mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 28 May 2025

594 papers

  1. Contraction-Aware Reinforcement Learning for Nonlinear Control with Statistical RobustnessDeep reinforcement learning methods → RL for robot locomotion and manipulation
  2. BLUR: A Benchmark for LLM Unlearning Robust to Forget-Retain OverlapLLM safety and security → Machine unlearning
  3. SimuGen: Multi-modal Agentic Framework for Constructing Block Diagram-Based Simulation ModelsLLM reasoning → Reasoning for agents, planning and code +1
  4. PALADIN : Robust Neural Fingerprinting for Text-to-Image Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
  5. Do You See Me : A Multidimensional Benchmark for Evaluating Visual Perception in Multimodal LLMsLLM reasoning → Multimodal reasoning +1
  6. Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient AmplifyingMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  7. ChatCFD: An LLM-Driven Agent for End-to-End CFD Automation with Structured Knowledge and ReasoningLLM reasoning → Spatial and embodied reasoning +1
  8. Enhancing Paraphrase Type Generation: The Impact of DPO and RLHF Evaluated with Human-Ranked DataLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  9. OSPO: Object-Centric Self-Improving Preference Optimization for Text-to-Image GenerationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +2
  10. Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness FrontiersRetrieval-augmented generation → RAG robustness and adaptive retrieval
  11. Rethinking Hybrid Retrieval: When Small Embeddings and LLM Re-ranking Beat Bigger ModelsLLM reasoning → Knowledge- and tool-augmented reasoning +1
  12. ACE-Step: A Step Towards Music Generation Foundation ModelDiffusion models → Audio, speech and music
  13. Enhancing Tool Learning in Large Language Models with Hierarchical Error ChecklistsLLM agents and tool use → Tool learning and function calling
  14. Decoding Dense Embeddings: Sparse Autoencoders for Interpreting and Discretizing Dense RetrievalMechanistic interpretability → SAE features and their applications
  15. Derailing Non-Answers via Logit Suppression at Output Subspace Boundaries in RLHF-Aligned Language ModelsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks
  16. Seven Security Challenges in Cross-domain Multi-agent LLM SystemsLLM agents and tool use → Agent threats, guardrails and governance
  17. Read Your Own Mind: Reasoning Helps Surface Self-Confidence Signals in LLMsLLM reasoning → Test-time compute and efficient thinking
  18. Evaluation Hallucination in Multi-Round Incomplete Information Lateral-Driven Reasoning TasksLLM reasoning → Reasoning benchmarks and evaluation
  19. SkewRoute: Training-Free LLM Routing for Knowledge Graph Retrieval-Augmented Generation via Score Skewness of Retrieved ContextRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  20. GeneBreaker: Jailbreak Attacks against DNA Language Models with Pathogenicity GuidanceLLM safety and security → Jailbreaking
  21. CoMaPOI: A Collaborative Multi-Agent Framework for Next POI Prediction Bridging the Gap Between Trajectory and LanguageLLM agents and tool use → Multimodal and embodied agents
  22. Benchmarking Abstract and Reasoning Abilities Through A Theoretical PerspectiveLLM reasoning → Reasoning benchmarks and evaluation
  23. EvoMoE: Expert Evolution in Mixture of Experts for Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  24. Reviewing Scientific Papers for Critical Problems With Reasoning LLMs: Baseline Approaches and Automatic EvaluationLLM reasoning → Knowledge- and tool-augmented reasoning
  25. NegVQA: Can Vision Language Models Understand Negation?Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  26. WorkForceAgent-R1: Incentivizing Reasoning Capability in LLM-based Web Agents via Reinforcement LearningLLM reasoning → Reasoning for agents, planning and code +1
  27. Is Noise Conditioning Necessary? A Unified Theory of Unconditional Graph Diffusion ModelsDiffusion models → Flow matching, time series and science
  28. Enhancing Study-Level Inference from Clinical Trial Papers via Reinforcement Learning-Based Numeric ReasoningLLM reasoning → Clinical and biomedical applications
  29. Leveraging Diffusion Models for Synthetic Data Augmentation in Protein Subcellular Localization ClassificationDiffusion models → Flow matching, time series and science
  30. Plug-and-Play Posterior Sampling for Blind Inverse ProblemsDiffusion models → Inverse problems and image restoration
  31. ER-Reason: A Benchmark Dataset for LLM Clinical Reasoning in the Emergency RoomLLM reasoning → Clinical and biomedical applications
  32. Re-ttention: Ultra Sparse Visual Generation via Attention Statistical ReshapeDiffusion models → Video generation
  33. cadrille: Multi-modal CAD Reconstruction with Reinforcement LearningDeep reinforcement learning methods → RL with diffusion and flow models
  34. Mustafar: Promoting Unstructured Sparsity for KV Cache Pruning in LLM InferenceEfficient LLM inference and serving → KV cache optimization
  35. Learning to Charge More: A Theoretical Study of Collusion by Q-Learning AgentsDeep reinforcement learning methods → Adversarial robustness and RL in finance
  36. VIGNETTE: Socially Grounded Bias Evaluation for Vision-Language ModelsMultimodal LLMs / vision-language models → Social bias and fairness in VLMs
  37. When Models Reason in Your Language: Controlling Thinking Language Comes at the Cost of AccuracyLLM reasoning → Reasoning benchmarks and evaluation
  38. Scaling Offline RL via Efficient and Expressive Shortcut ModelsOffline RL and imitation learning from data → Offline RL algorithms
  39. BinauralFlow: A Causal and Streamable Approach for High-Quality Binaural Speech Synthesis with Flow Matching ModelsDiffusion models → Audio, speech and music
  40. Operationalizing CaMeL: Strengthening LLM Defenses for Enterprise DeploymentLLM safety and security → Prompt injection and agent security
  41. RocqStar: Leveraging Similarity-driven Retrieval and Agentic Systems for Rocq generationLLM agents and tool use → Educational agents and math problem solving
  42. Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance StudyDiffusion models → Diffusion foundations and sampling
  43. Demystifying Adversarial Robustness in Diffusion Models: Compression, Randomness, and GeometryDiffusion models → Robustness, privacy and adversarial aspects
  44. Preference Learning with Response Time: Robust Losses and GuaranteesLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  45. A Large Language Model-Enabled Control Architecture for Dynamic Resource Capability Exploration in Multi-Agent Manufacturing SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  46. First Steps Towards Overhearing LLM Agents: A Case Study With Dungeons & Dragons GameplayLLM agents and tool use → Social simulation and multi-agent debate
  47. Anomalies by Synthesis: Anomaly Detection using Generative Diffusion Models for Off-Road NavigationDiffusion models → Flow matching, time series and science
  48. Evaluation of Cultural Competence of Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  49. Rhetorical Text-to-Image Generation via Two-layer Diffusion Policy OptimizationDiffusion models → Image generation, text-to-image and editing
  50. Calibrated Value-Aware Model Learning with Probabilistic Environment ModelsDeep reinforcement learning methods → RL theory and sample complexity
  51. In Dialogue with Intelligence: Rethinking Large Language Models as Collective KnowledgeLLM reasoning → Reasoning benchmarks and evaluation
  52. Pre-Training Curriculum for Multi-Token Prediction in Language ModelsEfficient LLM inference and serving → Speculative decoding
  53. Decomposing Elements of Problem Solving: What "Math" Does RL Teach?LLM reasoning → Reinforcement learning for reasoning
