we obtain drastically improved quality and resolution of the reconstructed attractors, as well as significantly reduced computational time, which can be orders of magnitude lower than that of alternative methods. Our tests show the flexibility and effectiveness of Homogeneous Differentiators and suggest that they can become the tool of choice for preprocessing noisy signals and reconstructing attractors of highly nonlinear dynamical systems from both theoretical models and real data. |
|
| TransDreamerV3: Implanting Transformer In DreamerV3 |
GitHub |
This paper introduces TransDreamerV3, a reinforcement learning model that enhances the DreamerV3 architecture by integrating a transformer encoder. The model is designed to improve memory and decision-making capabilities in complex environments. We conducted experiments on Atari-Boxing, Atari-Freeway, Atari-Pong, and Crafter tasks, where TransDreamerV3 demonstrated improved performance over DreamerV3, particularly in the Atari-Freeway and Crafter tasks. While issues in the Minecraft task and limited training across all tasks were noted, TransDreamerV3 displays advancement in world model-based reinforcement learning, leveraging transformer architectures. |
|
| Enhancing Step-by-Step and Verifiable Medical Reasoning in MLLMs |
GitHub |
Multimodal large language models (MLLMs) have begun to demonstrate robust reasoning capabilities on general tasks, yet their application in the medical domain remains in its early stages. Constructing chain-of-thought (CoT) training data is essential for bolstering the reasoning abilities of medical MLLMs. However, existing approaches exhibit a deficiency in offering a comprehensive framework for searching and evaluating effective reasoning paths towards critical diagnosis. To address this challenge, we propose Mentor-Intern Collaborative Search (MICS), a novel reasoning-path searching scheme to generate rigorous and effective medical CoT data. MICS first leverages mentor models to initialize the reasoning, one step at a time, then prompts each intern model to continue the thinking along those initiated paths, and finally selects the optimal reasoning path according to the overall reasoning performance of multiple intern models. The reasoning performance is determined by an MICS-Score, which assesses the quality of generated reasoning paths. Eventually, we construct MMRP, a multi-task medical reasoning dataset with ranked difficulty, and Chiron-o1, a new medical MLLM devised via a curriculum learning strategy, with robust visual question-answering and generalizable reasoning capabilities. Extensive experiments demonstrate that Chiron-o1, trained on our CoT dataset constructed using MICS, achieves state-of-the-art performance across a list of medical visual question answering and reasoning benchmarks. Codes are available at GitHub - manglu097/Chiron-o1: Enhancing Step-by-Step and Verifiable Medical Reasoning in MLLMs |
|
| Robust Reinforcement Learning for Discrete Compositional Generation via General Soft Operators |
GitHub |
A major bottleneck in scientific discovery involves narrowing a large combinatorial set of objects, such as proteins or molecules, to a small set of promising candidates. While this process largely relies on expert knowledge, recent methods leverage reinforcement learning (RL) to enhance this filtering. They achieve this by estimating proxy reward functions from available datasets and using regularization to generate more diverse candidates. These reward functions are inherently uncertain, raising a particularly salient challenge for scientific discovery. In this work, we show that existing methods, often framed as sampling proportional to a reward function, are inadequate and yield suboptimal candidates, especially in large search spaces. To remedy this issue, we take a robust RL approach and introduce a unified operator that seeks robustness to the uncertainty of the proxy reward function. This general operator targets peakier sampling distributions while encompassing known soft RL operators. It also leads us to a novel algorithm that identifies higher-quality, diverse candidates in both synthetic and real-world tasks. Ultimately, our work offers a new, flexible perspective on discrete compositional generation tasks. Code: https://github.com/marcojira/tgm. |
|
| Reward-Agnostic Prompt Optimization for Text-to-Image Diffusion Models |
GitHub |
We investigate a general approach for improving user prompts in text-to-image (T2I) diffusion models by finding prompts that maximize a reward function specified at test-time. Although diverse reward models are used for evaluating image generation, existing automated prompt engineering methods typically target specific reward configurations. Consequently, these specialized designs exhibit suboptimal performance when applied to new prompt engineering scenarios involving different reward models. To address this limitation, we introduce RATTPO (Reward-Agnostic Test-Time Prompt Optimization), a flexible test-time optimization method applicable across various reward scenarios without modification. RATTPO iteratively searches for optimized prompts by querying large language models (LLMs) \textit{without} requiring reward-specific task descriptions. Instead, it uses the optimization trajectory and a novel reward-aware feedback signal (termed a "hint") as context. Empirical results demonstrate the versatility of RATTPO, effectively enhancing user prompts across diverse reward setups that assess various generation aspects, such as aesthetics, general human preference, or spatial relationships between objects. RATTPO surpasses other test-time search baselines in search efficiency, using up to 3.5 times less inference budget, and, given sufficient inference budget, achieves performance comparable to learning-based baselines that require reward-specific fine-tuning. The code is available at https://github.com/seminkim/RATTPO. |
|
| Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning |
GitHub |
Effectively scaling up deep reinforcement learning models has proven notoriously difficult due to network pathologies during training, motivating various targeted interventions such as periodic reset and architectural advances such as layer normalization. Instead of pursuing more complex modifications, we show that introducing static network sparsity alone can unlock further scaling potential beyond their dense counterparts with state-of-the-art architectures. This is achieved through simple one-shot random pruning, where a predetermined percentage of network weights are randomly removed once before training. Our analysis reveals that, in contrast to naively scaling up dense DRL networks, such sparse networks achieve both higher parameter efficiency for network expressivity and stronger resistance to optimization challenges like plasticity loss and gradient interference. We further extend our evaluation to visual and streaming RL scenarios, demonstrating the consistent benefits of network sparsity. |
|
| A Neural Operator based Hybrid Microscale Model for Multiscale Simulation of Rate-Dependent Materials |
GitHub |
The behavior of materials is influenced by a wide range of phenomena occurring across various time and length scales. To better understand the impact of microstructure on macroscopic response, multiscale modeling strategies are essential. Numerical methods, such as the $\text{FE}^2$ approach, account for micro-macro interactions to predict the global response in a concurrent manner. However, these methods are computationally intensive due to the repeated evaluations of the microscale. This challenge has led to the integration of deep learning techniques into computational homogenization frameworks to accelerate multiscale simulations. In this work, we employ neural operators to predict the microscale physics, resulting in a hybrid model that combines data-driven and physics-based approaches. This allows for physics-guided learning and provides flexibility for different materials and spatial discretizations. We apply this method to time-dependent solid mechanics problems involving viscoelastic material behavior, where the state is represented by internal variables only at the microscale. The constitutive relations of the microscale are incorporated into the model architecture and the internal variables are computed based on established physical principles. The results for homogenized stresses ($<6\%$ error) show that the approach is computationally efficient ($\sim 100 \times$ faster). |
|
| Visual-Instructed Degradation Diffusion for All-in-One Image Restoration |
GitHub |
Image restoration tasks like deblurring, denoising, and dehazing usually need distinct models for each degradation type, restricting their generalization in real-world scenarios with mixed or unknown degradations. In this work, we propose \textbf{Defusion}, a novel all-in-one image restoration framework that utilizes visual instruction-guided degradation diffusion. Unlike existing methods that rely on task-specific models or ambiguous text-based priors, Defusion constructs explicit \textbf{visual instructions} that align with the visual degradation patterns. These instructions are grounded by applying degradations to standardized visual elements, capturing intrinsic degradation features while agnostic to image semantics. Defusion then uses these visual instructions to guide a diffusion-based model that operates directly in the degradation space, where it reconstructs high-quality images by denoising the degradation effects with enhanced stability and generalizability. Comprehensive experiments demonstrate that Defusion outperforms state-of-the-art methods across diverse image restoration tasks, including complex and real-world degradations. |
