mlsanityData to 7 Oct 2026

Papers

New on arXiv

Wed 21 May 2025

557 papers

  1. Procedural Environment Generation for Tool-Use AgentsLLM agents and tool use → Tool learning and function calling
  2. Angle Domain Guidance: Latent Diffusion Requires Rotation Rather Than ExtrapolationDiffusion models → Diffusion foundations and sampling
  3. MoTE: Mixture of Task-specific Experts for Pre-Trained ModelBased Class-incremental LearningMixture-of-experts → Mixture of LoRA experts
  4. CausalVLBench: Benchmarking Visual Causal Reasoning in Large Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
  5. Scaling Physical Reasoning with the PHYSICS DatasetLLM reasoning → Spatial and embodied reasoning
  6. Pixels Versus Priors: Controlling Knowledge Priors in Vision-Language Models through Visual CounterfactsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  7. Conformal Language Model Reasoning with Coherent FactualityLLM reasoning → Test-time compute and efficient thinking
  8. MTR-Bench: A Comprehensive Benchmark for Multi-Turn Reasoning EvaluationLLM reasoning → Reasoning benchmarks and evaluation
  9. Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data?LLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  10. NeSyGeo: A Neuro-Symbolic Framework for Multimodal Geometric Reasoning Data GenerationLLM reasoning → Spatial and embodied reasoning +1
  11. Systematic Evaluation of Machine-Generated Reasoning and PHQ-9 Labeling for Depression Detection Using Large Language ModelsLLM reasoning → Clinical and biomedical applications +1
  12. After Retrieval, Before Generation: Enhancing the Trustworthiness of Large Language Models in Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
  13. From Tokens to Thoughts: How LLMs and Humans Trade Compression for MeaningLLM reasoning → Reasoning benchmarks and evaluation
  14. Swarm Intelligence Enhanced Reasoning: A Density-Driven Framework for LLM-Based Multi-Agent OptimizationLLM reasoning → Reasoning for agents, planning and code +1
  15. Multi-Modality Expansion and Retention for LLMs through Parameter Merging and DecouplingMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  16. CRAKEN: Cybersecurity LLM Agent with Knowledge-Based ExecutionLLM agents and tool use → Agent threats, guardrails and governance
  17. RRTL: Red Teaming Reasoning Large Language Models in Tool LearningLLM reasoning → Reasoning for agents, planning and code +2
  18. Forging Time Series with Language: A Large Language Model Approach to Synthetic Data GenerationSynthetic data and self-improvement for LLMs → Model collapse from synthetic data
  19. Any Large Language Model Can Be a Reliable Judge: Debiasing with a Reasoning-based Bias DetectorLLM reasoning → Reasoning benchmarks and evaluation
  20. TACO: Enhancing Multimodal In-context Learning via Task Mapping-Guided Sequence ConfigurationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  21. Make LVLMs Focus: Context-Aware Attention Modulation for Better Multimodal In-Context LearningMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  22. FR-Mamba: Time-Series Physical Field Reconstruction Based on State Space ModelState-space sequence models (S4, Mamba) → Time series forecasting with SSMs
  23. AudioMorphix: Training-free audio editing with diffusion probabilistic modelsDiffusion models → Audio, speech and music
  24. How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following BehaviorLLM agents and tool use → Agent memory systems
  25. Aug2Search: Enhancing Facebook Marketplace Search with LLM-Generated Synthetic Data AugmentationSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  26. Not All Models Suit Expert Offloading: On Local Routing Consistency of Mixture-of-Expert ModelsMixture-of-experts → Expert routing strategies
  27. SPhyR: Spatial-Physical Reasoning Benchmark on Material DistributionLLM reasoning → Spatial and embodied reasoning
  28. Children's Mental Models of AI Reasoning: Implications for AI Literacy EducationLLM reasoning → Reasoning benchmarks and evaluation
  29. Benchmarking Chest X-ray Diagnosis Models Across Multinational DatasetsMultimodal LLMs / vision-language models → Medical vision-language models
  30. Context and Pixel Aware Large Language Model for Video Quality AssessmentMultimodal LLMs / vision-language models → Image editing and quality assessment
  31. NOVER: Incentive Training for Language Models via Verifier-Free Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning
  32. Ranking Free RAG: Replacing Re-ranking with Selection in RAG for Sensitive DomainsRetrieval-augmented generation → RAG robustness and adaptive retrieval +1
  33. Position: Agentic Systems Constitute a Key Component of Next-Generation Intelligent Image ProcessingLLM agents and tool use → Multimodal and embodied agents
  34. SLMEval: Entropy-Based Calibration for Human-Aligned Evaluation of Large Language ModelsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  35. Image-to-Image Translation with Diffusion Transformers and CLIP-Based Image ConditioningDiffusion models → Image generation, text-to-image and editing
  36. Diffusion Probabilistic Generative Models for Accelerated, in-NICU Permanent Magnet Neonatal MRIDiffusion models → Medical imaging and segmentation
  37. Pixel Reasoner: Incentivizing Pixel-Space Reasoning with Curiosity-Driven Reinforcement LearningLLM reasoning → Multimodal reasoning
  38. OViP: Online Vision-Language Preference Learning for VLM HallucinationMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs +1
  39. Efficient PRM Training Data Synthesis via Formal VerificationLLM reasoning → Reinforcement learning for reasoning +2
  40. VideoGameQA-Bench: Evaluating Vision-Language Models for Video Game Quality AssuranceMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  41. MoRE-Brain: Routed Mixture of Experts for Interpretable and Generalizable Cross-Subject fMRI Visual DecodingMixture-of-experts → Medical and biomedical MoE
  42. MAPS: A Multilingual Benchmark for Agent Performance and SecurityLLM agents and tool use → General LLM agent frameworks and benchmarks
  43. PhyX: Does Your Model Have the "Wits" for Physical Reasoning?LLM reasoning → Spatial and embodied reasoning
  44. ViQAgent: Zero-Shot Video Question Answering via Agent with Open-Vocabulary Grounding ValidationLLM agents and tool use → Multimodal and embodied agents
  45. CoT Information: Improved Sample Complexity under Chain-of-Thought SupervisionLLM reasoning → Prompting and chain-of-thought reasoning
  46. VERDI: VLM-Embedded Reasoning for Autonomous DrivingLLM reasoning → Chain-of-thought reasoning for driving +1
  47. Aligning Dialogue Agents with Global Feedback via Large Language Model Multimodal Reward DecompositionLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  48. BR-TaxQA-R: A Dataset for Question Answering with References for Brazilian Personal Income Tax Law, including case lawRetrieval-augmented generation → Legal and financial RAG
  49. Challenger: Affordable Adversarial Driving Video GenerationEnd-to-end autonomous driving → Adversarial scenarios and safety testing
  50. GRIT: Teaching MLLMs to Think with ImagesLLM reasoning → Multimodal reasoning
  51. InfoDeepSeek: Benchmarking Agentic Information Seeking for Retrieval-Augmented GenerationRetrieval-augmented generation → Agentic RAG, agents and memory +1