  54. HiDream-I1: A High-Efficient Image Generative Foundation Model with Sparse Diffusion TransformerDiffusion models → Diffusion foundations and sampling +1
  55. Design and testing of an agent chatbot supporting decision making with public transport dataLLM agents and tool use → General LLM agent frameworks and benchmarks
  56. When Does Neuroevolution Outcompete Reinforcement Learning in Transfer Learning Tasks?Deep reinforcement learning methods → Deep RL algorithms and representations
  57. Zero-Shot Vision Encoder Grafting via LLM SurrogatesMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  58. AutoL2S: Auto Long-Short Reasoning for Efficient Large Language ModelsLLM reasoning → Test-time compute and efficient thinking
  59. GuessArena: Guess Who I Am? A Self-Adaptive Framework for Evaluating LLMs in Domain-Specific Knowledge and ReasoningLLM reasoning → Reasoning for agents, planning and code
  60. Maximizing Confidence Alone Improves ReasoningLLM reasoning → Reinforcement learning for reasoning
  61. Position: Uncertainty Quantification Needs Reassessment for Large-language Model AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  62. VScan: Rethinking Visual Token Reduction for Efficient Large Vision-Language ModelsLLM reasoning → Multimodal reasoning +2
  63. The Climb Carves Wisdom Deeper Than the Summit: On the Noisy Rewards in Learning to ReasonLLM reasoning → Reinforcement learning for reasoning +1
  64. Sherlock: Self-Correcting Reasoning in Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
  65. On Learning Verifiers and Implications to Chain-of-Thought ReasoningLLM reasoning → Prompting and chain-of-thought reasoning
  66. Pre-training for Recommendation UnlearningLLM safety and security → Membership inference attacks
  67. WebDancer: Towards Autonomous Information Seeking AgencyLLM agents and tool use → Web, search, and research agents
  68. SPIRAL: Semantic-Aware Progressive LiDAR Scene Generation and UnderstandingWorld models → World modeling from LiDAR generation +1
  69. FastTD3: Simple, Fast, and Capable Reinforcement Learning for Humanoid ControlDeep reinforcement learning methods → RL for robot locomotion and manipulation
  70. Understanding (Un)Reliability of Steering Vectors in Language ModelsMechanistic interpretability → Activation steering methods
  71. Learning Composable Chains-of-ThoughtLLM reasoning → Prompting and chain-of-thought reasoning
  72. Spatial Knowledge Graph-Guided Multimodal SynthesisMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  73. SCIZOR: A Self-Supervised Approach to Data Curation for Large-Scale Imitation LearningOffline RL and imitation learning from data → Robot manipulation imitation learning
  74. Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel DecodingEfficient LLM inference and serving → Diffusion LLM and MoE inference
  75. The Entropy Mechanism of Reinforcement Learning for Reasoning Language ModelsLLM reasoning → Reinforcement learning for reasoning
  76. Machine Unlearning under OverparameterizationLLM safety and security → Machine unlearning
  77. SAM-R1: Leveraging SAM for Reward Feedback in Multimodal Segmentation via Reinforcement LearningLLM reasoning → Multimodal reasoning +1
  78. Self-Error-Instruct: Generalizing from Errors for LLMs Mathematical ReasoningLLM reasoning → Mathematical reasoning
  79. DocReRank: Single-Page Hard Negative Query Generation for Training Multi-Modal RAG RerankersRetrieval-augmented generation → Generation and context integration
  80. GitGoodBench: A Novel Benchmark For Evaluating Agentic Performance On GitLLM agents and tool use → Software engineering coding agents
  81. Less, but Better: Efficient Multilingual Expansion for LLMs via Layer-wise Mixture-of-ExpertsMixture-of-experts → MoE large language models
  82. Fusion Steering: Prompt-Specific Activation ControlMechanistic interpretability → Activation steering methods
  83. Agent-UniRAG: A Trainable Open-Source LLM Agent Framework for Unified Retrieval-Augmented Generation SystemsRetrieval-augmented generation → Agentic RAG, agents and memory +1
  84. ImageReFL: Balancing Quality and Diversity in Human-Aligned Diffusion ModelsDiffusion models → Diffusion and flow policies for robotics +1
  85. Do Large Language Models Think Like the Brain? Sentence-Level Evidences from Layer-Wise Embeddings and fMRILLM reasoning → Reasoning benchmarks and evaluation
  86. ClaimPKG: Enhancing Claim Verification via Pseudo-Subgraph Generation with Lightweight Specialized LLMLLM reasoning → Knowledge- and tool-augmented reasoning
  87. Emotion-o1: Adaptive Long Reasoning for Emotion Understanding in LLMsLLM reasoning → Audio-language model reasoning
  88. Scaling-up Perceptual Video Quality AssessmentMultimodal LLMs / vision-language models → Image editing and quality assessment
  89. TabularQGAN: A quantum generative model for tabular data synthesisSynthetic data and self-improvement for LLMs → Privacy-preserving tabular data synthesis
  90. Thinking with Generated ImagesLLM reasoning → Multimodal reasoning +1
  91. Inference-Time Scaling of Discrete Diffusion Models via Importance Weighting and Optimal Proposal DesignLLM reasoning → Diffusion reasoning and test-time scaling +1
  92. Multi-MLLM Knowledge Distillation for Out-of-Context News DetectionKnowledge distillation → Knowledge distillation for LLMs
  93. Surf2CT: Cascaded 3D Flow Matching Models for Torso 3D CT Synthesis from Skin SurfaceDiffusion models → Medical imaging and segmentation
  94. Sparsification and Reconstruction from the Perspective of Representation GeometryMechanistic interpretability → Sparse autoencoder training and evaluation
  95. Communication-Efficient Desire Alignment for Embodied Agent-Human AdaptationLLM agents and tool use → General LLM agent frameworks and benchmarks
  96. EvolveSearch: An Iterative Self-Evolving Search AgentLLM agents and tool use → Web, search, and research agents +1
  97. Demystifying the Paradox of Importance Sampling with an Estimated History-Dependent Behavior Policy in Off-Policy EvaluationDeep reinforcement learning methods → RL theory and sample complexity
  98. Cascaded 3D Diffusion Models for Whole-body 3D 18-F FDG PET/CT synthesis from DemographicsDiffusion models → Medical imaging and segmentation
  99. Topological Structure Learning Should Be A Research Priority for LLM-Based Multi-Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  100. Fostering Video Reasoning via Next-Event PredictionLLM reasoning → Multimodal reasoning
All 594
  1. First SFT, Second RL, Third UPT: Continual Improving Multi-Modal LLM Reasoning via Unsupervised Post-TrainingLLM reasoning → Reinforcement learning for reasoning +1
  2. AI Mathematician: Towards Fully Automated Frontier Mathematical ResearchLLM reasoning → Mathematical reasoning
  3. Fully Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
  4. RAG-Zeval: Towards Robust and Interpretable Evaluation on RAG Responses through End-to-End Rule-Guided ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning +1
  5. Zero-Shot 3D Visual Grounding from Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  6. Scaling Reasoning without AttentionLLM reasoning → Test-time compute and efficient thinking
  7. GeoDrive: 3D Geometry-Informed Driving World Model with Precise Action ControlWorld models → World models for autonomous driving +1
  8. Mitigating Overthinking in Large Reasoning Models via Manifold SteeringLLM reasoning → Test-time compute and efficient thinking
  9. Self-Reflective Reinforcement Learning for Diffusion-based Image Reasoning GenerationLLM reasoning → Multimodal reasoning +1
  10. Zooming from Context to Cue: Hierarchical Preference Optimization for Multi-Image MLLMsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  11. Physics-Informed Distillation of Diffusion Models for PDE-Constrained GenerationDiffusion models → Flow matching, time series and science