|
| Brain-inspired interpretable reservoir computing with resonant recurrent neural networks |
GitHub |
Traditional artificial neural networks consist of nodes with non-oscillatory dynamics. Biological neural networks, on the other hand, consist of oscillatory components embedded in an oscillatory environment. Motivated by this feature of biological neurons, we describe a reservoir computing framework with explicit damped, oscillatory node dynamics. We express the oscillatory dynamics using two history dependent terms to connect these dynamics with existing artificial neural network approaches and apply physical and stationary constraints to reduce the number of free parameters. We then optimize and illustrate reservoir performance by classifying different brain rhythms associated with epilepsy and show that reservoir elements support classification by resonating with features of the input signals. Applying the same reservoir network to visual and auditory signal types, we show the reservoir generalizes for accurate classification with few trainable parameters. Compared to existing artificial neural network approaches, the proposed resonant reservoir network (RRN) utilizes oscillatory dynamics expressed as a straightforward extension of traditional artificial neural networks, produces interpretable features for classification, avoids computationally expensive training (e.g., backpropagation), and performs well with few parameters in different classification scenarios. We propose that RRNs may serve as efficient, biologically implemented building blocks to achieve complex goals in biological and artificial neural networks. |
|
| Mesh-Informed Neural Operator : A Transformer Generative Approach |
GitHub |
Generative models in function spaces, situated at the intersection of generative modeling and operator learning, are attracting increasing attention due to their immense potential in diverse scientific and engineering applications. While functional generative models are theoretically domain- and discretization-agnostic, current implementations heavily rely on the Fourier Neural Operator (FNO), limiting their applicability to regular grids and rectangular domains. To overcome these critical limitations, we introduce the Mesh-Informed Neural Operator (MINO). By leveraging graph neural operators and cross-attention mechanisms, MINO offers a principled, domain- and discretization-agnostic backbone for generative modeling in function spaces. This advancement significantly expands the scope of such models to more diverse applications in generative, inverse, and regression tasks. Furthermore, MINO provides a unified perspective on integrating neural operators with general advanced deep learning architectures. Finally, we introduce a suite of standardized evaluation metrics that enable objective comparison of functional generative models, addressing another critical gap in the field. |
|
| ParkFormer: A Transformer-Based Parking Policy with Goal Embedding and Pedestrian-Aware Control |
GitHub |
Autonomous parking plays a vital role in intelligent vehicle systems, particularly in constrained urban environments where high-precision control is required. While traditional rule-based parking systems struggle with environmental uncertainties and lack adaptability in crowded or dynamic scenes, human drivers demonstrate the ability to park intuitively without explicit modeling. Inspired by this observation, we propose a Transformer-based end-to-end framework for autonomous parking that learns from expert demonstrations. The network takes as input surround-view camera images, goal-point representations, ego vehicle motion, and pedestrian trajectories. It outputs discrete control sequences including throttle, braking, steering, and gear selection. A novel cross-attention module integrates BEV features with target points, and a GRU-based pedestrian predictor enhances safety by modeling dynamic obstacles. We validate our method on the CARLA 0.9.14 simulator in both vertical and parallel parking scenarios. Experiments show our model achieves a high success rate of 96.57\%, with average positional and orientation errors of 0.21 meters and 0.41 degrees, respectively. The ablation studies further demonstrate the effectiveness of key modules such as pedestrian prediction and goal-point attention fusion. The code and dataset will be released at: https://github.com/little-snail-f/ParkFormer. |
|
| Robust Dynamic Material Handling via Adaptive Constrained Evolutionary Reinforcement Learning |
GitHub |
Dynamic material handling (DMH) involves the assignment of dynamically arriving material transporting tasks to suitable vehicles in real time for minimising makespan and tardiness. In real-world scenarios, historical task records are usually available, which enables the training of a decision policy on multiple instances consisting of historical records. Recently, reinforcement learning has been applied to solve DMH. Due to the occurrence of dynamic events such as new tasks, adaptability is highly required. Solving DMH is challenging since constraints including task delay should be satisfied. A feedback is received only when all tasks are served, which leads to sparse reward. Besides, making the best use of limited computational resources and historical records for training a robust policy is crucial. The time allocated to different problem instances would highly impact the learning process. To tackle those challenges, this paper proposes a novel adaptive constrained evolutionary reinforcement learning (ACERL) approach, which maintains a population of actors for diverse exploration. ACERL accesses each actor for tackling sparse rewards and constraint violation to restrict the behaviour of the policy. Moreover, ACERL adaptively selects the most beneficial training instances for improving the policy. Extensive experiments on eight training and eight unseen test instances demonstrate the outstanding performance of ACERL compared with several state-of-the-art algorithms. Policies trained by ACERL can schedule the vehicles while fully satisfying the constraints. Additional experiments on 40 unseen noised instances show the robust performance of ACERL. Cross-validation further presents the overall effectiveness of ACREL. Besides, a rigorous ablation study highlights the coordination and benefits of each ingredient of ACERL. |
|
| Few-Shot Generalized Category Discovery With Retrieval-Guided Decision Boundary Enhancement |
GitHub |
While existing Generalized Category Discovery (GCD) models have achieved significant success, their performance with limited labeled samples and a small number of known categories remains largely unexplored. In this work, we introduce the task of Few-shot Generalized Category Discovery (FSGCD), aiming to achieve competitive performance in GCD tasks under conditions of known information scarcity. To tackle this challenge, we propose a decision boundary enhancement framework with affinity-based retrieval. Our framework is designed to learn the decision boundaries of known categories and transfer these boundaries to unknown categories. First, we use a decision boundary pre-training module to mitigate the overfitting of pre-trained information on known category boundaries and improve the learning of these decision boundaries using labeled samples. Second, we implement a two-stage retrieval-guided decision boundary optimization strategy. Specifically, this strategy further enhances the severely limited known boundaries by using affinity-retrieved pseudo-labeled samples. Then, these refined boundaries are applied to unknown clusters via guidance from affinity-based feature retrieval. Experimental results demonstrate that our proposed method outperforms existing methods on six public GCD benchmarks under the FSGCD setting. The codes are available at: https://github.com/Ryh1218/FSGCD |
|
| Evaluating the Impact of Model Accuracy for Optimizing Battery Energy Storage Systems |
GitHub |
This study investigates two models of varying complexity for optimizing intraday arbitrage energy trading of a battery energy storage system using a model predictive control approach. Scenarios reflecting different stages of the system's lifetime are analyzed. The findings demonstrate that the equivalent-circuit-model-based non-linear optimization model outperforms the simpler linear model by delivering more accurate predictions of energy losses and system capabilities. This enhanced accuracy enables improved operational strategies, resulting in increased roundtrip efficiency and revenue, particularly in systems with batteries exhibiting high internal resistance, such as second-life batteries. However, to fully leverage the model's benefits, it is essential to identify the correct parameters. |
|
| TextBraTS: Text-Guided Volumetric Brain Tumor Segmentation with Innovative Dataset Development and Fusion Module Exploration |
GitHub |