  52. How Do Large Vision-Language Models See Text in Image? Unveiling the Distinctive Role of OCR HeadsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  53. AutoData: A Multi-Agent System for Open Web Data CollectionLLM agents and tool use → Web, search, and research agents
  54. Learning to Reason via Mixture-of-Thought for Logical ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  55. Streamline Without Sacrifice -- Squeeze out Computation Redundancy in LMMMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  56. Leveraging the Powerful Attention of a Pre-trained Diffusion Model for Exemplar-based Image ColorizationDiffusion models → Image generation, text-to-image and editing
  57. GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI AgentsLLM reasoning → Multimodal reasoning +1
  58. MMaDA: Multimodal Large Diffusion Language ModelsDiffusion models → Image generation, text-to-image and editing
  59. STAR-R1: Spatial TrAnsformation Reasoning by Reinforcing Multimodal LLMsLLM reasoning → Spatial and embodied reasoning +1
  60. VerifyBench: Benchmarking Reference-based Reward Systems for Large Language ModelsLLM reasoning → Reinforcement learning for reasoning
  61. Interspatial Attention for Efficient 4D Human Video GenerationDiffusion models → Video generation
  62. The Agentic EconomyLLM agents and tool use → Social simulation and multi-agent debate
  63. Reverse Engineering Human Preferences with Reinforcement LearningLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  64. HCRMP: A LLM-Hinted Contextual Reinforcement Learning Framework for Autonomous DrivingEnd-to-end autonomous driving → Large language models for driving
  65. VARD: Efficient and Dense Fine-Tuning for Diffusion Models with Value-based RLDiffusion models → Diffusion and flow policies for robotics
  66. dKV-Cache: The Cache for Diffusion Language ModelsDiffusion models → Discrete and text diffusion +1
  67. Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept SpaceLLM reasoning → Prompting and chain-of-thought reasoning
  68. ConvSearch-R1: Enhancing Query Reformulation for Conversational Search with Reasoning via Reinforcement LearningLLM reasoning → Knowledge- and tool-augmented reasoning
  69. Beyond Hard and Soft: Hybrid Context Compression for Balancing Local and Global Information RetentionEfficient LLM inference and serving → Prompt and context compression
  70. Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context RetrievalLLM safety and security → Jailbreaking
  71. Checkpoint-GCG: Auditing and Attacking Fine-Tuning-Based Prompt Injection DefensesLLM agents and tool use → Agent threats, guardrails and governance +1
  72. DEBATE, TRAIN, EVOLVE: Self Evolution of Language Model ReasoningLLM reasoning → Reasoning for agents, planning and code
  73. UAV-Flow Colosseo: A Real-World Benchmark for Flying-on-a-Word UAV Imitation LearningOffline RL and imitation learning from data → Imitation learning methods
  74. Beyond Empathy: Integrating Diagnostic and Therapeutic Reasoning with Large Language Models for Mental Health CounselingLLM reasoning → Clinical and biomedical applications
  75. TurnaboutLLM: A Deductive Reasoning Benchmark from Detective GamesLLM reasoning → Reasoning for agents, planning and code
  76. Advancing LLM Safe Alignment with Safety Representation RankingLLM safety and security → Safety alignment, refusal and guardrails
  77. HAMF: A Hybrid Attention-Mamba Framework for Joint Scene Context Understanding and Future Motion Representation LearningState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
  78. HDLxGraph: Bridging Large Language Models and HDL Repositories via HDL Graph DatabasesRetrieval-augmented generation → RAG pipeline design and evaluation
  79. "Alexa, can you forget me?" Machine Unlearning Benchmark in Spoken Language UnderstandingLLM safety and security → Machine unlearning
  80. A Unified Theoretical Analysis of Private and Robust Offline Alignment: from RLHF to DPOLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  81. TemplateRL: Structured Template-Guided Reinforcement Learning for LLM ReasoningLLM reasoning → Reinforcement learning for reasoning
  82. From Grounding to Manipulation: Case Studies of Foundation Model Integration in Embodied Robotic SystemsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  83. ThinkLess: A Training-Free Inference-Efficient Method for Reducing Reasoning RedundancyLLM reasoning → Test-time compute and efficient thinking +1
  84. SwarmDiff: Swarm Robotic Trajectory Planning in Cluttered Environments via Diffusion TransformerDiffusion models → Diffusion and flow policies for robotics
  85. UniErase: Towards Balanced and Precise Unlearning in Language ModelsLLM safety and security → Machine unlearning
  86. Graph-Conditional Flow Matching for Relational Data GenerationDiffusion models → Flow matching, time series and science
  87. Exploring the Limits of Vision-Language-Action Manipulations in Cross-task GeneralizationVision-language-action models → Generalist VLA models and benchmarks
  88. FLARE: Robot Learning with Implicit World ModelingWorld models → Embodied and robot world models +1
  89. Be Careful When Fine-tuning On Open-Source LLMs: Your Fine-tuning Data Could Be Secretly Stolen!LLM safety and security → Safety alignment, refusal and guardrails
  90. Can VLMs Detect and Localize Fine-Grained AI-Edited Images?Diffusion models → Image generation, text-to-image and editing
  91. Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language ModelsLLM reasoning → Prompting and chain-of-thought reasoning
  92. Listen to the Context: Towards Faithful Large Language Models for Retrieval Augmented Generation on Climate QuestionsRetrieval-augmented generation → Agentic RAG, agents and memory
  93. Direct Preference Optimization for Adaptive Concept-based ExplanationsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  94. Can LLMs textitunderstand Math? -- Exploring the Pitfalls in Mathematical ReasoningLLM reasoning → Mathematical reasoning
  95. LENS: Multi-level Evaluation of Multimodal Reasoning with Large Language ModelsLLM reasoning → Multimodal reasoning +1
  96. Learn to Reason Efficiently with Adaptive Length-based Reward ShapingLLM reasoning → Test-time compute and efficient thinking
  97. World Models as Reference Trajectories for Rapid Motor AdaptationWorld models → Latent dynamics models and model-based RL
  98. Visual Perturbation and Adaptive Hard Negative Contrastive Learning for Compositional Reasoning in Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
  99. TinyDrive: Multiscale Visual Question Answering with Selective Token Routing for Autonomous DrivingMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
  100. Do RAG Systems Really Suffer From Positional Bias?Retrieval-augmented generation → RAG pipeline design and evaluation
All 557
  1. Clapper: Compact Learning and Video Representation in VLMsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  2. Robo2VLM: Visual Question Answering from Large-Scale In-the-Wild Robot Manipulation DatasetsLLM reasoning → Spatial and embodied reasoning +1
  3. Visual Thoughts: A Unified Perspective of Understanding Multimodal Chain-of-ThoughtLLM reasoning → Multimodal reasoning +1
  4. Multilingual Test-Time Scaling via Initial Thought TransferLLM reasoning → Reasoning benchmarks and evaluation