  12. Pangu Embedded: An Efficient Dual-system LLM Reasoner with MetacognitionLLM reasoning → Reinforcement learning for reasoning
  13. AgentDNS: A Root Domain Naming System for LLM AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  14. Text2Grad: Reinforcement Learning from Natural Language FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
  15. Advancing Multimodal Reasoning via Reinforcement Learning with Cold StartLLM reasoning → Multimodal reasoning
  16. Advancing Expert Specialization for Better MoEMixture-of-experts → MoE large language models
  17. A Closer Look on Memorization in Tabular Diffusion Model: A Data-Centric PerspectiveDiffusion models → Diffusion foundations and sampling
  18. Flying Pigs, FaR and Beyond: Evaluating LLM Reasoning in Counterfactual WorldsLLM reasoning → Reasoning benchmarks and evaluation
  19. Skywork Open Reasoner 1 Technical ReportLLM reasoning → Reasoning benchmarks and evaluation
  20. From Large AI Models to Agentic AI: A Tutorial on Future Intelligent CommunicationsLLM agents and tool use → Agentic AI for wireless networks
  21. From Dormant to Deleted: Tamper-Resistant Unlearning Through Weight-Space RegularizationLLM safety and security → Machine unlearning
  22. Transformers Pretrained on Procedural Data Contain Modular Structures for Algorithmic ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  23. Versatile Cardiovascular Signal Generation with a Unified Diffusion TransformerDiffusion models → Medical imaging and segmentation
  24. IKIWISI: An Interactive Visual Pattern Generator for Evaluating the Reliability of Vision-Language Models Without Ground TruthMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  25. Voice CMS: updating the knowledge base of a digital assistant through conversationLLM agents and tool use → General LLM agent frameworks and benchmarks
  26. Adaptive Detoxification: Safeguarding General Capabilities of LLMs through Toxicity-Aware Knowledge EditingLLM safety and security → Safety alignment, refusal and guardrails
  27. Compensating for Data with Reasoning: Low-Resource Machine Translation with LLMsLLM reasoning → Reasoning benchmarks and evaluation
  28. Rethinking the Unsolvable: When In-Context Search Meets Test-Time ScalingLLM reasoning → Test-time compute and efficient thinking
  29. Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language ModelsLLM safety and security → Jailbreaking
  30. Revisiting Group Relative Policy Optimization: Insights into On-Policy and Off-Policy TrainingLLM reasoning → Reinforcement learning for reasoning
  31. Kronecker Factorization Improves Efficiency and Interpretability of Sparse AutoencodersMechanistic interpretability → SAE features and their applications
  32. StateSpaceDiffuser: Bringing Long Context to Diffusion World ModelsWorld models → Video-generation world models and simulators +1
  33. BioHopR: A Benchmark for Multi-Hop, Multi-Answer Reasoning in Biomedical DomainLLM reasoning → Clinical and biomedical applications
  34. Look & Mark: Leveraging Radiologist Eye Fixations and Bounding boxes in Multimodal Large Language Models for Chest X-ray Report GenerationMultimodal LLMs / vision-language models → Medical vision-language models
  35. From Accuracy to Robustness: A Study of Rule- and Model-based Verifiers in Mathematical ReasoningLLM reasoning → Reinforcement learning for reasoning
  36. Latent Reasoning via Sentence Embedding PredictionLLM reasoning → Test-time compute and efficient thinking
  37. Investigating Mechanisms for In-Context Vision Language BindingMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  38. Physics-inspired Generative AI models via real hardware-based noisy quantum diffusionDiffusion models → Diffusion foundations and sampling
  39. Efficient Leave-one-out Approximation in LLM Multi-agent Debate Based on IntrospectionLLM agents and tool use → Social simulation and multi-agent debate
  40. Speculative Decoding Meets Quantization: Compatibility Evaluation and Hierarchical Framework DesignEfficient LLM inference and serving → Speculative decoding
  41. Reverse Preference Optimization for Complex Instruction FollowingLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  42. Q-VDiT: Towards Accurate Quantization and Distillation of Video-Generation Diffusion TransformersDiffusion models → Diffusion foundations and sampling
  43. Unifying Continuous and Discrete Text Diffusion with Non-simultaneous Diffusion ProcessesDiffusion models → Discrete and text diffusion
  44. ForceVLA: Enhancing VLA Models with a Force-aware MoE for Contact-rich ManipulationVision-language-action models → Tactile, force-aware and humanoid VLA +1
  45. Oryx: a Scalable Sequence Model for Many-Agent Coordination in Offline MARLOffline RL and imitation learning from data → Offline multi-agent RL
  46. What Makes a Good Reasoning Chain? Uncovering Structural Patterns in Long Chain-of-Thought ReasoningLLM reasoning → Prompting and chain-of-thought reasoning
  47. 3D Question Answering via only 2D Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  48. Limited Generalizability in Argument Mining: State-Of-The-Art Models Learn Datasets, Not ArgumentsLLM reasoning → Reasoning for agents, planning and code
  49. RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative DecodingEfficient LLM inference and serving → Early exit and edge inference +1
  50. Enhancing Long-Chain Reasoning Distillation through Error-Aware Self-ReflectionLLM reasoning → Prompting and chain-of-thought reasoning +1
  51. What Makes for Text to 360-degree Panorama Generation with Stable Diffusion?Diffusion models → 3D, point cloud and scene generation
  52. THINK-Bench: Evaluating Thinking Efficiency and Chain-of-Thought Quality of Large Reasoning ModelsLLM reasoning → Test-time compute and efficient thinking
  53. Autoregression-free video prediction using diffusion model for mitigating error propagationDiffusion models → Video generation
  54. AudioTurbo: Fast Text-to-Audio Generation with Rectified DiffusionDiffusion models → Audio, speech and music
  55. Mixture-of-Retrieval Experts for Reasoning-Guided Multimodal Knowledge ExploitationLLM reasoning → Multimodal reasoning +2
  56. ReinFlow: Fine-tuning Flow Matching Policy with Online Reinforcement LearningDiffusion models → Diffusion and flow policies for robotics +1
  57. VIRAL: Vision-grounded Integration for Reward design And LearningLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  58. High Volume Rate 3D Ultrasound Reconstruction with Diffusion ModelsDiffusion models → Medical imaging and segmentation
  59. On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech RecognitionMixture-of-experts → Multimodal MoE models
  60. Delayed-KD: Delayed Knowledge Distillation based CTC for Low-Latency Streaming ASRKnowledge distillation → Speech and audio distillation
  61. Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R2)GRPOLLM reasoning → Knowledge- and tool-augmented reasoning
  62. From Failures to Fixes: LLM-Driven Scenario Repair for Self-Evolving Autonomous DrivingSynthetic data and self-improvement for LLMs → Self-evolving LLM agents
  63. Safeguarding Privacy of Retrieval Data against Membership Inference Attacks: Is This Query Too Close to Home?Retrieval-augmented generation → Privacy and security of RAG +1
  64. AudioGenie: A Training-Free Multi-Agent Framework for Diverse Multimodality-to-Multiaudio GenerationMixture-of-experts → Multimodal MoE models
  65. Reinforced Reasoning for Embodied PlanningLLM reasoning → Spatial and embodied reasoning
  66. Detecting Undesired Process Behavior by Means of Retrieval Augmented GenerationRetrieval-augmented generation → RAG for code