Deep learning has demonstrated remarkable success in medical image segmentation and computer-aided diagnosis. In particular, numerous advanced methods have achieved state-of-the-art performance in brain tumor segmentation from MRI scans. While recent studies in other medical imaging domains have revealed that integrating textual reports with visual data can enhance segmentation accuracy, the field of brain tumor analysis lacks a comprehensive dataset that combines radiological images with corresponding textual annotations. This limitation has hindered the exploration of multimodal approaches that leverage both imaging and textual data. To bridge this critical gap, we introduce the TextBraTS dataset, the first publicly available volume-level multimodal dataset that contains paired MRI volumes and rich textual annotations, derived from the widely adopted BraTS2020 benchmark. Building upon this novel dataset, we propose a novel baseline framework and sequential cross-attention method for text-guided volumetric medical image segmentation. Through extensive experiments with various text-image fusion strategies and templated text formulations, our approach demonstrates significant improvements in brain tumor segmentation accuracy, offering valuable insights into effective multimodal integration techniques. Our dataset, implementation code, and pre-trained models are publicly available at https://github.com/Jupitern52/TextBraTS. |
|
| Loupe: A Generalizable and Adaptive Framework for Image Forgery Detection |
GitHub |
The proliferation of generative models has raised serious concerns about visual content forgery. Existing deepfake detection methods primarily target either image-level classification or pixel-wise localization. While some achieve high accuracy, they often suffer from limited generalization across manipulation types or rely on complex architectures. In this paper, we propose Loupe, a lightweight yet effective framework for joint deepfake detection and localization. Loupe integrates a patch-aware classifier and a segmentation module with conditional queries, allowing simultaneous global authenticity classification and fine-grained mask prediction. To enhance robustness against distribution shifts of test set, Loupe introduces a pseudo-label-guided test-time adaptation mechanism by leveraging patch-level predictions to supervise the segmentation head. Extensive experiments on the DDL dataset demonstrate that Loupe achieves state-of-the-art performance, securing the first place in the IJCAI 2025 Deepfake Detection and Localization Challenge with an overall score of 0.846. Our results validate the effectiveness of the proposed patch-level fusion and conditional query design in improving both classification accuracy and spatial localization under diverse forgery patterns. The code is available at https://github.com/Kamichanw/Loupe. |
|
| Mathematical Proof as a Litmus Test: Revealing Failure Modes of Advanced Large Reasoning Models |
GitHub |
Large reasoning models (e.g., R1, o3) have demonstrated remarkable mathematical problem-solving abilities. However, the high reported accuracy of these advanced models on popular datasets, reliance on purely numerical evaluation and potential benchmark leakage, often masks their true reasoning shortcomings. To address this, we propose leveraging the inherent rigor and methodological complexity of mathematical proofs as a diagnostic tool to expose these hidden failures. Specifically, we introduce the RFMDataset (Reveal Failure Modes), a collection of 200 diverse mathematical proof problems, and thoroughly evaluate advanced models' performance on it. Our in-depth analysis of their failures uncovers 10 fine-grained error types, which shows fundamental limitations in current large reasoning models: 1) large reasoning models grapple profoundly with mathematical proofs, with some generating entirely correct proofs for less than 20% of problems and failing even on basic ones; 2) models exhibit a diverse spectrum of reasoning failures, prominently demonstrating the lack of guarantees for the correctness and rigor of single-step reasoning; and 3) models show hallucination and incompleteness during the reasoning process. Our findings reveal that models' self-reflection is insufficient to resolve the current logical dilemmas, necessitating formalized and fine-grained logical training. |
|
| Noise-Informed Diffusion-Generated Image Detection with Anomaly Attention |
GitHub |
With the rapid development of image generation technologies, especially the advancement of Diffusion Models, the quality of synthesized images has significantly improved, raising concerns among researchers about information security. To mitigate the malicious abuse of diffusion models, diffusion-generated image detection has proven to be an effective countermeasure.However, a key challenge for forgery detection is generalising to diffusion models not seen during training. In this paper, we address this problem by focusing on image noise. We observe that images from different diffusion models share similar noise patterns, distinct from genuine images. Building upon this insight, we introduce a novel Noise-Aware Self-Attention (NASA) module that focuses on noise regions to capture anomalous patterns. To implement a SOTA detection model, we incorporate NASA into Swin Transformer, forming an novel detection architecture NASA-Swin. Additionally, we employ a cross-modality fusion embedding to combine RGB and noise images, along with a channel mask strategy to enhance feature learning from both modalities. Extensive experiments demonstrate the effectiveness of our approach in enhancing detection capabilities for diffusion-generated images. When encountering unseen generation methods, our approach achieves the state-of-the-art performance.Our code is available at https://github.com/WeinanGuan/NASA-Swin. |
|
| Simultaneous Translation with Offline Speech and LLM Models in CUNI Submission to IWSLT 2025 |
GitHub, GitHub |
This paper describes Charles University submission to the Simultaneous Speech Translation Task of the IWSLT 2025. We cover all four language pairs with a direct or cascade approach. The backbone of our systems is the offline Whisper speech model, which we use for both translation and transcription in simultaneous mode with the state-of-the-art simultaneous policy AlignAtt. We further improve the performance by prompting to inject in-domain terminology, and we accommodate context. Our cascaded systems further use EuroLLM for unbounded simultaneous translation. Compared to the Organizers' baseline, our systems improve by 2 BLEU points on Czech to English and 13-22 BLEU points on English to German, Chinese and Japanese on the development sets. Additionally, we also propose a new enhanced measure of speech recognition latency. |
|
| Generalizable Agent Modeling for Agent Collaboration-Competition Adaptation with Multi-Retrieval and Dynamic Generation |
GitHub |
Adapting a single agent to a new multi-agent system brings challenges, necessitating adjustments across various tasks, environments, and interactions with unknown teammates and opponents. Addressing this challenge is highly complex, and researchers have proposed two simplified scenarios, Multi-agent reinforcement learning for zero-shot learning and Ad-Hoc Teamwork. Building on these foundations, we propose a more comprehensive setting, Agent Collaborative-Competitive Adaptation (ACCA), which evaluates an agent to generalize across diverse scenarios, tasks, and interactions with both unfamiliar opponents and teammates. In ACCA, agents adjust to task and environmental changes, collaborate with unseen teammates, and compete against unknown opponents. We introduce a new modeling approach, Multi-Retrieval and Dynamic Generation (MRDG), that effectively models both teammates and opponents using their behavioral trajectories. This method incorporates a positional encoder for varying team sizes and a hypernetwork module to boost agents' learning and adaptive capabilities. Additionally, a viewpoint alignment module harmonizes the observational perspectives of retrieved teammates and opponents with the learning agent. Extensive tests in benchmark scenarios like SMAC, Overcooked-AI, and Melting Pot show that MRDG significantly improves robust collaboration and competition with unseen teammates and opponents, surpassing established baselines. Our code is available at: https://github.com/vcis-wangchenxu/MRDG.git |
|
| Camera Calibration via Circular Patterns: A Comprehensive Framework with Measurement Uncertainty and Unbiased Projection Model |
GitHub |
Camera calibration using planar targets has been widely favored, and two types of control points have been mainly considered as measurements: the corners of the checkerboard and the centroid of circles. Since a centroid is derived from numerous pixels, the circular pattern provides more precise measurements than the checkerboard. However, the existing projection model of circle centroids is biased under lens distortion, resulting in low performance. To surmount this limitation, we propose an unbiased projection model of the circular pattern and demonstrate its superior accuracy compared to the checkerboard. Complementing this, we introduce uncertainty into circular patterns to enhance calibration robustness and completeness. Defining centroid uncertainty improves the performance of calibration components, including pattern detection, optimization, and evaluation metrics. We also provide guidelines for performing good camera calibration based on the evaluation metric. The core concept of this approach is to model the boundary points of a two-dimensional shape as a Markov random field, considering its connectivity. The shape distribution is propagated to the centroid uncertainty through an appropriate shape representation based on the Green theorem. Consequently, the resulting framework achieves marked gains in calibration accuracy and robustness. The complete source code and demonstration video are available at https://github.com/chaehyeonsong/discocal. |
|
| Generative Modeling of Full-Atom Protein Conformations using Latent Diffusion on Graph Embeddings |
GitHub |