  5. Prompt Tuning Vision Language Models with Margin Regularizer for Few-Shot Learning under Distribution ShiftsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  6. Seeing Through Deception: Uncovering Misleading Creator Intent in Multimodal News with Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  7. PhysicsArena: The First Multimodal Physics Reasoning Benchmark Exploring Variable, Process, and Solution DimensionsLLM reasoning → Spatial and embodied reasoning +1
  8. CoLA: Collaborative Low-Rank AdaptationMixture-of-experts → Mixture of LoRA experts
  9. Comprehensive Evaluation and Analysis for NSFW Concept Erasure in Text-to-Image Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
  10. Single LLM, Multiple Roles: A Unified Retrieval-Augmented Generation Framework Using Role-Specific Token OptimizationRetrieval-augmented generation → RAG pipeline design and evaluation
  11. Adaptive Chain-of-Focus Reasoning via Dynamic Visual Search and Zooming for Efficient VLMsLLM reasoning → Multimodal reasoning +1
  12. TimeCausality: Evaluating the Causal Ability in Time Dimension for Vision Language ModelsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  13. Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-ThoughtLLM reasoning → Test-time compute and efficient thinking +2
  14. Responsible Diffusion Models via Constraining Text Embeddings within Safe RegionsDiffusion models → Robustness, privacy and adversarial aspects
  15. On the Robustness of Medical Vision-Language Models: Are they Truly Generalizable?Multimodal LLMs / vision-language models → Medical vision-language models
  16. Silent Leaks: Implicit Knowledge Extraction Attack on RAG Systems through Benign QueriesRetrieval-augmented generation → Privacy and security of RAG +1
  17. Efficient Data Driven Mixture-of-Expert Extraction from Trained NetworksMixture-of-experts → Vision mixture-of-experts
  18. Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language ModelsLLM safety and security → Audio jailbreaks and speech backdoors
  19. How Should We Enhance the Safety of Large Reasoning Models: An Empirical StudyLLM reasoning → Reasoning for agents, planning and code
  20. When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient ReasoningLLM reasoning → Test-time compute and efficient thinking
  21. Understanding the Anchoring Effect of LLM with Synthetic Data: Existence, Mechanism, and Potential MitigationsSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  22. Are Vision-Language Models Safe in the Wild? A Meme-Based Benchmark StudyMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  23. Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  24. RAZER: Robust Accelerated Zero-Shot 3D Open-Vocabulary Panoptic Reconstruction with Spatio-Temporal AggregationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  25. X-WebAgentBench: A Multilingual Interactive Web Benchmark for Evaluating Global Agentic SystemLLM reasoning → Reasoning for agents, planning and code +1
  26. Better Safe Than Sorry? Overreaction Problem of Vision Language Models in Visual Emergency RecognitionMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  27. FlowKV: Enhancing Multi-Turn Conversational Coherence in LLMs via Isolated Key-Value Cache ManagementEfficient LLM inference and serving → KV cache optimization
  28. SSR: Speculative Parallel Scaling Reasoning in Test-timeLLM reasoning → Test-time compute and efficient thinking +1
  29. My Face Is Mine, Not Yours: Facial Protection Against Diffusion Model Face SwappingDiffusion models → Robustness, privacy and adversarial aspects
  30. Towards Zero-Shot Differential Morphing Attack Detection with Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  31. FaceCrafter: Identity-Conditional Diffusion with Disentangled Control over Facial Pose, Expression, and EmotionDiffusion models → Image generation, text-to-image and editing
  32. Trajectory Bellman Residual Minimization: A Simple Value-Based Method for LLM ReasoningLLM reasoning → Reinforcement learning for reasoning
  33. Multiple Weaks Win Single Strong: Large Language Models Ensemble Weak Reinforcement Learning Agents into a Supreme OneLLM agents and tool use → Reinforcement learning for LLM agents
  34. Saliency-Aware Quantized Imitation Learning for Efficient Robotic ControlVision-language-action models → Efficient VLA inference and adaptation +1
  35. AgentThink: A Unified Framework for Tool-Augmented Chain-of-Thought Reasoning in Vision-Language Models for Autonomous DrivingLLM reasoning → Chain-of-thought reasoning for driving +2
  36. Web-Shepherd: Advancing PRMs for Reinforcing Web AgentsLLM agents and tool use → Web, search, and research agents +1
  37. When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in ReasoningLLM reasoning → Test-time compute and efficient thinking
  38. Scaling Diffusion Transformers Efficiently via μPDiffusion models → Diffusion foundations and sampling
  39. LiveVLM: Efficient Online Video Understanding via Streaming-Oriented KV Cache and RetrievalEfficient LLM inference and serving → Visual token pruning in multimodal models
  40. ReGUIDE: Data Efficient GUI Grounding via Spatial Reasoning and SearchLLM reasoning → Multimodal reasoning +1
  41. When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual ReasonersLLM reasoning → Reasoning benchmarks and evaluation
  42. Fooling the LVLM Judges: Visual Biases in LVLM-Based EvaluationMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  43. Towards Explainable Temporal Reasoning in Large Language Models: A Structure-Aware Generative FrameworkLLM reasoning → Knowledge- and tool-augmented reasoning
  44. UNet with Self-Adaptive Mamba-Like Attention and Causal-Resonance Learning for Medical Image SegmentationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  45. BountyBench: Dollar Impact of AI Agent Attackers and Defenders on Real-World Cybersecurity SystemsLLM agents and tool use → Agent threats, guardrails and governance
  46. R-TOFU: Unlearning in Large Reasoning ModelsLLM reasoning → Reasoning for agents, planning and code +1
  47. Deliberation on Priors: Trustworthy Reasoning of Large Language Models on Knowledge GraphsLLM reasoning → Knowledge- and tool-augmented reasoning +1
  48. DUSK: Do Not Unlearn Shared KnowledgeLLM safety and security → Machine unlearning
  49. ReflAct: World-Grounded Decision Making in LLM Agents via Goal-State ReflectionLLM agents and tool use → General LLM agent frameworks and benchmarks
  50. RAG or Fine-tuning? A Comparative Study on LCMs-based Code Completion in IndustryRetrieval-augmented generation → RAG for code
  51. A Unified Gradient-based Framework for Task-agnostic Continual Learning-UnlearningLLM safety and security → Machine unlearning
  52. A Linear Approach to Data PoisoningLLM safety and security → Backdoor and data poisoning attacks
  53. Lossless Token Merging Even Without Fine-Tuning in Vision TransformersEfficient LLM inference and serving → Token pruning and merging for ViTs
  54. ALN-P3: Unified Language Alignment for Perception, Prediction, and Planning in Autonomous DrivingEnd-to-end autonomous driving → Reasoning VLA and VLM driving policies
  55. Cascaded Diffusion Models for Neural Motion PlanningDiffusion models → Diffusion and flow policies for robotics
  56. R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint OptimizationLLM agents and tool use → Financial trading and forecasting agents