  67. OmniAD: Detect and Understand Industrial Anomaly via Multimodal ReasoningLLM reasoning → Chain-of-thought reasoning for driving
  68. Balanced Token Pruning: Accelerating Vision Language Models Beyond Local OptimizationMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  69. Jailbreak Distillation: Renewable Safety BenchmarkingLLM safety and security → Jailbreaking
  70. Analysis and Evaluation of Synthetic Data Generation in Speech Dysfluency DetectionSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  71. Improving Respiratory Sound Classification with Architecture-Agnostic Knowledge Distillation from EnsemblesKnowledge distillation → Speech and audio distillation
  72. VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement LearningRetrieval-augmented generation → Multimodal RAG
  73. The Price of a Second Thought: On the Evaluation of Reasoning Efficiency in Large Language ModelsLLM reasoning → Test-time compute and efficient thinking
  74. Align-DA: Align Score-based Atmospheric Data Assimilation with Multiple PreferencesDiffusion models → Flow matching, time series and science +1
  75. Efficiently Enhancing General Agents With Hierarchical-categorical MemoryLLM agents and tool use → Agent memory systems
  76. D-Fusion: Direct Preference Optimization for Aligning Diffusion Models with Visually Consistent SamplesDiffusion models → Diffusion and flow policies for robotics +1
  77. Collaborative Learning for Unsupervised Multimodal Remote Sensing Image Registration: Integrating Self-Supervision and MIM-Guided Diffusion-Based Image TranslationDiffusion models → Inverse problems and image restoration
  78. VRAG: Learning World Models for Interactive Video GenerationWorld models → Video-generation world models and simulators +1
  79. Learning Compositional Behaviors from Demonstration and LanguageOffline RL and imitation learning from data → Robot manipulation imitation learning
  80. Pearl: A Multimodal Culturally-Aware Arabic Instruction DatasetMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  81. Two-Stage Feature Generation with Transformer and Reinforcement LearningDeep reinforcement learning methods → RL with diffusion and flow models
  82. DvD: Unleashing a Generative Paradigm for Document Dewarping via Coordinates-based Diffusion ModelDiffusion models → Image generation, text-to-image and editing
  83. DORAEMON: Decentralized Ontology-aware Reliable Agent with Enhanced Memory Oriented NavigationLLM agents and tool use → Multimodal and embodied agents
  84. Seeing the Threat: Vulnerabilities in Vision-Language Models to Adversarial AttackMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  85. MapStory: Prototyping Editable Map Animations with LLM AgentsLLM agents and tool use → Multimodal and embodied agents
  86. UI-Evol: Automatic Knowledge Evolving for Computer Use AgentsLLM agents and tool use → GUI and mobile agents
  87. LaMDAgent: An Autonomous Framework for Post-Training Pipeline Optimization via LLM AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  88. A2Seek: Towards Reasoning-Centric Benchmark for Aerial Anomaly UnderstandingLLM reasoning → Spatial and embodied reasoning
  89. One-Way Ticket:Time-Independent Unified Encoder for Distilling Text-to-Image Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  90. Cross-modal RAG: Sub-dimensional Text-to-Image Retrieval-Augmented GenerationRetrieval-augmented generation → Multimodal RAG
  91. Towards Comprehensive Scene Understanding: Integrating First and Third-Person Views for LVLMsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  92. Test-Time Scaling with Repeated Sampling Improves Multilingual Text GenerationLLM reasoning → Test-time compute and efficient thinking
  93. RISE: Reasoning Enhancement via Iterative Self-Exploration in Multi-hop Question AnsweringLLM reasoning → Knowledge- and tool-augmented reasoning
  94. RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS EnvironmentsLLM agents and tool use → Agent threats, guardrails and governance +1
  95. From Reasoning to Learning: A Survey on Hypothesis Discovery and Rule Learning with Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  96. Towards Efficient Key-Value Cache Management for Prefix Prefilling in LLM InferenceEfficient LLM inference and serving → KV cache optimization
  97. Reinforcement Learning for Out-of-Distribution Reasoning in LLMs: An Empirical Study on Diagnosis-Related Group CodingLLM reasoning → Clinical and biomedical applications
  98. Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and TaxonomyLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  99. ChatVLA-2: Vision-Language-Action Model with Open-World Embodied Reasoning from Pretrained KnowledgeLLM reasoning → Spatial and embodied reasoning +1
  100. Reference-Guided Identity Preserving Face RestorationDiffusion models → Inverse problems and image restoration
  101. CAST: Contrastive Adaptation and Distillation for Semi-Supervised Instance SegmentationKnowledge distillation → Detection and dense prediction distillation
  102. Co-Saving: Resource Aware Multi-Agent Collaboration for Software DevelopmentLLM agents and tool use → General LLM agent frameworks and benchmarks
  103. SIPO: Stabilized and Improved Preference Optimization for Aligning Diffusion ModelsDiffusion models → Diffusion and flow policies for robotics +1
  104. Almost Linear Convergence under Minimal Score Assumptions: Quantized Transition DiffusionDiffusion models → Diffusion foundations and sampling
  105. EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache ReuseEfficient LLM inference and serving → KV cache optimization
  106. EPiC: Efficient Video Camera Control Learning with Precise Anchor-Video GuidanceDiffusion models → Video generation
  107. Targeted Unlearning Using Perturbed Sign Gradient Methods With Applications On Medical ImagesLLM safety and security → Machine unlearning
  108. Evaluating the Retrieval Robustness of Large Language ModelsRetrieval-augmented generation → RAG robustness and adaptive retrieval
  109. A Provable Approach for End-to-End Safe Reinforcement LearningDeep reinforcement learning methods → Safe and constrained RL
  110. Streaming Flow Policy: Simplifying diffusion/flow-matching policies by treating action trajectories as flow trajectoriesDiffusion models → Diffusion and flow policies for robotics +1
  111. Beyond Perception: Evaluating Abstract Visual Reasoning through Multi-Stage TaskLLM reasoning → Multimodal reasoning +1
  112. FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token EmbeddingsDiffusion models → Diffusion foundations and sampling
  113. Test-Time Adaptation of Vision-Language Models for Open-Vocabulary Semantic SegmentationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  114. An Optimistic Algorithm for online CMDPS with Anytime Adversarial ConstraintsDeep reinforcement learning methods → RL theory and sample complexity
  115. MAIA: A Collaborative Medical AI Platform for Integrated Healthcare Innovation
  116. Global Context-aware Representation Learning for Spatially Resolved Transcriptomics
  117. DeepRTL2: A Versatile Model for RTL-Related Tasks
  118. CoC: Chain-of-Cancer based on Cross-Modal Autoregressive Traction for Survival Prediction
  119. SemIRNet: A Semantic Irony Recognition Network for Multimodal Sarcasm Detection
  120. Continuous Evolution Pool: Taming Recurring Concept Drift in Online Time Series Forecasting
  121. GUST: Quantifying Free-Form Geometric Uncertainty of Metamaterials Using Small Data
  122. Identifying critical residues of a protein using meaningfully-thresholded Random Geometric Graphs
  123. NOCL: Node-Oriented Conceptualization LLM for Graph Tasks without Message Passing
  124. Contextual Memory Intelligence -- A Foundational Paradigm for Human-AI Collaboration and Reflective Generative AI Systems