Generating diverse, all-atom conformational ensembles of dynamic proteins such as G-protein-coupled receptors (GPCRs) is critical for understanding their function, yet most generative models simplify atomic detail or ignore conformational diversity altogether. We present latent diffusion for full protein generation (LD-FPG), a framework that constructs complete all-atom protein structures, including every side-chain heavy atom, directly from molecular dynamics (MD) trajectories. LD-FPG employs a Chebyshev graph neural network (ChebNet) to obtain low-dimensional latent embeddings of protein conformations, which are processed using three pooling strategies: blind, sequential and residue-based. A diffusion model trained on these latent representations generates new samples that a decoder, optionally regularized by dihedral-angle losses, maps back to Cartesian coordinates. Using D2R-MD, a 2-microsecond MD trajectory (12 000 frames) of the human dopamine D2 receptor in a membrane environment, the sequential and residue-based pooling strategy reproduces the reference ensemble with high structural fidelity (all-atom lDDT of approximately 0.7; C-alpha-lDDT of approximately 0.8) and recovers backbone and side-chain dihedral-angle distributions with a Jensen-Shannon divergence of less than 0.03 compared to the MD data. LD-FPG thereby offers a practical route to system-specific, all-atom ensemble generation for large proteins, providing a promising tool for structure-based therapeutic design on complex, dynamic targets. The D2R-MD dataset and our implementation are freely available to facilitate further research. |
|
| Consistent Sampling and Simulation: Molecular Dynamics with Energy-Based Diffusion Models |
GitHub |
Diffusion models have recently gained significant attention due to their effectiveness in various scientific domains, including biochemistry. When trained on equilibrium molecular distributions, diffusion models provide both: a generative procedure to sample equilibrium conformations and associated forces derived from the model's scores. However, using the forces for coarse-grained molecular dynamics simulations uncovers inconsistencies in the samples generated via classical diffusion inference and simulation, despite both originating from the same model. Particularly at the small diffusion timesteps required for simulations, diffusion models fail to satisfy the Fokker-Planck equation, which governs how the score should evolve over time. We interpret this deviation as an indication of the observed inconsistencies and propose an energy-based diffusion model with a Fokker-Planck-derived regularization term enforcing consistency. We demonstrate the effectiveness of our approach on toy systems, alanine dipeptide, and introduce a state-of-the-art transferable Boltzmann emulator for dipeptides that supports simulation and demonstrates enhanced consistency and efficient sampling. |
|
| RealSR-R1: Reinforcement Learning for Real-World Image Super-Resolution with Vision-Language Chain-of-Thought |
GitHub |
Real-World Image Super-Resolution is one of the most challenging task in image restoration. However, existing methods struggle with an accurate understanding of degraded image content, leading to reconstructed results that are both low-fidelity and unnatural. We present RealSR-R1 in this work, which empowers the RealSR models with understanding and reasoning capabilities. Inspired by the success of Chain of Thought (CoT) in large language models (LLMs), we simulate the human process of handling degraded images and propose the VLCoT framework, which integrates vision and language reasoning. The framework aims to precisely restore image details by progressively generating more comprehensive text and higher-resolution images. To overcome the challenge of traditional supervised learning CoT failing to generalize to real-world scenarios, we introduce, for the first time, Group Relative Policy Optimization (GRPO) into the Real-World Image Super-Resolution task. We propose VLCoT-GRPO as a solution, which designs four reward functions: (1) Format reward, used to standardize the CoT process; (2) Degradation reward, to incentivize accurate degradation estimation; (3) Understanding reward, to ensure the accuracy of the generated content; and (4) Generation reward, where we propose using a visual expert model to evaluate the quality of generated images, encouraging the model to generate more realistic images. Extensive experiments demonstrate that our proposed RealSR-R1 can generate realistic details and accurately understand image content, particularly in semantically rich scenes or images with severe degradation. |
|
| Off-Policy Actor-Critic for Adversarial Observation Robustness: Virtual Alternative Training via Symmetric Policy Evaluation |
GitHub |
Recently, robust reinforcement learning (RL) methods designed to handle adversarial input observations have received significant attention, motivated by RL's inherent vulnerabilities. While existing approaches have demonstrated reasonable success, addressing worst-case scenarios over long time horizons requires both minimizing the agent's cumulative rewards for adversaries and training agents to counteract them through alternating learning. However, this process introduces mutual dependencies between the agent and the adversary, making interactions with the environment inefficient and hindering the development of off-policy methods. In this work, we propose a novel off-policy method that eliminates the need for additional environmental interactions by reformulating adversarial learning as a soft-constrained optimization problem. Our approach is theoretically supported by the symmetric property of policy evaluation between the agent and the adversary. The implementation is available at https://github.com/nakanakakosuke/VALT_SAC. |
|
| Cache Me If You Can: How Many KVs Do You Need for Effective Long-Context LMs? |
GitHub |
Language models handle increasingly long contexts for tasks such as book summarization, but this leads to growing memory costs for the key-value (KV) cache. Many prior works have proposed ways of discarding KVs from memory, but their approaches are tailored to favorable settings, obscuring caveats like high peak memory and performance degradation, and a fair comparison between methods is difficult. In this paper, we propose the KV footprint as a unified metric, which accounts for both the amount of KV entries stored and their lifespan in memory. We evaluate methods based on the smallest footprint they attain while preserving performance in both long-context understanding and generation, with context lengths of up to 128K tokens. This metric reveals the high peak memory of prior KV eviction methods. One class of methods -- post-fill eviction -- has a high footprint due to being incompatible with eviction during pre-filling. We adapt these methods to be able to evict KVs during pre-filling, achieving substantially lower KV footprints. We then turn to recency eviction methods, wherein we propose PruLong, an end-to-end optimization method for learning which attention heads need to retain the full KV cache and which do not. PruLong saves memory while preserving long-context performance, achieving 12% smaller KV footprint than prior methods while retaining performance in challenging recall tasks. Our paper clarifies the complex tangle of long-context inference methods and paves the way for future development to minimize the KV footprint. |
|
| On Training-Test (Mis)alignment in Unsupervised Combinatorial Optimization: Observation, Empirical Exploration, and Analysis |
GitHub |
In unsupervised combinatorial optimization (UCO), during training, one aims to have continuous decisions that are promising in a probabilistic sense for each training instance, which enables end-to-end training on initially discrete and non-differentiable problems. At the test time, for each test instance, starting from continuous decisions, derandomization is typically applied to obtain the final deterministic decisions. Researchers have developed more and more powerful test-time derandomization schemes to enhance the empirical performance and the theoretical guarantee of UCO methods. However, we notice a misalignment between training and testing in the existing UCO methods. Consequently, lower training losses do not necessarily entail better post-derandomization performance, even for the training instances without any data distribution shift. Empirically, we indeed observe such undesirable cases. We explore a preliminary idea to better align training and testing in UCO by including a differentiable version of derandomization into training. Our empirical exploration shows that such an idea indeed improves training-test alignment, but also introduces nontrivial challenges into training. |
|
| Long-term Traffic Simulation with Interleaved Autoregressive Motion and Scenario Generation |
GitHub |
An ideal traffic simulator replicates the realistic long-term point-to-point trip that a self-driving system experiences during deployment. Prior models and benchmarks focus on closed-loop motion simulation for initial agents in a scene. This is problematic for long-term simulation. Agents enter and exit the scene as the ego vehicle enters new regions. We propose InfGen, a unified next-token prediction model that performs interleaved closed-loop motion simulation and scene generation. InfGen automatically switches between closed-loop motion simulation and scene generation mode. It enables stable long-term rollout simulation. InfGen performs at the state-of-the-art in short-term (9s) traffic simulation, and significantly outperforms all other methods in long-term (30s) simulation. The code and model of InfGen will be released at https://orangesodahub.github.io/InfGen |
|