  57. Prolonged Reasoning Is Not All You Need: Certainty-Based Adaptive Routing for Efficient LLM/MLLM ReasoningLLM reasoning → Test-time compute and efficient thinking +1
  58. Time Tracker: Mixture-of-Experts-Enhanced Foundation Time Series Forecasting Model with Decoupled Training PipelinesMixture-of-experts → MoE for time series and graphs
  59. BanditSpec: Adaptive Speculative Decoding via Bandit AlgorithmsEfficient LLM inference and serving → Speculative decoding
  60. The Unreasonable Effectiveness of Entropy Minimization in LLM ReasoningLLM reasoning → Reinforcement learning for reasoning
  61. Few-Shot Adversarial Low-Rank Fine-Tuning of Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  62. An Empirical Study on Reinforcement Learning for Reasoning-Search Interleaved LLM AgentsLLM reasoning → Knowledge- and tool-augmented reasoning +1
  63. iPad: Iterative Proposal-centric End-to-End Autonomous DrivingEnd-to-end autonomous driving → End-to-end system architecture
  64. RoT: Enhancing Table Reasoning with Iterative Row-Wise TraversalsLLM reasoning → Knowledge- and tool-augmented reasoning
  65. A Risk Ontology for Evaluating AI-Powered Psychotherapy Virtual AgentsLLM agents and tool use → Medical and scientific domain agents
  66. StepSearch: Igniting LLMs Search Ability via Step-Wise Proximal Policy OptimizationLLM reasoning → Knowledge- and tool-augmented reasoning
  67. Mechanistic evaluation of Transformers and state space modelsState-space sequence models (S4, Mamba) → Core SSM architectures for language
  68. Steering Generative Models with Experimental Data for Protein Fitness OptimizationDiffusion models → Flow matching, time series and science
  69. ThinkRec: Thinking-based recommendation via LLMLLM reasoning → LLM reasoning for recommendation
  70. Data Augmentation and Resolution Enhancement using GANs and Diffusion Models for Tree SegmentationDiffusion models → Inverse problems and image restoration
  71. Agentic Feature Augmentation: Unifying Selection and Generation with Teaming, Planning, and MemoriesLLM agents and tool use → Reinforcement learning for LLM agents
  72. Traveling Across Languages: Benchmarking Cross-Lingual Consistency in Multimodal LLMsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  73. DISCO Balances the Scales: Adaptive Domain- and Difficulty-Aware Reinforcement Learning on Imbalanced DataLLM reasoning → Reinforcement learning for reasoning +1
  74. UrduFactCheck: An Agentic Fact-Checking Framework for Urdu with Evidence Boosting and BenchmarkingLLM agents and tool use → Web, search, and research agents
  75. SAKE: Structured Agentic Knowledge Extrapolation for Complex LLM Reasoning via Reinforcement LearningLLM reasoning → Knowledge- and tool-augmented reasoning +1
  76. AsynFusion: Towards Asynchronous Latent Consistency Models for Decoupled Whole-Body Audio-Driven AvatarsDiffusion models → Audio, speech and music
  77. Non-rigid Motion Correction for MRI Reconstruction via Coarse-To-Fine Diffusion ModelsDiffusion models → Medical imaging and segmentation
  78. Lost in Benchmarks? Rethinking Large Language Model Benchmarking with Item Response TheoryLLM reasoning → Reasoning benchmarks and evaluation
  79. PiFlow: Principle-Aware Scientific Discovery with Multi-Agent CollaborationLLM agents and tool use → Web, search, and research agents
  80. RLBenchNet: The Right Network for the Right Reinforcement Learning TaskState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
  81. RL Tango: Reinforcing Generator and Verifier Together for Language ReasoningLLM reasoning → Reinforcement learning for reasoning +1
  82. UniSTPA: A Safety Analysis Framework for End-to-End Autonomous DrivingEnd-to-end autonomous driving → Adversarial scenarios and safety testing
  83. Towards Spoken Mathematical Reasoning: Benchmarking Speech-based Models over Multi-faceted Math ProblemsLLM reasoning → Mathematical reasoning +1
  84. Learning to Rank Chain-of-Thought: Using a Small ModelLLM reasoning → Test-time compute and efficient thinking
  85. MAS-ZERO: Designing Multi-Agent Systems with Zero SupervisionLLM agents and tool use → General LLM agent frameworks and benchmarks
  86. Physical models realizing the transformer architecture of large language models
  87. Unsupervised Learning for Optimal Transport plan prediction between unbalanced graphs
  88. FlexQuant: A Flexible and Efficient Dynamic Precision Switching Framework for LLM Quantization
  89. 15,500 Seconds: Lean UAV Classification Using EfficientNet and Lightweight Fine-Tuning
  90. I Can't Believe It's Not Real: CV-MuSeNet: Complex-Valued Multi-Signal Segmentation
  91. Perception-Driven Bias Detection in Machine Learning via Crowdsourced Visual Judgment
  92. The Effects of Data Augmentation on Confidence Estimation for LLMs
  93. Boost Post-Training Quantization via Null Space Optimization for Large Language Models
  94. A Framework for Non-Linear Attention via Modern Hopfield Networks
  95. GenFT: A Generative Parameter-Efficient Fine-Tuning Method for Pretrained Foundation Models
  96. ChemHGNN: A Hierarchical Hypergraph Neural Network for Reaction Virtual Screening and Discovery
  97. Large Language models for Time Series Analysis: Techniques, Applications, and Challenges
  98. Mini-Game Lifetime Value Prediction in WeChat
  99. Human-centered Interactive Learning via MLLMs for Text-to-Image Person Re-identification
  100. Tversky Neural Networks: Psychologically Plausible Deep Learning with Differentiable Tversky Similarity
  101. Reward Is Enough: LLMs Are In-Context Reinforcement Learners
  102. Bayes Error Rate Estimation in Difficult Situations
  103. DUAL: Dynamic Uncertainty-Aware Learning
  104. 4,500 Seconds: Small Data Training Approaches for Deep UAV Audio Classification
  105. SIMCOPILOT: Evaluating Large Language Models for Copilot-Style Code Generation
  106. Reinforcement Twinning for Hybrid Control of Flapping-Wing Drones
  107. CrossRF: A Domain-Invariant Deep Learning Approach for RF Fingerprinting
  108. NEXT-EVAL: Next Evaluation of Traditional and LLM Web Data Record Extraction
  109. Self-Interpretability: LLMs Can Describe Complex Internal Processes that Drive Their Decisions
  110. Comparative Evaluation of Prompting and Fine-Tuning for Applying Large Language Models to Grid-Structured Geospatial Data
  111. RAVEN: Query-Guided Representation Alignment for Question Answering over Audio, Video, Embedded Sensors, and Natural Language
  112. Cultural Value Alignment in Large Language Models: A Prompt-based Analysis of Schwartz Values in Gemini, ChatGPT, and DeepSeek
  113. Mitigating Cyber Risk in the Age of Open-Weight LLMs: Policy Gaps and Technical Realities
  114. REMS: a unified solution representation, problem modeling and metaheuristic algorithm design for general combinatorial optimization problems
  115. Transparency in Healthcare AI: Testing European Regulatory Provisions against Users' Transparency Needs
  116. P2P: Automated Paper-to-Poster Generation and Fine-Grained Benchmark
  117. BanglaByT5: Byte-Level Modelling for Bangla
  118. A quantitative analysis of semantic information in deep representations of text and images
  119. Learning Interpretable Representations Leads to Semantically Faithful EEG-to-Text Generation
  120. TAGS: 3D Tumor-Adaptive Guidance for SAM
  121. Are LLMs reliable? An exploration of the reliability of large language models in clinical note generation
