mlsanityData to 14 Oct 2026

Papers

New on arXiv

Fri 30 May 2025

536 papers

  1. RAST: Reasoning Activation in LLMs via Small-model TransferLLM reasoning → Reinforcement learning for reasoning
  2. Every Rollout Counts: Optimal Resource Allocation for Efficient Test-Time ScalingLLM reasoning → Test-time compute and efficient thinking
  3. MDPO: Multi-Granularity Direct Preference Optimization for Mathematical ReasoningLLM reasoning → Mathematical reasoning +1
  4. Minifinetuning: Low-Data Generation Domain Adaptation through Corrective Self-DistillationKnowledge distillation → Knowledge distillation for LLMs
  5. Compiler-R1: Towards Agentic Compiler Auto-tuning with Reinforcement LearningLLM agents and tool use → Software engineering coding agents
  6. Who is in the Spotlight: The Hidden Bias Undermining Multimodal Retrieval-Augmented GenerationRetrieval-augmented generation → Multimodal RAG
  7. Memory OS of AI AgentLLM agents and tool use → Agent memory systems
  8. A Red Teaming Roadmap Towards System-Level SafetyLLM safety and security → Prompt injection and agent security
  9. Continual Learning in Vision-Language Models via Aligned Model MergingMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  10. Lossless Token Sequence Compression via Meta-TokensEfficient LLM inference and serving → Prompt and context compression
  11. Inference-Time Alignment of Diffusion Models via Evolutionary AlgorithmsDiffusion models → Diffusion foundations and sampling
  12. DLM-One: Diffusion Language Models for One-Step Sequence GenerationDiffusion models → Discrete and text diffusion
  13. Recursive Entropic Risk Optimization in Discounted MDPs: Sample Complexity Bounds with a Generative ModelDeep reinforcement learning methods → RL theory and sample complexity
  14. Adversarial Threat Vectors and Risk Mitigation for Retrieval-Augmented Generation SystemsRetrieval-augmented generation → Privacy and security of RAG +1
  15. Chances and Challenges of the Model Context Protocol in Digital Forensics and Incident ResponseLLM agents and tool use → Agent threats, guardrails and governance
  16. GPR: Empowering Generation with Graph-Pretrained RetrieverRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  17. Hidden in Plain Sight: Reasoning in Underspecified and Misspecified Scenarios for Multimodal LLMsLLM reasoning → Multimodal reasoning +1
  18. Aligned but Blind: Alignment Increases Implicit Bias by Reducing Awareness of RaceLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment +1
  19. MIR: Methodology Inspiration Retrieval for Scientific Research ProblemsLLM reasoning → Knowledge- and tool-augmented reasoning
  20. MedOrch: Medical Diagnosis with Tool-Augmented Reasoning Agents for Flexible ExtensibilityLLM reasoning → Clinical and biomedical applications +1
  21. ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question AnsweringRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  22. Ctrl-Crash: Controllable Diffusion for Realistic Car CrashesDiffusion models → Diffusion and flow policies for robotics
  23. Diff-SPORT: Diffusion-based Sensor Placement Optimization and Reconstruction of Turbulent flows in urban environmentsDiffusion models → Flow matching, time series and science
  24. REIC: RAG-Enhanced Intent Classification at ScaleRetrieval-augmented generation → RAG pipeline design and evaluation
  25. Let Them Down Easy! Contextual Effects of LLM Guardrails on User Perceptions and PreferencesLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  26. Control-R: Towards controllable test-time scalingLLM reasoning → Prompting and chain-of-thought reasoning
  27. Breakpoint: Scalable evaluation of system-level reasoning in LLM code agentsLLM reasoning → Reasoning for agents, planning and code +1
  28. Disentangled Safety Adapters Enable Efficient Guardrails and Flexible Inference-Time AlignmentLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  29. Verbal Werewolf: Engage Users with Verbalized Agentic Werewolf Game FrameworkLLM agents and tool use → Reinforcement learning for LLM agents
  30. Aligning Language Models with Observational Data: Opportunities and Risks from a Causal PerspectiveLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  31. Intrinsic Goals for Autonomous Agents: Model-Based Exploration in Virtual Zebrafish Predicts Ethological Behavior and Whole-Brain DynamicsDeep reinforcement learning methods → Deep RL algorithms and representations
  32. On Designing Diffusion Autoencoders for Efficient Generation and Representation LearningDiffusion models → Diffusion foundations and sampling
  33. Belief-Based Offline Reinforcement Learning for Delay-Robust Policy OptimizationOffline RL and imitation learning from data → Offline RL algorithms
  34. Visual Embodied Brain: Let Multimodal Large Language Models See, Think, and Control in SpacesLLM reasoning → Spatial and embodied reasoning +1