| Cross-Modal Epileptic Signal Harmonization: Frequency Domain Mapping Quantization for Pre-training a Unified Neurophysiological Transformer |
GitHub |
Scalp electroencephalography (EEG) and intracranial EEG (iEEG) are vital for epilepsy diagnosis and treatment. Their unified analysis offers the potential to harness the complementary strengths of each modality but is challenging due to variations in recording montages, amplitude and signal-to-noise ratio (SNR), and frequency components. To address the aforementioned challenges, this paper introduces EpiNT, a novel Transformer-based pre-trained model for unified EEG and iEEG analysis. EpiNT employs channel-independent modeling with masked autoencoders (MAE) and vector quantization (VQ), along with a frequency domain mapping quantizer to capture crucial frequency features. Pre-trained on over 2,700 hours of multi-modal clinical neurophysiological data from 1,199 patients, EpiNT outperformed both randomly initialized models and other pre-trained methods on six downstream classification tasks, demonstrating robust representation learning capabilities. This work presents a promising approach for unified epilepsy neurophysiology analysis. |
|
| RGBTrack: Fast, Robust Depth-Free 6D Pose Estimation and Tracking |
GitHub |
We introduce a robust framework, RGBTrack, for real-time 6D pose estimation and tracking that operates solely on RGB data, thereby eliminating the need for depth input for such dynamic and precise object pose tracking tasks. Building on the FoundationPose architecture, we devise a novel binary search strategy combined with a render-and-compare mechanism to efficiently infer depth and generate robust pose hypotheses from true-scale CAD models. To maintain stable tracking in dynamic scenarios, including rapid movements and occlusions, RGBTrack integrates state-of-the-art 2D object tracking (XMem) with a Kalman filter and a state machine for proactive object pose recovery. In addition, RGBTrack's scale recovery module dynamically adapts CAD models of unknown scale using an initial depth estimate, enabling seamless integration with modern generative reconstruction techniques. Extensive evaluations on benchmark datasets demonstrate that RGBTrack's novel depth-free approach achieves competitive accuracy and real-time performance, making it a promising practical solution candidate for application areas including robotics, augmented reality, and computer vision. The source code for our implementation will be made publicly available at https://github.com/GreatenAnoymous/RGBTrack.git. |
|
| Knee-Deep in C-RASP: A Transformer Depth Hierarchy |
GitHub |
It has been observed that transformers with greater depth (that is, more layers) have more capabilities, but can we establish formally which capabilities are gained with greater depth? We answer this question with a theoretical proof followed by an empirical study. First, we consider transformers that round to fixed precision except inside attention. We show that this subclass of transformers is expressively equivalent to the programming language C-RASP and this equivalence preserves depth. Second, we prove that deeper C-RASP programs are more expressive than shallower C-RASP programs, implying that deeper transformers are more expressive than shallower transformers (within the subclass mentioned above). These results are established by studying a form of temporal logic with counting operators, which was shown equivalent to C-RASP in previous work. Finally, we provide empirical evidence that our theory predicts the depth required for transformers without positional encodings to length-generalize on a family of sequential dependency tasks. |
|
| Adversarial Attacks and Detection in Visual Place Recognition for Safer Robot Navigation |
GitHub |
Stand-alone Visual Place Recognition (VPR) systems have little defence against a well-designed adversarial attack, which can lead to disastrous consequences when deployed for robot navigation. This paper extensively analyzes the effect of four adversarial attacks common in other perception tasks and four novel VPR-specific attacks on VPR localization performance. We then propose how to close the loop between VPR, an Adversarial Attack Detector (AAD), and active navigation decisions by demonstrating the performance benefit of simulated AADs in a novel experiment paradigm -- which we detail for the robotics community to use as a system framework. In the proposed experiment paradigm, we see the addition of AADs across a range of detection accuracies can improve performance over baseline; demonstrating a significant improvement -- such as a ~50% reduction in the mean along-track localization error -- can be achieved with True Positive and False Positive detection rates of only 75% and up to 25% respectively. We examine a variety of metrics including: Along-Track Error, Percentage of Time Attacked, Percentage of Time in an `Unsafe' State, and Longest Continuous Time Under Attack. Expanding further on these results, we provide the first investigation into the efficacy of the Fast Gradient Sign Method (FGSM) adversarial attack for VPR. The analysis in this work highlights the need for AADs in real-world systems for trustworthy navigation, and informs quantitative requirements for system design. |
|
| Revela: Dense Retriever Learning via Language Modeling |
GitHub |
Dense retrievers play a vital role in accessing external and specialized knowledge to augment language models (LMs). Training dense retrievers typically requires annotated query-document pairs, which are costly and hard to obtain in specialized domains such as code-motivating growing interest in self-supervised retriever learning. Since LMs are trained to capture token-level dependencies through a self-supervised learning objective (i.e., next-token prediction), we can analogously cast retrieval as learning dependencies among chunks of tokens. This analogy naturally leads to the question: How can we adapt self-supervised learning objectives in the spirit of language modeling to train retrievers? To answer this question, we introduce Revela, a unified and scalable training framework for self-supervised retriever learning via language modeling. Revela models semantic dependencies among documents by conditioning next-token prediction on both local and cross-document context through an in-batch attention mechanism. This attention is weighted by retriever-computed similarity scores, enabling the retriever to be optimized as part of language modeling. We evaluate Revela on both general-domain (BEIR) and domain-specific (CoIR) benchmarks across various retriever backbones. At a comparable parameter scale, Revela outperforms the previous best method with absolute improvements of 5.2 % (18.3 % relative) and 5.6 % (14.4 % relative) on NDCG@10, respectively, underscoring its effectiveness. Performance increases with model size, highlighting both the scalability of our approach and its promise for self-supervised retriever learning. |
|
| Dense 3D Displacement Estimation for Landslide Monitoring via Fusion of TLS Point Clouds and Embedded RGB Images |
GitHub |
Landslide monitoring is essential for understanding geohazards and mitigating associated risks. However, existing point cloud-based methods typically rely on either geometric or radiometric information and often yield sparse or non-3D displacement estimates. In this paper, we propose a hierarchical partition-based coarse-to-fine approach that fuses 3D point clouds and co-registered RGB images to estimate dense 3D displacement vector fields. We construct patch-level matches using both 3D geometry and 2D image features. These matches are refined via geometric consistency checks, followed by rigid transformation estimation per match. Experimental results on two real-world landslide datasets demonstrate that our method produces 3D displacement estimates with high spatial coverage (79% and 97%) and high accuracy. Deviations in displacement magnitude with respect to external measurements (total station or GNSS observations) are 0.15 m and 0.25 m on the two datasets, respectively, and only 0.07 m and 0.20 m compared to manually derived references. These values are below the average scan resolutions (0.08 m and 0.30 m). Our method outperforms the state-of-the-art method F2S3 in spatial coverage while maintaining comparable accuracy. Our approach offers a practical and adaptable solution for TLS-based landslide monitoring and is extensible to other types of point clouds and monitoring tasks. Our example data and source code are publicly available at https://github.com/zhaoyiww/fusion4landslide. |
|
| Geometric Learning in Black-Box Optimization: A GNN Framework for Algorithm Performance Prediction |
GitHub |
Automated algorithm performance prediction in numerical blackbox optimization often relies on problem characterizations, such as exploratory landscape analysis features. These features are typically used as inputs to machine learning models and are represented in a tabular format. However, such approaches often overlook algorithm configurations, a key factor influencing performance. The relationships between algorithm operators, parameters, problem characteristics, and performance outcomes form a complex structure best represented as a graph. This work explores the use of heterogeneous graph data structures and graph neural networks to predict the performance of optimization algorithms by capturing the complex dependencies between problems, algorithm configurations, and performance outcomes. We focus on two modular frameworks, modCMA-ES and modDE, which decompose two widely used derivative-free optimization algorithms: the covariance matrix adaptation evolution strategy (CMA-ES) and differential evolution (DE). We evaluate 324 modCMA-ES and 576 modDE variants on 24 BBOB problems across six runtime budgets and two problem dimensions. Achieving up to 36.6% improvement in MSE over traditional tabular-based methods, this work highlights the potential of geometric learning in black-box optimization. |