  122. Neuromorphic Mimicry Attacks Exploiting Brain-Inspired Computing for Covert Cyber Intrusions
  123. P2VA: Converting Persona Descriptions into Voice Attributes for Fair and Controllable Text-to-Speech
  124. Covert Attacks on Machine Learning Training in Passively Secure MPC
  125. Oh SnapMMD! Forecasting Stochastic Dynamics Beyond the Schr"odinger Bridge's End
  126. BiasLab: Toward Explainable Political Bias Detection with Dual-Axis Annotations and Rationale Indicators
  127. SynEVO: A neuro-inspired spatiotemporal evolutional framework for cross-domain adaptation
  128. Small Language Models in the Real World: Insights from Industrial Text Classification
  129. Ensembling Sparse Autoencoders
  130. Bidirectional Variational Autoencoders
  131. Merge to Mix: Mixing Datasets via Model Merging
  132. Internal and External Impacts of Natural Language Processing Papers
  133. Few-Shot Test-Time Optimization Without Retraining for Semiconductor Recipe Generation and Beyond
  134. Mesh-free sparse identification of nonlinear dynamics
  135. Signals of Provenance: Practices & Challenges of Navigating Indicators in AI-Generated Media for Sighted and Blind Individuals
  136. Learning from Algorithm Feedback: One-Shot SAT Solver Guidance with GNNs
  137. Flow-based Generative Modeling of Potential Outcomes and Counterfactuals
  138. Multimodal Biomarkers for Schizophrenia: Towards Individual Symptom Severity Estimation
  139. Physics-based machine learning for mantle convection simulations
  140. An Exploratory Approach Towards Investigating and Explaining Vision Transformer and Transfer Learning for Brain Disease Detection
  141. Causal LLM Routing: End-to-End Regret Minimization from Observational Data
  142. OpenEthics: A Comprehensive Ethical Evaluation of Open-Source Generative Large Language Models
  143. Equivariant Eikonal Neural Networks: Grid-Free, Scalable Travel-Time Prediction on Homogeneous Spaces
  144. An Approach Towards Identifying Bangladeshi Leaf Diseases through Transfer Learning and XAI
  145. Learning better representations for crowded pedestrians in offboard LiDAR-camera 3D tracking-by-detection
  146. Comprehensive Lung Disease Detection Using Deep Learning Models and Hybrid Chest X-ray Data with Explainable AI
  147. Toward Theoretical Insights into Diffusion Trajectory Distillation via Operator Merging
  148. Prototypical Human-AI Collaboration Behaviors from LLM-Assisted Writing in the Wild
  149. GradPCA: Leveraging NTK Alignment for Reliable Out-of-Distribution Detection
  150. LAGO: Few-shot Crosslingual Embedding Inversion Attacks via Language Similarity-Aware Graph Optimization
  151. Evaluating Adversarial Robustness of Concept Representations in Sparse Autoencoders
  152. Causal Interventions Reveal Shared Structure Across English Filler-Gap Constructions
  153. Leveraging Online Data to Enhance Medical Knowledge in a Small Persian Language Model
  154. Exploring Flow-Lenia Universes with a Curiosity-driven AI Scientist: Discovering Diverse Ecosystem Dynamics
  155. Domain Adaptive Skin Lesion Classification via Conformal Ensemble of Vision Transformers
  156. Explaining Puzzle Solutions in Natural Language: An Exploratory Study on 6x6 Sudoku
  157. Towards Identifiability of Interventional Stochastic Differential Equations
  158. Real-Time Stress Monitoring, Detection, and Management in College Students: A Wearable Technology and Machine-Learning Approach
  159. Analyzing Hierarchical Structure in Vision Models with Sparse Autoencoders
  160. Pre-training Limited Memory Language Models with Internal and External Knowledge
  161. Super-Resolution with Structured Motion
  162. Data-driven Verification of Procedural Programs with Integer Arrays
  163. Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey
  164. Citation Parsing and Analysis with Language Models
  165. Improving the Predictability of the Madden-Julian Oscillation at Subseasonal Scales with Gaussian Process Models
  166. AllMetrics: A Unified Python Library for Standardized Metric Evaluation and Robust Data Validation in Machine Learning
  167. Extracting Probabilistic Knowledge from Large Language Models for Bayesian Network Parameterization
  168. Is (Selective) Round-To-Nearest Quantization All You Need?
  169. Last Layer Empirical Bayes
  170. Highlighting What Matters: Promptable Embeddings for Attribute-Focused Image Retrieval
  171. Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging
  172. Text-to-Pipeline: Bridging Natural Language and Data Preparation Pipelines
  173. Satellites Reveal Mobility: A Commuting Origin-destination Flow Generator for Global Cities
  174. An Inclusive Foundation Model for Generalizable Cytogenetics in Precision Oncology
  175. SCENIR: Visual Semantic Clarity through Unsupervised Scene Graph Retrieval
  176. Multi-omic Causal Discovery using Genotypes and Gene Expression
  177. Generative AI for Autonomous Driving: A Review
  178. Bandit based Dynamic Candidate Edge Selection in Solving Traveling Salesman Problems
  179. P3Net: Progressive and Periodic Perturbation for Semi-Supervised Medical Image Segmentation
  180. InstructSAM: A Training-Free Framework for Instruction-Oriented Remote Sensing Object Recognition
  181. A Taxonomy of Structure from Motion Methods
  182. Meta-Learning an In-Context Transformer Model of Human Higher Visual Cortex
  183. On the creation of narrow AI: hierarchy and nonlocality of neural network skills
  184. Neural Conditional Transport Maps
  185. The Atlas of In-Context Learning: How Attention Heads Shape In-Context Retrieval Augmentation
  186. Keep Security! Benchmarking Security Policy Preservation in Large Language Model Contexts Against Indirect Attacks in Question Answering
  187. Adaptive Estimation and Learning under Temporal Distribution Shift
  188. A Deep Learning Framework for Two-Dimensional, Multi-Frequency Propagation Factor Estimation
  189. Model Merging is Secretly Certifiable: Non-Vacuous Generalisation Bounds for Low-Shot Learning
  190. Long-Form Information Alignment Evaluation Beyond Atomic Facts
  191. Exploring the Innovation Opportunities for Pre-trained Models
  192. Fair Supervised Learning Through Constraints on Smooth Nonconvex Unfairness-Measure Surrogates
  193. Large Language Models as Computable Approximations to Solomonoff Induction
  194. Solving General-Utility Markov Decision Processes in the Single-Trial Regime with Online Planning
  195. IA-T2I: Internet-Augmented Text-to-Image Generation
  196. Projection-Based Correction for Enhancing Deep Inverse Networks
  197. ToxicTone: A Mandarin Audio Dataset Annotated for Toxicity and Toxic Utterance Tonality
  198. MIKU-PAL: An Automated and Standardized Multi-Modal Method for Speech Paralinguistic and Affect Labeling
  199. Transfer of Structural Knowledge from Synthetic Languages
  200. Constructing a 3D Scene from a Single Image
  201. Exploring The Visual Feature Space for Multimodal Neural Decoding
  202. Improving planning and MBRL with temporally-extended actions
  203. Multi-modal Integration Analysis of Alzheimer's Disease Using Large Language Models and Knowledge Graphs
  204. Higher-order Structure Boosts Link Prediction on Temporal Graphs
  205. Neuro-Argumentative Learning with Case-Based Reasoning
  206. Large Language Models and Evolutionary Computation: A Critical Review of Bidirectional Interaction, Automated Algorithm Design, and Co-Adaptive Systems