  125. MR.NAVI: Mixed-Reality Navigation Assistant for the Visually Impaired
  126. Speaking images. A novel framework for the automated self-description of artworks
  127. Triple Attention Transformer Architecture for Time-Dependent Concrete Creep Prediction
  128. Improving Out-of-Distribution Detection with Markov Logic Networks
  129. EdgeVidSum: Real-Time Personalized Video Summarization at the Edge
  130. Improvement of human health lifespan with hybrid group pose estimation methods
  131. Farm-LightSeek: An Edge-centric Multimodal Agricultural IoT Data Analytics Framework with Lightweight LLMs
  132. Distributionally Robust Wireless Semantic Communication with Large AI Models
  133. DistMLIP: A Distributed Inference Platform for Machine Learning Interatomic Potentials
  134. Dynamic-Aware Video Distillation: Optimizing Temporal Resolution Based on Video Semantics
  135. Fairness through Feedback: Addressing Algorithmic Misgendering in Automatic Gender Recognition
  136. Are classical deep neural networks weakly adversarially robust?
  137. Research on Driving Scenario Technology Based on Multimodal Large Lauguage Model Optimization
  138. Improving statistical learning methods via features selection without replacement sampling and random projection
  139. Using LLMs to Advance the Cognitive Science of Collectives
  140. Graph Contrastive Learning for Optimizing Sparse Data in Recommender Systems with LightGCL
  141. Risks of AI-driven product development and strategies for their mitigation
  142. Probabilistic intraday electricity price forecasting using generative machine learning
  143. From Motion to Behavior: Hierarchical Modeling of Humanoid Generative Behavior Control
  144. ASyMOB: Algebraic Symbolic Mathematical Operations Benchmark
  145. CADRE: Customizable Assurance of Data Readiness in Privacy-Preserving Federated Learning
  146. Scalable, Symbiotic, AI and Non-AI Agent Based Parallel Discrete Event Simulations
  147. Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation
  148. Fair Document Valuation in LLM Summaries via Shapley Values
  149. Measuring Sycophancy of Language Models in Multi-turn Dialogues
  150. Exploring the Landscape of Text-to-SQL with Large Language Models: Progresses, Challenges and Opportunities
  151. Large Language Models Often Know When They Are Being Evaluated
  152. Say What You Mean: Natural Language Access Control with Large Language Models for Internet of Things
  153. Patient-Aware Feature Alignment for Robust Lung Sound Classification:Cohesion-Separation and Global Alignment Losses
  154. LegalSearchLM: Rethinking Legal Case Retrieval as Legal Elements Generation
  155. ICH-Qwen: A Large Language Model Towards Chinese Intangible Cultural Heritage
  156. BiasFilter: An Inference-Time Debiasing Framework for Large Language Models
  157. ValueSim: Generating Backstories to Model Individual Value Systems
  158. RAGPPI: RAG Benchmark for Protein-Protein Interactions in Drug Discovery
  159. Speech as a Multimodal Digital Phenotype for Multi-Task LLM-based Mental Health Prediction
  160. Arbiters of Ambivalence: Challenges of Using LLMs in No-Consensus Tasks
  161. OWL: Probing Cross-Lingual Recall of Memorized Texts via World Literature
  162. ATI: Any Trajectory Instruction for Controllable Video Generation
  163. Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates
  164. Generative Social Choice: The Next Generation
  165. Fast Isotropic Median Filtering
  166. Improving QA Efficiency with DistilBERT: Fine-Tuning and Inference on mobile Intel CPUs
  167. Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging
  168. Scalable Parameter and Memory Efficient Pretraining for LLM: Recent Algorithmic Advances and Benchmarking
  169. Structured Memory Mechanisms for Stable Context Representation in Large Language Models
  170. Hierarchical Material Recognition from Local Appearance
  171. Talent or Luck? Evaluating Attribution Bias in Large Language Models
  172. Learning Hierarchical Sparse Transform Coding for 3DGS Compression
  173. Conversational Alignment with Artificial Intelligence in Context
  174. HiLDe: Intentional Code Generation via Human-in-the-Loop Decoding
  175. Defining Foundation Models for Computational Science: A Call for Clarity and Rigor
  176. On the Dynamic Regret of Following the Regularized Leader: Optimism with History Pruning
  177. Local Stability and Region of Attraction Analysis for Neural Network Feedback Systems under Positivity Constraints
  178. Smart Surrogate Losses for Contextual Stochastic Linear Optimization with Robust Constraints
  179. Semantic Exploration and Dense Mapping of Complex Environments using Ground Robot with Panoramic LiDAR-Camera Fusion
  180. BugWhisperer: Fine-Tuning LLMs for SoC Hardware Vulnerability Detection
  181. Forecasting Residential Heating and Electricity Demand with Scalable, High-Resolution, Open-Source Models
  182. The WHY in Business Processes: Unification of Causal Process Models
  183. CFP-Gen: Combinatorial Functional Protein Generation via Diffusion Language Models
  184. CrossNAS: A Cross-Layer Neural Architecture Search Framework for PIM Systems
  185. GateNLP at SemEval-2025 Task 10: Hierarchical Three-Step Prompting for Multilingual Narrative Classification
  186. Large Language Models for Depression Recognition in Spoken Language Integrating Psychological Knowledge
  187. Causal-PIK: Causality-based Physical Reasoning with a Physics-Informed Kernel
  188. Permissioned LLMs: Enforcing Access Control in Large Language Models
  189. 4DTAM: Non-Rigid Tracking and Mapping via Dynamic Surface Gaussians
  190. A Probabilistic Jump-Diffusion Framework for Open-World Egocentric Activity Recognition
  191. NGPU-LM: GPU-Accelerated N-Gram Language Model for Context-Biasing in Greedy ASR Decoding
  192. IRS: Incremental Relationship-guided Segmentation for Digital Pathology
  193. CLIPGaussian: Universal and Multimodal Style Transfer Based on Gaussian Splatting
  194. What is the Right Embedding Space for Contrastive Learning in Referring Expression Counting?
  195. LiTEx: A Linguistic Taxonomy of Explanations for Understanding Within-Label Variation in Natural Language Inference
  196. "That's another doom I haven't thought about": A User Study on AI Labels as a Safeguard Against Image-Based Misinformation