|
| EndoMUST: Monocular Depth Estimation for Robotic Endoscopy via End-to-end Multi-step Self-supervised Training |
GitHub |
Monocular depth estimation and ego-motion estimation are significant tasks for scene perception and navigation in stable, accurate and efficient robot-assisted endoscopy. To tackle lighting variations and sparse textures in endoscopic scenes, multiple techniques including optical flow, appearance flow and intrinsic image decomposition have been introduced into the existing methods. However, the effective training strategy for multiple modules are still critical to deal with both illumination issues and information interference for self-supervised depth estimation in endoscopy. Therefore, a novel framework with multistep efficient finetuning is proposed in this work. In each epoch of end-to-end training, the process is divided into three steps, including optical flow registration, multiscale image decomposition and multiple transformation alignments. At each step, only the related networks are trained without interference of irrelevant information. Based on parameter-efficient finetuning on the foundation model, the proposed method achieves state-of-the-art performance on self-supervised depth estimation on SCARED dataset and zero-shot depth estimation on Hamlyn dataset, with 4\%$\sim$10\% lower error. The evaluation code of this work has been published on https://github.com/BaymaxShao/EndoMUST. |
|
| Leveraging Influence Functions for Resampling Data in Physics-Informed Neural Networks |
GitHub |
Physics-informed neural networks (PINNs) offer a powerful approach to solving partial differential equations (PDEs), which are ubiquitous in the quantitative sciences. Applied to both forward and inverse problems across various scientific domains, PINNs have recently emerged as a valuable tool in the field of scientific machine learning. A key aspect of their training is that the data -- spatio-temporal points sampled from the PDE's input domain -- are readily available. Influence functions, a tool from the field of explainable AI (XAI), approximate the effect of individual training points on the model, enhancing interpretability. In the present work, we explore the application of influence function-based sampling approaches for the training data. Our results indicate that such targeted resampling based on data attribution methods has the potential to enhance prediction accuracy in physics-informed neural networks, demonstrating a practical application of an XAI method in PINN training. |
|
| Explainable Rule Application via Structured Prompting: A Neural-Symbolic Approach |
GitHub |
Large Language Models (LLMs) excel in complex reasoning tasks but struggle with consistent rule application, exception handling, and explainability, particularly in domains like legal analysis that require both natural language understanding and precise logical inference. This paper introduces a structured prompting framework that decomposes reasoning into three verifiable steps: entity identification, property extraction, and symbolic rule application. By integrating neural and symbolic approaches, our method leverages LLMs' interpretive flexibility while ensuring logical consistency through formal verification. The framework externalizes task definitions, enabling domain experts to refine logical structures without altering the architecture. Evaluated on the LegalBench hearsay determination task, our approach significantly outperformed baselines, with OpenAI o-family models showing substantial improvements - o1 achieving an F1 score of 0.929 and o3-mini reaching 0.867 using structured decomposition with complementary predicates, compared to their few-shot baselines of 0.714 and 0.74 respectively. This hybrid neural-symbolic system offers a promising pathway for transparent and consistent rule-based reasoning, suggesting potential for explainable AI applications in structured legal reasoning tasks. |
|
| Large Language Models are Near-Optimal Decision-Makers with a Non-Human Learning Behavior |
GitHub |
Human decision-making belongs to the foundation of our society and civilization, but we are on the verge of a future where much of it will be delegated to artificial intelligence. The arrival of Large Language Models (LLMs) has transformed the nature and scope of AI-supported decision-making; however, the process by which they learn to make decisions, compared to humans, remains poorly understood. In this study, we examined the decision-making behavior of five leading LLMs across three core dimensions of real-world decision-making: uncertainty, risk, and set-shifting. Using three well-established experimental psychology tasks designed to probe these dimensions, we benchmarked LLMs against 360 newly recruited human participants. Across all tasks, LLMs often outperformed humans, approaching near-optimal performance. Moreover, the processes underlying their decisions diverged fundamentally from those of humans. On the one hand, our finding demonstrates the ability of LLMs to manage uncertainty, calibrate risk, and adapt to changes. On the other hand, this disparity highlights the risks of relying on them as substitutes for human judgment, calling for further inquiry. |
|
| JETHICS: Japanese Ethics Understanding Evaluation Dataset |
GitHub |
In this work, we propose JETHICS, a Japanese dataset for evaluating ethics understanding of AI models. JETHICS contains 78K examples and is built by following the construction methods of the existing English ETHICS dataset. It includes four categories based normative theories and concepts from ethics and political philosophy; and one representing commonsense morality. Our evaluation experiments on non-proprietary large language models (LLMs) and on GPT-4o reveal that even GPT-4o achieves only an average score of about 0.7, while the best-performing Japanese LLM attains around 0.5, indicating a relatively large room for improvement in current LLMs. |
|
| FinCoT: Grounding Chain-of-Thought in Expert Financial Reasoning |
GitHub |
This paper presents FinCoT, a structured chain-of-thought (CoT) prompting approach that incorporates insights from domain-specific expert financial reasoning to guide the reasoning traces of large language models. We investigate that there are three main prompting styles in FinNLP: (1) standard prompting--zero-shot prompting; (2) unstructured CoT--CoT prompting without an explicit reasoning structure, such as the use of tags; and (3) structured CoT prompting--CoT prompting with explicit instructions or examples that define structured reasoning steps. Previously, FinNLP has primarily focused on prompt engineering with either standard or unstructured CoT prompting. However, structured CoT prompting has received limited attention in prior work. Furthermore, the design of reasoning structures in structured CoT prompting is often based on heuristics from non-domain experts. In this study, we investigate each prompting approach in FinNLP. We evaluate the three main prompting styles and FinCoT on CFA-style questions spanning ten financial domains. We observe that FinCoT improves performance from 63.2% to 80.5% and Qwen-2.5-7B-Instruct from 69.7% to 74.2%, while reducing generated tokens eight-fold compared to structured CoT prompting. Our findings show that domain-aligned structured prompts not only improve performance and reduce inference costs but also yield more interpretable and expert-aligned reasoning traces. |
|
| Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details |
GitHub |
In this report, we present Hunyuan3D 2.5, a robust suite of 3D diffusion models aimed at generating high-fidelity and detailed textured 3D assets. Hunyuan3D 2.5 follows two-stages pipeline of its previous version Hunyuan3D 2.0, while demonstrating substantial advancements in both shape and texture generation. In terms of shape generation, we introduce a new shape foundation model -- LATTICE, which is trained with scaled high-quality datasets, model-size, and compute. Our largest model reaches 10B parameters and generates sharp and detailed 3D shape with precise image-3D following while keeping mesh surface clean and smooth, significantly closing the gap between generated and handcrafted 3D shapes. In terms of texture generation, it is upgraded with phyiscal-based rendering (PBR) via a novel multi-view architecture extended from Hunyuan3D 2.0 Paint model. Our extensive evaluation shows that Hunyuan3D 2.5 significantly outperforms previous methods in both shape and end-to-end texture generation. |
|
| RiOT: Efficient Prompt Refinement with Residual Optimization Tree |
GitHub |
Recent advancements in large language models (LLMs) have highlighted their potential across a variety of tasks, but their performance still heavily relies on the design of effective prompts. Existing methods for automatic prompt optimization face two challenges: lack of diversity, limiting the exploration of valuable and innovative directions and semantic drift, where optimizations for one task can degrade performance in others. To address these issues, we propose Residual Optimization Tree (RiOT), a novel framework for automatic prompt optimization. RiOT iteratively refines prompts through text gradients, generating multiple semantically diverse candidates at each step, and selects the best prompt using perplexity. Additionally, RiOT incorporates the text residual connection to mitigate semantic drift by selectively retaining beneficial content across optimization iterations. A tree structure efficiently manages the optimization process, ensuring scalability and flexibility. Extensive experiments across five benchmarks, covering commonsense, mathematical, logical, temporal, and semantic reasoning, demonstrate that RiOT outperforms both previous prompt optimization methods and manual prompting. |