  207. HybridProver: Augmenting Theorem Proving with LLM-Driven Proof Synthesis and Refinement
  208. RUSplatting: Robust 3D Gaussian Splatting for Sparse-View Underwater Scene Reconstruction
  209. Are machine learning interpretations reliable? A stability study on global interpretations
  210. VocalBench: Benchmarking the Vocal Conversational Abilities for Speech Interaction Models
  211. Shared Path: Unraveling Memorization in Multilingual LLMs through Language Similarities
  212. Privacy-Preserving Conformal Prediction Under Local Differential Privacy
  213. LyapLock: Bounded Knowledge Preservation in Sequential Large Language Model Editing
  214. MaxPoolBERT: Enhancing BERT Classification via Layer- and Token-Wise Aggregation
  215. Can Large Language Models be Effective Online Opinion Miners?
  216. Average Reward Reinforcement Learning for Omega-Regular and Mean-Payoff Objectives
  217. A packing lemma for VCNk-dimension and learning high-dimensional data
  218. Discovering Pathology Rationale and Token Allocation for Efficient Multimodal Pathology Reasoning
  219. FedSEA-LLaMA: A Secure, Efficient and Adaptive Federated Splitting Framework for Large Language Models
  220. The Representational Alignment between Humans and Language Models is implicitly driven by a Concreteness Effect
  221. Enhancing Monte Carlo Dropout Performance for Uncertainty Quantification
  222. SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model
  223. Segmentation-Variant Codebooks for Preservation of Paralinguistic and Prosodic Information
  224. Transformer-Based Neural Quantum Digital Twins for Many-Body Spectral Reconstruction and Adaptive Quantum-Annealing Schedule Design
  225. Deep greedy unfolding: Sorting out argsorting in greedy sparse recovery algorithms
  226. LCDB 1.1: A Database Illustrating Learning Curves Are More Ill-Behaved Than Previously Thought
  227. The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection
  228. Learning Small Decision Trees with Few Outliers: A Parameterized Perspective
  229. Second-Order Convergence in Private Stochastic Non-Convex Optimization
  230. Word Level Timestamp Generation for Automatic Speech Recognition and Translation
  231. Optimal Best-Arm Identification under Fixed Confidence with Multiple Optima
  232. A Simple Approximation Algorithm for Optimal Decision Tree
  233. Bayesian Ensembling: Insights from Online Optimization and Empirical Bayes
  234. Oral Imaging for Malocclusion Issues Assessments: OMNI Dataset, Deep Learning Baselines and Benchmarking
  235. Distance Adaptive Beam Search for Provably Accurate Graph-Based Nearest Neighbor Search
  236. Guidelines for the Quality Assessment of Energy-Aware NAS Benchmarks
  237. SNAP: A Benchmark for Testing the Effects of Capture Conditions on Fundamental Vision Tasks
  238. Mechanistic Insights into Grokking from the Embedding Layer
  239. Benchmarking Energy and Latency in TinyML: A Novel Method for Resource-Constrained AI
  240. From Problem-Solving to Teaching Problem-Solving: Aligning LLMs with Pedagogy using Reinforcement Learning
  241. Deep Learning for Continuous-Time Stochastic Control with Jumps
  242. Exploring LLM-Generated Feedback for Economics Essays: How Teaching Assistants Evaluate and Envision Its Use
  243. A Methodology to Evaluate Strategies Predicting Rankings on Unseen Domains
  244. Beyond Classification: Evaluating Diffusion Denoised Smoothing for Security-Utility Trade off
  245. VP Lab: a PEFT-Enabled Visual Prompting Laboratory for Semantic Segmentation
  246. MIRB: Mathematical Information Retrieval Benchmark
  247. Advancing Marine Research: UWSAM Framework and UIIS10K Dataset for Precise Underwater Instance Segmentation
  248. Federated Learning with Unlabeled Clients: Personalization Can Happen in Low Dimensions
  249. Bridging the Domain Gap in Equation Distillation with Reinforcement Feedback
  250. Out-of-Distribution Detection via Channelwise Feature Aggregation in Neural Network-Based Receivers
  251. Semantic-based Unsupervised Framing Analysis (SUFA): A Novel Approach for Computational Framing Analysis
  252. Impact of Data Sparsity on Machine Learning for Fault Detection in Power System Protection
  253. Moonbeam: A MIDI Foundation Model Using Both Absolute and Relative Music Attributes
  254. Robo-DM: Data Management For Large Robot Datasets
  255. Modular Jump Gaussian Processes
  256. A Survey on Multilingual Mental Disorders Detection from Social Media Data
  257. DayDreamer at CQs-Gen 2025: Generating Critical Questions through Argument Scheme Completion
  258. Social Bias in Popular Question-Answering Benchmarks
  259. Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training
  260. Oversmoothing, Oversquashing, Heterophily, Long-Range, and more: Demystifying Common Beliefs in Graph Machine Learning
  261. Multi-View Projection for Unsupervised Domain Adaptation in 3D Semantic Segmentation
  262. A Temporal Difference Method for Stochastic Continuous Dynamics
  263. Convolutional Long Short-Term Memory Neural Networks Based Numerical Simulation of Flow Field
  264. PlantDreamer: Achieving Realistic 3D Plant Models with Diffusion-Guided Gaussian Splatting
  265. Evaluate Bias without Manual Test Sets: A Concept Representation Perspective for LLMs
  266. Detection of Underwater Multi-Targets Based on Self-Supervised Learning and Deformable Path Aggregation Feature Pyramid Network
  267. Explainable embeddings with Distance Explainer
  268. AM-PPO: (Advantage) Alpha-Modulation with Proximal Policy Optimization
  269. NOMAD Projection
  270. Directional Non-Commutative Monoidal Structures for Compositional Embeddings in Machine Learning
  271. Deep Learning Enabled Segmentation, Classification and Risk Assessment of Cervical Cancer
  272. Exploiting Low-Dimensional Manifold of Features for Few-Shot Whole Slide Image Classification
  273. Coloring Between the Lines: Personalization in the Null Space of Planning Constraints
  274. Protoknowledge Shapes Behaviour of LLMs in Downstream Tasks: Memorization and Generalization with Knowledge Graphs
  275. Certified Neural Approximations of Nonlinear Dynamics
  276. Fast Rate Bounds for Multi-Task and Meta-Learning with Different Sample Sizes
  277. Spectral-Aware Global Fusion for RGB-Thermal Semantic Segmentation
  278. Collaborative Problem-Solving in an Optimization Game
  279. Machine Learning Derived Blood Input for Dynamic PET Images of Rat Heart
  280. KaFT: Knowledge-aware Fine-tuning for Boosting LLMs' Domain-specific Question-Answering Performance
  281. Pura: An Efficient Privacy-Preserving Solution for Face Recognition
  282. LFTF: Locating First and Then Fine-Tuning for Mitigating Gender Bias in Large Language Models
  283. A Qualitative Investigation into LLM-Generated Multilingual Code Comments and Automatic Evaluation Metrics
  284. Joint Flashback Adaptation for Forgetting-Resistant Instruction Tuning
  285. A Participatory Strategy for AI Ethics in Education and Rehabilitation grounded in the Capability Approach
  286. AI-based Decision Support System for Heritage Aircraft Corrosion Prevention
  287. Teaching Language Models to Evolve with Users: Dynamic Profile Modeling for Personalized Alignment
  288. ViaRL: Adaptive Temporal Grounding via Visual Iterated Amplification Reinforcement Learning
  289. ALIEN: Aligned Entropy Head for Improving Uncertainty Estimation of LLMs