  197. On the Reliability and Stability of Selective Methods in Malware Classification Tasks
  198. Bayesian Attention Mechanism: A Probabilistic Framework for Positional Encoding and Context Length Extrapolation
  199. Development and Validation of SXI++ LNM Algorithm for Sepsis Prediction
  200. Orca: Browsing at Scale Through User-Driven and AI-Facilitated Orchestration Across Malleable Webpages
  201. What Has Been Lost with Synthetic Evaluation?
  202. Bridging Distribution Shift and AI Safety: Conceptual and Methodological Synergies
  203. PGLearn -- An Open-Source Learning Toolkit for Optimal Power Flow
  204. Self-Critique and Refinement for Faithful Natural Language Explanations
  205. A Tool for Generating Exceptional Behavior Tests With Large Language Models
  206. IMTS is Worth Time × Channel Patches: Visual Masked Autoencoders for Irregular Multivariate Time Series Prediction
  207. X-Factor: Quality Is a Dataset-Intrinsic Property
  208. Highly Efficient and Effective LLMs with Multi-Boolean Architectures
  209. VidText: Towards Comprehensive Evaluation for Video Text Understanding
  210. Distribution free M-estimation
  211. CLUE: Neural Networks Calibration via Learning Uncertainty-Error alignment
  212. Towards a More Generalized Approach in Open Relation Extraction
  213. Efficient Preimage Approximation for Neural Network Certification
  214. Fast Trajectory-Independent Model-Based Reconstruction Algorithm for Multi-Dimensional Magnetic Particle Imaging
  215. Can Large Language Models Match the Conclusions of Systematic Reviews?
  216. Navigating the Latent Space Dynamics of Neural Models
  217. Temporal Convolutional Autoencoder for Interference Mitigation in FMCW Radar Altimeters
  218. Finite-Sample Convergence Bounds for Trust Region Policy Optimization in Mean-Field Games
  219. Predicting Human Depression with Hybrid Data Acquisition utilizing Physical Activity Sensing and Social Media Feeds
  220. Machine Learning Models Have a Supply Chain Problem
  221. MEDAL: A Framework for Benchmarking LLMs as Multilingual Open-Domain Dialogue Evaluators
  222. Counting trees: A treebank-driven exploration of syntactic variation in speech and writing across languages
  223. Automated Essay Scoring Incorporating Annotations from Automated Feedback Systems
  224. MAC-Gaze: Motion-Aware Continual Calibration for Mobile Gaze Tracking
  225. Multivariate de Bruijn Graphs: A Symbolic Graph Framework for Time Series Forecasting
  226. StressTest: Can YOUR Speech LM Handle the Stress?
  227. Test-time augmentation improves efficiency in conformal prediction
  228. MIAS-SAM: Medical Image Anomaly Segmentation without thresholding
  229. A comprehensive analysis of PINNs: Variants, Applications, and Challenges
  230. Non-convex entropic mean-field optimization via Best Response flow
  231. FAMA: The First Large-Scale Open-Science Speech Foundation Model for English and Italian
  232. FlashFormer: Whole-Model Kernels for Efficient Low-Batch Inference
  233. Enhancing Lifelong Multi-Agent Path-finding by Using Artificial Potential Fields
  234. Climate Finance Bench
  235. Self-orthogonalizing attractor neural networks emerging from the free energy principle
  236. StarBASE-GP: Biologically-Guided Automated Machine Learning for Genotype-to-Phenotype Association Analysis
  237. Information-Computation Gaps in Quantum Learning via Low-Degree Likelihood
  238. Training Language Models to Generate Quality Code with Program Analysis Feedback
  239. Private Rate-Constrained Optimization with Applications to Fair Learning
  240. Frequency-Adaptive Discrete Cosine-ViT-ResNet Architecture for Sparse-Data Vision
  241. Update Your Transformer to the Latest Release: Re-Basin of Task Vectors
  242. LLM-ODDR: A Large Language Model Framework for Joint Order Dispatching and Driver Repositioning
  243. MoRE: A Mixture of Low-Rank Experts for Adaptive Multi-Task Learning
  244. SlimLLM: Accurate Structured Pruning for Large Language Models
  245. Investigating the effectiveness of multimodal data in forecasting SARS-COV-2 case surges
  246. Training Free Stylized Abstraction
  247. 3DLLM-Mem: Long-Term Spatial-Temporal Memory for Embodied 3D Large Language Model
  248. Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation
  249. Characterizing Bias: Benchmarking Large Language Models in Simplified versus Traditional Chinese
  250. Spectral Survival Analysis
  251. SimProcess: High Fidelity Simulation of Noisy ICS Physical Processes
  252. Precise Object and Effect Removal with Adaptive Target-Aware Attention
  253. Stochastic Chameleons: Irrelevant Context Hallucinations Reveal Class-Based (Mis)Generalization in LLMs
  254. Chain-of-Talkers (CoTalk): Fast Human Annotation of Dense Image Captions
  255. Principled Out-of-Distribution Generalization via Simplicity
  256. PS4PRO: Pixel-to-pixel Supervision for Photorealistic Rendering and Optimization
  257. RICO: Improving Accuracy and Completeness in Image Recaptioning via Visual Reconstruction
  258. Chest Disease Detection In X-Ray Images Using Deep Learning Classification Method
  259. Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates
  260. Adversarially Robust AI-Generated Image Detection for Free: An Information Theoretic Perspective
  261. One Rank at a Time: Cascading Error Dynamics in Sequential Learning
  262. Performance of machine-learning-assisted Monte Carlo in sampling from simple statistical physics models
  263. HDDLGym: A Tool for Studying Multi-Agent Hierarchical Problems Defined in HDDL with OpenAI Gym
  264. Multi-Environment GLAMP: Approximate Message Passing for Transfer Learning with Applications to Lasso-based Estimators
  265. Comparative Analysis of Machine Learning Models for Lung Cancer Mutation Detection and Staging Using 3D CT Scans
  266. Precise In-Parameter Concept Erasure in Large Language Models
  267. Tell me Habibi, is it Real or Fake?
  268. Favorability of Loss Landscape with Weight Decay Requires Both Large Overparametrization and Initialization
  269. FNOPE: Simulation-based inference on function spaces with Fourier Neural Operators
  270. Multipath cycleGAN for harmonization of paired and unpaired low-dose lung computed tomography reconstruction kernels
  271. Universal Visuo-Tactile Video Understanding for Embodied Interaction
  272. PRISM: Video Dataset Condensation with Progressive Refinement and Insertion for Sparse Motion
  273. Geometric Hyena Networks for Large-scale Equivariant Learning
  274. MultiFormer: A Multi-Person Pose Estimation System Based on CSI and Attention Mechanism
  275. A Copula Based Supervised Filter for Feature Selection in Diabetes Risk Prediction Using Machine Learning
  276. Deep Learning-Based BMD Estimation from Radiographs with Conformal Uncertainty Quantification
  277. DES-LOC: Desynced Low Communication Adaptive Optimizers for Training Foundation Models
  278. A Human-Centric Approach to Explainable AI for Personalized Education
  279. Uncertainty Quantification with Proper Scoring Rules: Adjusting Measures to Prediction Tasks
  280. RiverMamba: A State Space Model for Global River Discharge and Flood Forecasting
  281. Training RL Agents for Multi-Objective Network Defense Tasks
  282. Symplectic Generative Networks (SGNs): A Hamiltonian Framework for Invertible Deep Generative Modeling
  283. PrismLayers: Open Data for High-Quality Multi-Layer Transparent Image Generative Models
  284. PathFL: Multi-Alignment Federated Learning for Pathology Image Segmentation
  285. Evaluating Supervised Learning Models for Fraud Detection: A Comparative Study of Classical and Deep Architectures on Imbalanced Transaction Data
  286. IGNIS: A Robust Neural Network Framework for Constrained Parameter Estimation in Archimedean Copulas
  287. Strengthening Proportionality in Temporal Voting
  288. Accelerating Optimization via Differentiable Stopping Time
  289. Geometric GNNs for Charged Particle Tracking at GlueX
  290. Assessing Quantum Advantage for Gaussian Process Regression
  291. SABER: Spatially Consistent 3D Universal Adversarial Objects for BEV Detectors
  292. Risk-Sensitive Conformal Prediction for Catheter Placement Detection in Chest X-rays
  293. ProSpero: Active Learning for Robust Protein Design Beyond Wild-Type Neighborhoods
  294. On the Surprising Effectiveness of Large Learning Rates under Standard Width Scaling
  295. ProCrop: Learning Aesthetic Image Cropping from Professional Compositions
  296. Effective Context in Neural Speech Models
  297. Understanding Adversarial Training with Energy-based Models
  298. A Closer Look at Multimodal Representation Collapse
  299. Hypothesis Testing in Imaging Inverse Problems
  300. Human-Centered Human-AI Collaboration (HCHAC)
  301. Non-Asymptotic Analysis of (Sticky) Track-and-Stop
  302. Forecasting Multivariate Urban Data via Decomposition and Spatio-Temporal Graph Analysis
  303. Pure Exploration with Infinite Answers
  304. CPINN-ABPI: Physics-Informed Neural Networks for Accurate Power Estimation in MPSoCs
  305. Single Domain Generalization for Alzheimer's Detection from 3D MRIs with Pseudo-Morphological Augmentations and Contrastive Learning