|
| Can AI Dream of Unseen Galaxies? Conditional Diffusion Model for Galaxy Morphology Augmentation |
GitHub |
Observational astronomy relies on visual feature identification to detect critical astrophysical phenomena. While machine learning (ML) increasingly automates this process, models often struggle with generalization in large-scale surveys due to the limited representativeness of labeled datasets -- whether from simulations or human annotation -- a challenge pronounced for rare yet scientifically valuable objects. To address this, we propose a conditional diffusion model to synthesize realistic galaxy images for augmenting ML training data. Leveraging the Galaxy Zoo 2 dataset which contains visual feature -- galaxy image pairs from volunteer annotation, we demonstrate that our model generates diverse, high-fidelity galaxy images closely adhere to the specified morphological feature conditions. Moreover, this model enables generative extrapolation to project well-annotated data into unseen domains and advancing rare object detection. Integrating synthesized images into ML pipelines improves performance in standard morphology classification, boosting completeness and purity by up to 30\% across key metrics. For rare object detection, using early-type galaxies with prominent dust lane features ( $\sim$0.1\% in GZ2 dataset) as a test case, our approach doubled the number of detected instances from 352 to 872, compared to previous studies based on visual inspection. This study highlights the power of generative models to bridge gaps between scarce labeled data and the vast, uncharted parameter space of observational astronomy and sheds insight for future astrophysical foundation model developments. Our project homepage is available at https://galaxysd-webpage.streamlit.app/. |
|
| Floating-Point Neural Networks Are Provably Robust Universal Approximators |
GitHub |
The classical universal approximation (UA) theorem for neural networks establishes mild conditions under which a feedforward neural network can approximate a continuous function $f$ with arbitrary accuracy. A recent result shows that neural networks also enjoy a more general interval universal approximation (IUA) theorem, in the sense that the abstract interpretation semantics of the network using the interval domain can approximate the direct image map of $f$ (i.e., the result of applying $f$ to a set of inputs) with arbitrary accuracy. These theorems, however, rest on the unrealistic assumption that the neural network computes over infinitely precise real numbers, whereas their software implementations in practice compute over finite-precision floating-point numbers. An open question is whether the IUA theorem still holds in the floating-point setting. This paper introduces the first IUA theorem for floating-point neural networks that proves their remarkable ability to perfectly capture the direct image map of any rounded target function $f$, showing no limits exist on their expressiveness. Our IUA theorem in the floating-point setting exhibits material differences from the real-valued setting, which reflects the fundamental distinctions between these two computational models. This theorem also implies surprising corollaries, which include (i) the existence of provably robust floating-point neural networks; and (ii) the computational completeness of the class of straight-line programs that use only floating-point additions and multiplications for the class of all floating-point programs that halt. |
|
| Reranking-based Generation for Unbiased Perspective Summarization |
GitHub |
Generating unbiased summaries in real-world settings such as political perspective summarization remains a crucial application of Large Language Models (LLMs). Yet, existing evaluation frameworks rely on traditional metrics for measuring key attributes such as coverage and faithfulness without verifying their applicability, and efforts to develop improved summarizers are still nascent. We address these gaps by (1) identifying reliable metrics for measuring perspective summary quality, and (2) investigating the efficacy of LLM-based methods beyond zero-shot inference. Namely, we build a test set for benchmarking metric reliability using human annotations and show that traditional metrics underperform compared to language model-based metrics, which prove to be strong evaluators. Using these metrics, we show that reranking-based methods yield strong results, and preference tuning with synthetically generated and reranking-labeled data further boosts performance. Our findings aim to contribute to the reliable evaluation and development of perspective summarization methods. |
|
| One Period to Rule Them All: Identifying Critical Learning Periods in Deep Networks |
GitHub |
Critical Learning Periods comprehend an important phenomenon involving deep learning, where early epochs play a decisive role in the success of many training recipes, such as data augmentation. Existing works confirm the existence of this phenomenon and provide useful insights. However, the literature lacks efforts to precisely identify when critical periods occur. In this work, we fill this gap by introducing a systematic approach for identifying critical periods during the training of deep neural networks, focusing on eliminating computationally intensive regularization techniques and effectively applying mechanisms for reducing computational costs, such as data pruning. Our method leverages generalization prediction mechanisms to pinpoint critical phases where training recipes yield maximum benefits to the predictive ability of models. By halting resource-intensive recipes beyond these periods, we significantly accelerate the learning phase and achieve reductions in training time, energy consumption, and CO$_2$ emissions. Experiments on standard architectures and benchmarks confirm the effectiveness of our method. Specifically, we achieve significant milestones by reducing the training time of popular architectures by up to 59.67%, leading to a 59.47% decrease in CO$_2$ emissions and a 60% reduction in financial costs, without compromising performance. Our work enhances understanding of training dynamics and paves the way for more sustainable and efficient deep learning practices, particularly in resource-constrained environments. In the era of the race for foundation models, we believe our method emerges as a valuable framework. The repository is available at https://github.com/baunilhamarga/critical-periods |
|
| InstructTTSEval: Benchmarking Complex Natural-Language Instruction Following in Text-to-Speech Systems |
GitHub |
In modern speech synthesis, paralinguistic information--such as a speaker's vocal timbre, emotional state, and dynamic prosody--plays a critical role in conveying nuance beyond mere semantics. Traditional Text-to-Speech (TTS) systems rely on fixed style labels or inserting a speech prompt to control these cues, which severely limits flexibility. Recent attempts seek to employ natural-language instructions to modulate paralinguistic features, substantially improving the generalization of instruction-driven TTS models. Although many TTS systems now support customized synthesis via textual description, their actual ability to interpret and execute complex instructions remains largely unexplored. In addition, there is still a shortage of high-quality benchmarks and automated evaluation metrics specifically designed for instruction-based TTS, which hinders accurate assessment and iterative optimization of these models. To address these limitations, we introduce InstructTTSEval, a benchmark for measuring the capability of complex natural-language style control. We introduce three tasks, namely Acoustic-Parameter Specification, Descriptive-Style Directive, and Role-Play, including English and Chinese subsets, each with 1k test cases (6k in total) paired with reference audio. We leverage Gemini as an automatic judge to assess their instruction-following abilities. Our evaluation of accessible instruction-following TTS systems highlights substantial room for further improvement. We anticipate that InstructTTSEval will drive progress toward more powerful, flexible, and accurate instruction-following TTS. |
|
| MambaHash: Visual State Space Deep Hashing Model for Large-Scale Image Retrieval |
GitHub |
Deep image hashing aims to enable effective large-scale image retrieval by mapping the input images into simple binary hash codes through deep neural networks. More recently, Vision Mamba with linear time complexity has attracted extensive attention from researchers by achieving outstanding performance on various computer tasks. Nevertheless, the suitability of Mamba for large-scale image retrieval tasks still needs to be explored. Towards this end, we propose a visual state space hashing model, called MambaHash. Concretely, we propose a backbone network with stage-wise architecture, in which grouped Mamba operation is introduced to model local and global information by utilizing Mamba to perform multi-directional scanning along different groups of the channel. Subsequently, the proposed channel interaction attention module is used to enhance information communication across channels. Finally, we meticulously design an adaptive feature enhancement module to increase feature diversity and enhance the visual representation capability of the model. We have conducted comprehensive experiments on three widely used datasets: CIFAR-10, NUS-WIDE and IMAGENET. The experimental results demonstrate that compared with the state-of-the-art deep hashing methods, our proposed MambaHash has well efficiency and superior performance to effectively accomplish large-scale image retrieval tasks. Source code is available https://github.com/shuaichaochao/MambaHash.git |