  290. On the Generalization vs Fidelity Paradox in Knowledge Distillation
  291. Quick ViTs: Speeding up Vision Transformers through Equivariance
  292. FRN: Fractal-Based Recursive Spectral Reconstruction Network
  293. Bridging Sign and Spoken Languages: Pseudo Gloss Generation for Sign Language Translation
  294. Adaptive Cumulative Mass Calibration with Conformal Prediction
  295. Set-LLM: A Permutation-Invariant LLM
  296. Uncertainty Quantification in SVM prediction
  297. Likelihood Variance as Text Importance for Resampling Texts to Map Language Models
  298. NeoN: A Tool for Automated Detection, Linguistic and LLM-Driven Analysis of Neologisms in Polish
  299. Gated Integration of Low-Rank Adaptation for Continual Learning of Large Language Models
  300. SplitWise Regression: Stepwise Modeling with Adaptive Dummy Encoding
  301. Trends and Challenges in Authorship Analysis: A Review of ML, DL, and LLM Approaches
  302. Guided Policy Optimization under Partial Observability
  303. Robust Multimodal Learning via Entropy-Gated Contrastive Fusion
  304. ClickSight: Interpreting Student Clickstreams to Reveal Insights on Learning Strategies via LLMs
  305. Mouse Lockbox Dataset: Behavior Recognition for Mice Solving Lockboxes
  306. Efficient Differentiable Approximation of Generalized Low-rank Regularization
  307. HOPSE: Scalable Higher-Order Positional and Structural Encoder for Combinatorial Representations
  308. Prosody-Adaptable Audio Codecs for Zero-Shot Voice Conversion via In-Context Learning
  309. Visual Question Answering on Multiple Remote Sensing Image Modalities
  310. Expanding Zero-Shot Object Counting with Rich Prompts
  311. InTreeger: An End-to-End Framework for Integer-Only Decision Tree Inference
  312. RePPL: Recalibrating Perplexity by Uncertainty in Semantic Propagation and Language Generation for Explainable QA Hallucination Detection
  313. EVA: Expressive Virtual Avatars from Multi-view Videos
  314. Inter-Subject Variance Transfer Learning for EMG Pattern Classification Based on Bayesian Inference
  315. The P3 Dataset: Pixels, Points and Polygons for Multimodal Building Vectorization
  316. Distributionally Robust Federated Learning with Client Drift Minimization
  317. AI vs. Human Judgment of Content Moderation: LLM-as-a-Judge and Ethics-Based Response Refusals
  318. Objective Bicycle Occlusion Level Classification using a Deformable Parts-Based Model
  319. NL-Debugging: Exploiting Natural Language as an Intermediate Representation for Code Debugging
  320. Decoding Phone Pairs from MEG Signals Across Speech Modalities
  321. Post-Training Corrections for Improved Time-Series Forecasting
  322. Establishing a Scale for Kullback-Leibler Divergence in Language Models Across Various Settings
  323. The Super Emotion Dataset
  324. Hadamax Encoding: Elevating Performance in Model-Free Atari
  325. Policy Testing in Markov Decision Processes
  326. Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text Detectors
  327. Parameter-Efficient Fine-Tuning of Multispectral Foundation Models for Hyperspectral Image Classification
  328. Leveraging Unit Language Guidance to Advance Speech Modeling in Textless Speech-to-Speech Translation
  329. Fourier-Invertible Neural Encoder (FINE) for Homogeneous Flows
  330. SoftHGNN: Soft Hypergraph Neural Networks for General Visual Recognition
  331. Improving LLM First-Token Predictions in Multiple-Choice Question Answering via Output Prefilling
  332. CEBSNet: Change-Excited and Background-Suppressed Network with Temporal Dependency Modeling for Bitemporal Change Detection
  333. Emotional Supporters often Use Multiple Strategies in a Single Turn
  334. Sonnet: Spectral Operator Neural Network for Multivariable Time Series Forecasting
  335. BadSR: Stealthy Label Backdoor Attacks on Image Super-Resolution
  336. Laplace Sample Information: Data Informativeness Through a Bayesian Lens
  337. Multi-Hop Question Generation via Dual-Perspective Keyword Guidance
  338. Chinese Toxic Language Mitigation via Sentiment Polarity Consistent Rewrites
  339. R3GS: Gaussian Splatting for Robust Reconstruction and Relocalization in Unconstrained Image Collections
  340. LLM-Explorer: A Plug-in Reinforcement Learning Policy Exploration Enhancement Driven by Large Language Models
  341. Hallucinate at the Last in Long Response Generation: A Case Study on Long Document Summarization
  342. GS2E: Gaussian Splatting is an Effective Data Generator for Event Stream Generation
  343. Reconsider the Template Mesh in Deep Learning-based Mesh Reconstruction
  344. Kernel PCA for Out-of-Distribution Detection: Non-Linear Kernel Selection and Approximation
  345. Exploring In-Image Machine Translation with Real-World Background
  346. Learning-based Autonomous Oversteer Control and Collision Avoidance
  347. Identification of Probabilities of Causation: from Recursive to Closed-Form Bounds
  348. DiffProb: Data Pruning for Face Recognition
  349. Contrastive Learning-Enhanced Trajectory Matching for Small-Scale Dataset Distillation
  350. Blind Spot Navigation: Evolutionary Discovery of Sensitive Semantic Concepts for LVLMs
  351. gen2seg: Generative Models Enable Generalizable Instance Segmentation
  352. AGENT-X: Adaptive Guideline-based Expert Network for Threshold-free AI-generated teXt detection
  353. Zero-Shot Gaze-based Volumetric Medical Image Segmentation
  354. Boosting Large Language Models for Mental Manipulation Detection via Data Augmentation and Distillation
  355. An Efficient Private GPT Never Autoregressively Decodes
  356. Loss-Guided Auxiliary Agents for Overcoming Mode Collapse in GFlowNets
  357. Margin-aware Fuzzy Rough Feature Selection: Bridging Uncertainty Characterization and Pattern Classification
  358. VET-DINO: Learning Anatomical Understanding Through Multi-View Distillation in Veterinary Imaging
  359. Mitigating Spurious Correlations with Causal Logit Perturbation
  360. Reliable Vertical Federated Learning in 5G Core Network Architecture
  361. Adaptive Plan-Execute Framework for Smart Contract Security Auditing
  362. Disentangled Geometric Alignment with Adaptive Contrastive Perturbation for Reliable Domain Transfer
  363. Generalised Probabilistic Modelling and Improved Uncertainty Estimation in Comparative LLM-as-a-judge
  364. Neural Collapse is Globally Optimal in Deep Regularized ResNets and Transformers
  365. X-GRM: Large Gaussian Reconstruction Model for Sparse-view X-rays to Computed Tomography
  366. CAD: A General Multimodal Framework for Video Deepfake Detection via Cross-Modal Alignment and Distillation
  367. DC-Scene: Data-Centric Learning for 3D Scene Understanding
  368. Finding separatrices of dynamical flows with Deep Koopman Eigenfunctions
  369. Multilingual Prompting for Improving LLM Generation Diversity
  370. Degree-Optimized Cumulative Polynomial Kolmogorov-Arnold Networks
  371. Continuous Representation Methods, Theories, and Applications: An Overview and Perspectives
  372. Estimation methods of Matrix-valued AR model
  373. Versatile Reservoir Computing for Heterogeneous Complex Networks
  374. Recognition of Unseen Combined Motions via Convex Combination-based EMG Pattern Synthesis for Myoelectric Control
  375. Multimodal Conditional Information Bottleneck for Generalizable AI-Generated Image Detection
  376. Clustering and Pruning in Causal Data Fusion