  306. SHTOcc: Effective 3D Occupancy Prediction with Sparse Head and Tail Voxels
  307. Universal Domain Adaptation for Semantic Segmentation
  308. Depth-Based Matrix Classification for the HHL Quantum Algorithm
  309. Position: All Current Generative Fidelity and Diversity Metrics are Flawed
  310. NFR: Neural Feature-Guided Non-Rigid Shape Registration
  311. On Geometry-Enhanced Parameter-Efficient Fine-Tuning for 3D Scene Segmentation
  312. Can NeRFs See without Cameras?
  313. Data-Driven Antenna Miniaturization: A Knowledge-Based System Integrating Quantum PSO and Predictive Machine Learning Models
  314. Synonymous Variational Inference for Perceptual Image Compression
  315. Distance Transform Guided Mixup for Alzheimer's Detection
  316. RC-AutoCalib: An End-to-End Radar-Camera Automatic Calibration Network
  317. STaR-Bets: Sequential Target-Recalculating Bets for Tighter Confidence Intervals
  318. Neural Face Skinning for Mesh-agnostic Facial Expression Cloning
  319. Frugal Incremental Generative Modeling using Variational Autoencoders
  320. STDR: Spatio-Temporal Decoupling for Real-Time Dynamic Scene Rendering
  321. PacTure: Efficient PBR Texture Generation on Packed Views with Visual Autoregressive Models
  322. Train with Perturbation, Infer after Merging: A Two-Stage Framework for Continual Learning
  323. DAM: Domain-Aware Module for Multi-Domain Dataset Condensation
  324. Exact Algorithms and Lower Bounds for Forming Coalitions of Constrained Maximum Size
  325. A Divide-and-Conquer Approach for Modeling Arrival Times in Business Process Simulation
  326. SplitLoRA: Balancing Stability and Plasticity in Continual Learning Through Gradient Space Splitting
  327. Computing Optimal Transport Maps and Wasserstein Barycenters Using Conditional Normalizing Flows
  328. Directed Homophily-Aware Graph Neural Network
  329. Continuum-armed Bandit Optimization with Batch Pairwise Comparison Oracles
  330. Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion
  331. Multiclass Loss Geometry Matters for Generalization of Gradient Descent in Separable Classification
  332. Adaptive Budget Allocation for Orthogonal-Subspace Adapter Tuning in LLMs Continual Learning
  333. Suitability Filter: A Statistical Framework for Classifier Evaluation in Real-World Deployment Settings
  334. Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning
  335. LLMs Struggle to Reject False Presuppositions when Misinformation Stakes are High
  336. VME: A Satellite Imagery Dataset and Benchmark for Detecting Vehicles in the Middle East and Beyond
  337. ChatPD: An LLM-driven Paper-Dataset Networking System
  338. Task-Driven Implicit Representations for Automated Design of LiDAR Systems
  339. Empowering Intelligent Low-altitude Economy with Large AI Model Deployment
  340. Progressive Data Dropout: An Embarrassingly Simple Approach to Faster Training
  341. Learning to Infer Parameterized Representations of Plants from 3D Scans
  342. UP-SLAM: Adaptively Structured Gaussian SLAM with Uncertainty Prediction in Dynamic Environments
  343. Credal Prediction based on Relative Likelihood
  344. NLP for Social Good: A Survey and Outlook of Challenges, Opportunities, and Responsible Deployment
  345. Individualised Counterfactual Examples Using Conformal Prediction Intervals
  346. Rethinking BPS: A Utility-Based Evaluation Framework
  347. Large-Area Fabrication-Aware Computational Diffractive Optics
  348. CADReview: Automatically Reviewing CAD Programs with Error Detection and Correction
  349. 360-LLaMA-Factory: Plug & Play Sequence Parallelism for Long Post-Training
  350. Neural Restoration of Greening Defects in Historical Autochrome Photographs Based on Purely Synthetic Data
  351. Compression versus Accuracy: A Hierarchy of Lifted Models
  352. New Tools are Needed for Tracking Adherence to AI Model Behavioral Use Clauses
  353. From Controlled Scenarios to Real-World: Cross-Domain Degradation Pattern Matching for All-in-One Image Restoration
  354. Natural Language Processing in Support of Evidence-based Medicine: A Scoping Review
  355. Learning Fine-Grained Geometry for Sparse-View Splatting via Cascade Depth Loss
  356. Full Domain Analysis in Fluid Dynamics
  357. Comprehensive Evaluation on Lexical Normalization: Boundary-Aware Approaches for Unsegmented Languages
  358. MRT at SemEval-2025 Task 8: Maximizing Recovery from Tables with Multiple Steps
  359. Domain Adaptation of Attention Heads for Zero-shot Anomaly Detection
  360. LiDAR Based Semantic Perception for Forklifts in Outdoor Environments
  361. A Unified Online-Offline Framework for Co-Branding Campaign Recommendations
  362. B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data
  363. Evaluation of LLMs in Speech is Often Flawed: Test Set Contamination in Large Language Models for Speech Recognition
  364. YH-MINER: Multimodal Intelligent System for Natural Ecological Reef Metric Extraction
  365. A Preprocessing Framework for Efficient Approximate Bi-Objective Shortest-Path Computation in the Presence of Correlated Objectives
  366. UDuo: Universal Dual Optimization Framework for Online Matching
  367. Yambda-5B -- A Large-Scale Multi-modal Dataset for Ranking And Retrieval
  368. A Linguistically Motivated Analysis of Intonational Phrasing in Text-to-Speech Systems: Revealing Gaps in Syntactic Sensitivity
  369. Optimal kernel regression bounds under energy-bounded noise
  370. Judging Quality Across Languages: A Multilingual Approach to Pretraining Data Filtering with Language Models
  371. Advancing Hearing Assessment: An ASR-Based Frequency-Specific Speech Test for Diagnosing Presbycusis
  372. Enjoying Information Dividend: Gaze Track-based Medical Weakly Supervised Segmentation
  373. GoMatching++: Parameter- and Data-Efficient Arbitrary-Shaped Video Text Spotting and Benchmarking
  374. Expressive yet Efficient Feature Expansion with Adaptive Cross-Hadamard Products
  375. Solver-Free Decision-Focused Learning for Linear Optimization Problems
  376. Handling bounded response in high dimensions: a Horseshoe prior Bayesian Beta regression approach
  377. A Survey on Training-free Open-Vocabulary Semantic Segmentation
  378. LaMM: Semi-Supervised Pre-Training of Large-Scale Materials Models
  379. Enhancing Uncertainty Estimation and Interpretability via Bayesian Non-negative Decision Layer
  380. An Augmentation-Aware Theory for Self-Supervised Contrastive Learning
  381. S2AFormer: Strip Self-Attention for Efficient Vision Transformer
  382. Breaking the Cloak! Unveiling Chinese Cloaked Toxicity with Homophone Graph and Toxic Lexicon
  383. TabXEval: Why this is a Bad Table? An eXhaustive Rubric for Table Evaluation
  384. Online Fair Division for Personalized 2-Value Instances
  385. ReliableEval: A Recipe for Stochastic LLM Evaluation via Method of Moments
  386. The informativeness of the gradient revisited
  387. LASER: Stratified Selective Sampling for Instruction Tuning with Dedicated Scoring Strategy
  388. InComeS: Integrating Compression and Selection Mechanisms into LLMs for Efficient Model Editing
  389. Learning A Robust RGB-Thermal Detector for Extreme Modality Imbalance
  390. Uncertainty Estimation for Heterophilic Graphs Through the Lens of Information Theory
  391. Improving Brain-to-Image Reconstruction via Fine-Grained Text Bridging
  392. Lifted Forward Planning in Relational Factored Markov Decision Processes with Concurrent Actions
  393. Flexible Tool Selection through Low-dimensional Attribute Alignment of Vision and Language
  394. FaceEditTalker: Controllable Talking Head Generation with Facial Attribute Editing
  395. Real-Time Blind Defocus Deblurring for Earth Observation: The IMAGIN-e Mission Approach
  396. SridBench: Benchmark of Scientific Research Illustration Drawing of Image Generation Model
  397. Sentiment Simulation using Generative AI Agents
  398. LoKI: Low-damage Knowledge Implanting of Large Language Models
  399. Multilingual vs Crosslingual Retrieval of Fact-Checked Claims: A Tale of Two Approaches
  400. Multimodal Forecasting of Sparse Intraoperative Hypotension Events Powered by Language Model
  401. BiMi Sheets: Infosheets for bias mitigation methods
  402. Visual Large Language Models Exhibit Human-Level Cognitive Flexibility in the Wisconsin Card Sorting Test
  403. The quest for the GRAph Level autoEncoder (GRALE)
  404. Inclusive Federated Learning Through Compliance-Weighted Noise Allocation in Healthcare AI
  405. Curse of High Dimensionality Issue in Transformer for Long-context Modeling
  406. Adapting Segment Anything Model for Power Transmission Corridor Hazard Segmentation
  407. Efficient Dynamic Shielding for Parametric Safety Specifications
  408. MemOS: An Operating System for Memory-Augmented Generation (MAG) in Large Language Models
  409. On the Transferability and Discriminability of Repersentation Learning in Unsupervised Domain Adaptation
  410. UAVPairs: A Challenging Benchmark for Match Pair Retrieval of Large-scale UAV Images
  411. Knowledge Base Construction for Knowledge-Augmented Text-to-SQL
  412. From Coders to Critics: Empowering Students through Peer Assessment in the Age of AI Copilots
  413. Efficient feature matching for UAV images based on compact GPU data scheduling
  414. Visual Cues Support Robust Turn-taking Prediction in Noise
  415. Cognitively-Inspired Emergent Communication via Knowledge Graphs for Assisting the Visually Impaired
  416. iDSE: Navigating Design Space Exploration in High-Level Synthesis Using LLMs