|
| Malware Classification Leveraging NLP & Machine Learning for Enhanced Accuracy |
GitHub |
This paper investigates the application of natural language processing (NLP)-based n-gram analysis and machine learning techniques to enhance malware classification. We explore how NLP can be used to extract and analyze textual features from malware samples through n-grams, contiguous string or API call sequences. This approach effectively captures distinctive linguistic patterns among malware and benign families, enabling finer-grained classification. We delve into n-gram size selection, feature representation, and classification algorithms. While evaluating our proposed method on real-world malware samples, we observe significantly improved accuracy compared to the traditional methods. By implementing our n-gram approach, we achieved an accuracy of 99.02% across various machine learning algorithms by using hybrid feature selection technique to address high dimensionality. Hybrid feature selection technique reduces the feature set to only 1.6% of the original features. |
|
| Watermarking Autoregressive Image Generation |
GitHub |
Watermarking the outputs of generative models has emerged as a promising approach for tracking their provenance. Despite significant interest in autoregressive image generation models and their potential for misuse, no prior work has attempted to watermark their outputs at the token level. In this work, we present the first such approach by adapting language model watermarking techniques to this setting. We identify a key challenge: the lack of reverse cycle-consistency (RCC), wherein re-tokenizing generated image tokens significantly alters the token sequence, effectively erasing the watermark. To address this and to make our method robust to common image transformations, neural compression, and removal attacks, we introduce (i) a custom tokenizer-detokenizer finetuning procedure that improves RCC, and (ii) a complementary watermark synchronization layer. As our experiments demonstrate, our approach enables reliable and robust watermark detection with theoretically grounded p-values. |
|
| AGC-Drive: A Large-Scale Dataset for Real-World Aerial-Ground Collaboration in Driving Scenarios |
GitHub |
By sharing information across multiple agents, collaborative perception helps autonomous vehicles mitigate occlusions and improve overall perception accuracy. While most previous work focus on vehicle-to-vehicle and vehicle-to-infrastructure collaboration, with limited attention to aerial perspectives provided by UAVs, which uniquely offer dynamic, top-down views to alleviate occlusions and monitor large-scale interactive environments. A major reason for this is the lack of high-quality datasets for aerial-ground collaborative scenarios. To bridge this gap, we present AGC-Drive, the first large-scale real-world dataset for Aerial-Ground Cooperative 3D perception. The data collection platform consists of two vehicles, each equipped with five cameras and one LiDAR sensor, and one UAV carrying a forward-facing camera and a LiDAR sensor, enabling comprehensive multi-view and multi-agent perception. Consisting of approximately 120K LiDAR frames and 440K images, the dataset covers 14 diverse real-world driving scenarios, including urban roundabouts, highway tunnels, and on/off ramps. Notably, 19.5% of the data comprises dynamic interaction events, including vehicle cut-ins, cut-outs, and frequent lane changes. AGC-Drive contains 400 scenes, each with approximately 100 frames and fully annotated 3D bounding boxes covering 13 object categories. We provide benchmarks for two 3D perception tasks: vehicle-to-vehicle collaborative perception and vehicle-to-UAV collaborative perception. Additionally, we release an open-source toolkit, including spatiotemporal alignment verification tools, multi-agent visualization systems, and collaborative annotation utilities. The dataset and code are available at https://github.com/PercepX/AGC-Drive. |
|
| Probing the Robustness of Large Language Models Safety to Latent Perturbations |
GitHub |
Safety alignment is a key requirement for building reliable Artificial General Intelligence. Despite significant advances in safety alignment, we observe that minor latent shifts can still trigger unsafe responses in aligned models. We argue that this stems from the shallow nature of existing alignment methods, which focus on surface-level refusal behaviors without sufficiently altering internal representations. Consequently, small shifts in hidden activations can re-trigger harmful behaviors embedded in the latent space. To explore the robustness of safety alignment to latent perturbations, we introduce a probing method that measures the Negative Log-Likelihood of the original response generated by the model. This probe quantifies local sensitivity in the latent space, serving as a diagnostic tool for identifying vulnerable directions. Based on this signal, we construct effective jailbreak trajectories, giving rise to the Activation Steering Attack (ASA). More importantly, these insights offer a principled foundation for improving alignment robustness. To this end, we introduce Layer-wise Adversarial Patch Training~(LAPT), a fine-tuning strategy that inject controlled perturbations into hidden representations during training. Experimental results highlight that LAPT strengthen alignment robustness without compromising general capabilities. Our findings reveal fundamental flaws in current alignment paradigms and call for representation-level training strategies that move beyond surface-level behavior supervision. Codes and results are available at https://github.com/Carol-gutianle/LatentSafety. |
|
| Generating Directed Graphs with Dual Attention and Asymmetric Encoding |
GitHub |
Directed graphs naturally model systems with asymmetric, ordered relationships, essential to applications in biology, transportation, social networks, and visual understanding. Generating such graphs enables tasks such as simulation, data augmentation and novel instance discovery; however, directed graph generation remains underexplored. We identify two key factors limiting progress in this direction: first, modeling edge directionality introduces a substantially larger dependency space, making the underlying distribution harder to learn; second, the absence of standardized benchmarks hinders rigorous evaluation. Addressing the former requires more expressive models that are sensitive to directional topologies. We propose Directo, the first generative model for directed graphs built upon the discrete flow matching framework. Our approach combines: (i) principled positional encodings tailored to asymmetric pairwise relations, (ii) a dual-attention mechanism capturing both incoming and outgoing dependencies, and (iii) a robust, discrete generative framework. To support evaluation, we introduce a benchmark suite covering synthetic and real-world datasets. It shows that our method performs strongly across diverse settings and even competes with specialized models for particular classes, such as directed acyclic graphs. Our results highlight the effectiveness and generality of our approach, establishing a solid foundation for future research in directed graph generation. |
|
| AutoHFormer: Efficient Hierarchical Autoregressive Transformer for Time Series Prediction |
GitHub |
Time series forecasting requires architectures that simultaneously achieve three competing objectives: (1) strict temporal causality for reliable predictions, (2) sub-quadratic complexity for practical scalability, and (3) multi-scale pattern recognition for accurate long-horizon forecasting. We introduce AutoHFormer, a hierarchical autoregressive transformer that addresses these challenges through three key innovations: 1) Hierarchical Temporal Modeling: Our architecture decomposes predictions into segment-level blocks processed in parallel, followed by intra-segment sequential refinement. This dual-scale approach maintains temporal coherence while enabling efficient computation. 2) Dynamic Windowed Attention: The attention mechanism employs learnable causal windows with exponential decay, reducing complexity while preserving precise temporal relationships. This design avoids both the anti-causal violations of standard transformers and the sequential bottlenecks of RNN hybrids. 3) Adaptive Temporal Encoding: a novel position encoding system is adopted to capture time patterns at multiple scales. It combines fixed oscillating patterns for short-term variations with learnable decay rates for long-term trends. Comprehensive experiments demonstrate that AutoHFormer 10.76X faster training and 6.06X memory reduction compared to PatchTST on PEMS08, while maintaining consistent accuracy across 96-720 step horizons in most of cases. These breakthroughs establish new benchmarks for efficient and precise time series modeling. Implementations of our method and all baselines in hierarchical autoregressive mechanism are available at https://github.com/lizzyhku/Autotime. |
|