  377. KernelOracle: Predicting the Linux Scheduler's Next Move with Deep Learning
  378. Group Distributionally Robust Optimization with Flexible Sample Queries
  379. GT2-GS: Geometry-aware Texture Transfer for Gaussian Splatting
  380. EndoVLA: Dual-Phase Vision-Language-Action Model for Autonomous Tracking in Endoscopy
  381. Flashback: Memory-Driven Zero-shot, Real-time Video Anomaly Detection
  382. EEG-Based Inter-Patient Epileptic Seizure Detection Combining Domain Adversarial Training with CNN-BiLSTM Network
  383. Reconstruction of Graph Signals on Complex Manifolds with Kernel Methods
  384. Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problems
  385. Intentional Gesture: Deliver Your Intentions with Gestures for Speech
  386. EcomScriptBench: A Multi-task Benchmark for E-commerce Script Planning via Step-wise Intention-Driven Product Association
  387. Self-Boost via Optimal Retraining: An Analysis via Approximate Message Passing
  388. GAMA: Geometry-Aware Manifold Alignment via Structured Adversarial Perturbations for Robust Domain Adaptation
  389. Leveraging Foundation Models for Multimodal Graph-Based Action Recognition
  390. Geometrically Regularized Transfer Learning with On-Manifold and Off-Manifold Perturbation
  391. MonoSplat: Generalizable 3D Gaussian Splatting from Monocular Depth Foundation Models
  392. AuxDet: Auxiliary Metadata Matters for Omni-Domain Infrared Small Target Detection
  393. NeuBM: Mitigating Model Bias in Graph Neural Networks through Neutral Input Calibration
  394. SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps
  395. Improving the generalization of gait recognition with limited datasets
  396. Enhancing Certified Robustness via Block Reflector Orthogonal Layers and Logit Annealing Loss
  397. AvatarShield: Visual Reinforcement Learning for Human-Centric Synthetic Video Detection
  398. Harnessing Caption Detailness for Data-Efficient Text-to-Image Generation
  399. Sculpting Features from Noise: Reward-Guided Hierarchical Diffusion for Task-Optimal Feature Transformation
  400. From Pixels to Images: A Structural Survey of Deep Learning Paradigms in Remote Sensing Image Semantic Segmentation
  401. lmgame-Bench: How Good are LLMs at Playing Games?
  402. CineTechBench: A Benchmark for Cinematographic Technique Understanding and Generation
  403. Filtering Learning Histories Enhances In-Context Reinforcement Learning
  404. EC-LDA : Label Distribution Inference Attack against Federated Graph Learning with Embedding Compression
  405. Unified Cross-Modal Attention-Mixer Based Structural-Functional Connectomics Fusion for Neuropsychiatric Disorder Diagnosis
  406. Global Convergence for Average Reward Constrained MDPs with Primal-Dual Actor Critic Algorithm
  407. Multispectral Detection Transformer with Infrared-Centric Feature Fusion
  408. Physics-Guided Multi-View Graph Neural Network for Schizophrenia Classification via Structural-Functional Coupling
  409. DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer
  410. Seeing the Trees for the Forest: Rethinking Weakly-Supervised Medical Visual Grounding
  411. Lung Nodule-SSM: Self-Supervised Lung Nodule Detection and Classification in Thoracic CT Images
  412. Graph Foundation Models: A Comprehensive Survey
  413. Khan-GCL: Kolmogorov-Arnold Network Based Graph Contrastive Learning with Hard Negatives
  414. Cost-aware LLM-based Online Dataset Annotation
  415. Object-Focus Actor for Data-efficient Robot Generalization Dexterous Manipulation
  416. Nek Minit: Harnessing Pragmatic Metacognitive Prompting for Explainable Sarcasm Detection of Australian and Indian English
  417. SciCUEval: A Comprehensive Dataset for Evaluating Scientific Context Understanding in Large Language Models
  418. DeFTX: Denoised Sparse Fine-Tuning for Zero-Shot Cross-Lingual Transfer
  419. Leveraging Large Language Models for Command Injection Vulnerability Analysis in Python: An Empirical Study on Popular Open-Source Projects
  420. HopWeaver: Cross-Document Synthesis of High-Quality and Authentic Multi-Hop Questions
  421. Robust Multi-Modal Forecasting: Integrating Static and Dynamic Features
  422. SUS backprop: linear backpropagation algorithm for long inputs in transformers
  423. MoTime: A Dataset Suite for Multimodal Time Series Forecasting
  424. Can Large Language Models Understand Internet Buzzwords Through User-Generated Content
  425. An Alternative to FLOPS Regularization to Effectively Productionize SPLADE-Doc
  426. In-Domain African Languages Translation Using LLMs and Multi-armed Bandits
  427. ModelingAgent: Bridging LLMs and Mathematical Modeling for Real-World Challenges
  428. The Pursuit of Empathy: Evaluating Small Language Models for PTSD Dialogue Support
  429. Why and When Deep is Better than Shallow: Implementation-Agnostic State-Transition Model of Deep Learning
  430. Restricted Spectral Gap Decomposition for Simulated Tempering Targeting Mixture Distributions
  431. MolLangBench: A Comprehensive Benchmark for Language-Prompted Molecular Structure Recognition, Editing, and Generation
  432. Entailed Opinion Matters: Improving the Fact-Checking Performance of Language Models by Relying on their Entailment Ability
  433. Towards a Working Definition of Designing Generative User Interfaces
  434. ChartCards: A Chart-Metadata Generation Framework for Multi-Task Chart Understanding
  435. Diffusion vs. Autoregressive Language Models: A Text Embedding Perspective
  436. Learning-based Airflow Inertial Odometry for MAVs using Thermal Anemometers in a GPS and vision denied environment
  437. LogiCase: Effective Test Case Generation from Logical Description in Competitive Programming
  438. Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering
  439. Fault-Tolerant Multi-Robot Coordination with Limited Sensing within Confined Environments
  440. Toward Task Capable Active Matter: Learning to Avoid Clogging in Confined Collectives via Collisions
  441. Are the confidence scores of reviewers consistent with the review content? Evidence from top conference proceedings in AI
  442. A Systematic Evaluation of On-Device LLMs: Quantization, Performance, and Resources
  443. Diagnosing our datasets: How does my language model learn clinical information?
  444. Towards a Science of Causal Interpretability in Deep Learning for Software Engineering
  445. Infinite hierarchical contrastive clustering for personal digital envirotyping
  446. Multi-Scale Harmonic Encoding for Feature-Wise Graph Message Passing
  447. Convergence of Adam in Deep ReLU Networks via Directional Complexity and Kakeya Bounds
  448. HAVA: Hybrid Approach to Value-Alignment through Reward Weighing for Reinforcement Learning
  449. How Transformers Learn In-Context Recall Tasks? Optimality, Training Dynamics and Generalization
  450. Know When to Abstain: Optimal Selective Classification with Likelihood Ratios
  451. Unraveling the iterative CHAD
  452. Effective and Efficient Schema-aware Information Extraction Using On-Device Large Language Models
  453. Language Specific Knowledge: Do Models Know Better in X than in English?
  454. AnyBody: A Benchmark Suite for Cross-Embodiment Manipulation
  455. Pre-validation Revisited
  456. CRAFT: Training-Free Cascaded Retrieval for Tabular QA
  457. Toward Informed AV Decision-Making: Computational Model of Well-being and Trust in Mobility