  417. PADAM: Parallel averaged Adam reduces the error for stochastic optimization in scientific machine learning
  418. MObyGaze: a film dataset of multimodal objectification densely annotated by experts
  419. Hyperbolic recurrent neural network as the first type of non-Euclidean neural quantum state ansatz
  420. Can Test-time Computation Mitigate Reproduction Bias in Neural Symbolic Regression?
  421. Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis
  422. ArgInstruct: Specialized Instruction Fine-Tuning for Computational Argumentation
  423. The Resurrection of the ReLU
  424. AquaMonitor: A multimodal multi-view image sequence dataset for real-life aquatic invertebrate biodiversity monitoring
  425. Voice Adaptation for Swiss German
  426. Differentiable Generalized Sliced Wasserstein Plans
  427. Learning Curves of Stochastic Gradient Descent in Kernel Regression
  428. LatentMove: Towards Complex Human Movement Video Generation
  429. Mitigating Audiovisual Mismatch in Visual-Guide Audio Captioning
  430. Estimating the Effects of Sample Training Orders for Large Language Models without Retraining
  431. Guess the Age of Photos: An Interactive Web Platform for Historical Image Age Estimation
  432. Weakly-Supervised Contrastive Learning for Imprecise Class Labels
  433. Learnable Burst-Encodable Time-of-Flight Imaging for High-Fidelity Long-Distance Depth Sensing
  434. RESOUND: Speech Reconstruction from Silent Videos via Acoustic-Semantic Decomposed Modeling
  435. GL-PGENet: A Parameterized Generation Framework for Robust Document Image Enhancement
  436. Improving Continual Pre-training Through Seamless Data Packing
  437. PanoWan: Lifting Diffusion Video Generation Models to 360deg with Latitude/Longitude-aware Mechanisms
  438. Learning in Compact Spaces with Approximately Normalized Transformer
  439. Prototype Embedding Optimization for Human-Object Interaction Detection in Livestreaming
  440. Event-based Egocentric Human Pose Estimation in Dynamic Environment
  441. Lightweight Domain Adaptation of a Large Language Model for Legal Assistance in the Indian Context
  442. Found in Translation: Measuring Multilingual LLM Consistency as Simple as Translate then Evaluate
  443. Leveraging Interview-Informed LLMs to Model Survey Responses: Comparative Insights from AI-Generated and Human Data
  444. A decomposition-based robust training of physics-informed neural networks for nearly incompressible linear elasticity
  445. Functional Matching of Logic Subgraphs: Beyond Structural Isomorphism
  446. ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning
  447. Reward-Independent Messaging for Decentralized Multi-Agent Reinforcement Learning
  448. BOFormer: Learning to Solve Multi-Objective Bayesian Optimization via Non-Markovian RL
  449. LLMs Judging LLMs: A Simplex Perspective
  450. EnsemW2S: Enhancing Weak-to-Strong Generalization with Large Language Model Ensembles
  451. Resolving Knowledge Conflicts in Domain-specific Data Selection: A Case Study on Medical Instruction-tuning
  452. Revisiting Active Speaker Detection: An In-the-Wild Benchmark for Generalization and Robustness
  453. Stochastic Primal-Dual Double Block-Coordinate for Two-way Partial AUC Maximization
  454. Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting
  455. Continual Learning Beyond Experience Rehearsal and Full Model Surrogates
  456. Practical Adversarial Attacks on Stochastic Bandits via Fake Data Injection
  457. Graph-Assisted Culturally Adaptable Idiomatic Translation for Indic Languages
  458. Higher-Order Group Synchronization
  459. Efficient Ensemble for Fine-tuning Language Models on Multiple Datasets
  460. Subspecialty-Specific Foundation Model for Intelligent Gastrointestinal Pathology
  461. Beyond Completion: A Foundation Model for General Knowledge Graph Reasoning
  462. RenderFormer: Transformer-based Neural Rendering of Triangle Meshes with Global Illumination
  463. FALCON: An ML Framework for Fully Automated Layout-Constrained Analog Circuit Design
  464. InfoSAM: Fine-Tuning the Segment Anything Model from An Information-Theoretic Perspective
  465. Self-supervised Learning Method Using Transformer for Multi-dimensional Sensor Data Processing
  466. BD Open LULC Map: High-resolution land use land cover mapping & benchmarking for urban development in Dhaka, Bangladesh
  467. LiDARDustX: A LiDAR Dataset for Dusty Unstructured Road Environments
  468. Detecting Cultural Differences in News Video Thumbnails via Computational Aesthetics
  469. AlignGen: Boosting Personalized Image Generation with Cross-Modality Prior Alignment
  470. Taming Transformer Without Using Learning Rate Warmup
  471. Concentrate on Weakness: Mining Hard Prototypes for Few-Shot Medical Image Segmentation
  472. SineLoRADelta: Sine-Activated Delta Compression
  473. Diffusion-Denoised Hyperspectral Gaussian Splatting
  474. SVRPBench: A Realistic Benchmark for Stochastic Vehicle Routing Problem
  475. HydraNet: Momentum-Driven State Space Duality for Multi-Granularity Tennis Tournaments Analysis
  476. Incorporating LLMs for Large-Scale Urban Complex Mobility Simulation
  477. Symbolic Foundation Regressor on Complex Networks
  478. Hybrid Batch Normalisation: Resolving the Dilemma of Batch Normalisation in Federated Learning
  479. MAMBO-NET: Multi-Causal Aware Modeling Backdoor-Intervention Optimization for Medical Image Segmentation Network
  480. HelixDesign-Binder: A Scalable Production-Grade Platform for Binder Design Built on HelixFold3
  481. Cross-DINO: Cross the Deep MLP and Transformer for Small Object Detection
  482. CSI-Bench: A Large-Scale In-the-Wild Dataset for Multi-task WiFi Sensing
  483. GETReason: Enhancing Image Context Extraction through Hierarchical Multi-Agent Reasoning
  484. Towards Scalable Language-Image Pre-training for 3D Medical Imaging
  485. Principled Content Selection to Generate Diverse and Personalized Multi-Document Summaries
  486. Optimizable Model Averaging for Ensembling Heterogeneous Model Outputs
  487. Extracting Research Instruments from Educational Literature Using LLMs
  488. Rethinking Gradient-based Adversarial Attacks on Point Cloud Classification
  489. Xinyu AI Search: Enhanced Relevance and Comprehensive Results with Rich Answer Presentations
  490. RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers
  491. Spectral clustering for dependent community Hawkes process models of temporal networks
  492. A Physics-Informed Learning Framework to Solve the Infinite-Horizon Optimal Control Problem
  493. Nonadaptive Output Regulation of Second-Order Nonlinear Uncertain Systems
  494. UniMoGen: Universal Motion Generation