  35. Writing-Zero: Bridge the Gap Between Non-verifiable Tasks and Verifiable RewardsLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  36. Interactive Imitation Learning for Dexterous Robotic Manipulation: Challenges and Perspectives -- A SurveyOffline RL and imitation learning from data → Robot manipulation imitation learning
  37. Navigation of a Three-Link Microswimmer via Deep Reinforcement LearningDeep reinforcement learning methods → RL for robot navigation and UAV control
  38. Who Gets the Kidney? Human-AI Alignment, Indecision, and Moral ValuesLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  39. Open CaptchaWorld: A Comprehensive Web-based Platform for Testing and Benchmarking Multimodal LLM AgentsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  40. Agent-X: Evaluating Deep Multimodal Reasoning in Vision-Centric Agentic TasksLLM reasoning → Multimodal reasoning +1
  41. ReasonGen-R1: CoT for Autoregressive Image generation models through SFT and RLLLM reasoning → Multimodal reasoning
  42. MiniMax-Remover: Taming Bad Noise Helps Video Object RemovalDiffusion models → Inverse problems and image restoration
  43. ProxyThinker: Test-Time Guidance through Small Visual ReasonersLLM reasoning → Multimodal reasoning +1
  44. MoDoMoDo: Multi-Domain Data Mixtures for Multimodal LLM Reinforcement LearningMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  45. SiLVR: A Simple Language-based Video Reasoning FrameworkLLM reasoning → Multimodal reasoning
  46. Time Blindness: Why Video-Language Models Can't See What Humans Can?Multimodal LLMs / vision-language models → Video understanding with MLLMs
  47. ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language ModelsLLM reasoning → Reinforcement learning for reasoning
  48. AlphaOne: Reasoning Models Thinking Slow and Fast at Test TimeLLM reasoning → Test-time compute and efficient thinking
  49. Beyond Multiple Choice: Evaluating Steering Vectors for SummarizationMechanistic interpretability → Activation steering methods
  50. Accelerated Sampling from Masked Diffusion Models via Entropy Bounded UnmaskingDiffusion models → Discrete and text diffusion
  51. Harnessing Negative Signals: Reinforcement Distillation from Teacher Data for LLM ReasoningLLM reasoning → Reinforcement learning for reasoning +2
  52. MiCRo: Mixture Modeling and Context-aware Routing for Personalized Preference LearningLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  53. Improving Reliability and Explainability of Medical Question Answering through Atomic Fact Checking in Retrieval-Augmented LLMsRetrieval-augmented generation → Medical and biomedical RAG
  54. PhySense: Principle-Based Physics Reasoning Benchmarking for Large Language ModelsLLM reasoning → Spatial and embodied reasoning
  55. RealDrive: Retrieval-Augmented Driving with Diffusion ModelsRetrieval-augmented generation → Multimodal RAG +2
  56. Draw ALL Your Imagine: A Holistic Benchmark and Agent Framework for Complex Instruction-based Image GenerationLLM agents and tool use → Multimodal and embodied agents
  57. AXIOM: Learning to Play Games in Minutes with Expanding Object-Centric ModelsDeep reinforcement learning methods → Deep RL algorithms and representations
  58. Generalization Dynamics of Linear Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  59. Circuit Stability Characterizes Language Model GeneralizationMechanistic interpretability → Circuits and mechanistic analysis
  60. Reflect, Retry, Reward: Self-Improving LLMs via Reinforcement LearningSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training
  61. Reinforcing Video Reasoning with Focused ThinkingLLM reasoning → Multimodal reasoning +1
  62. FinMME: Benchmark Dataset for Financial Multi-Modal Reasoning EvaluationLLM reasoning → Reasoning for agents, planning and code +1
  63. On Symmetric Losses for Robust Policy Optimization with Noisy PreferencesLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  64. Conformal Prediction for Zero-Shot ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  65. Speech-to-Text Translation with Phoneme-Augmented CoT: Enhancing Cross-Lingual Transfer in Low-Resource ScenariosLLM reasoning → Audio-language model reasoning
  66. Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding ExplorationLLM reasoning → Test-time compute and efficient thinking
  67. TumorGen: Boundary-Aware Tumor-Mask Synthesis with Rectified Flow MatchingDiffusion models → Medical imaging and segmentation
  68. TRIDENT: Enhancing Large Language Model Safety with Tri-Dimensional Diversified Red-Teaming Data SynthesisSynthetic data and self-improvement for LLMs → Safety of self-evolving systems +1
  69. Multiple LLM Agents Debate for Equitable Cultural AlignmentLLM agents and tool use → Social simulation and multi-agent debate
  70. BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  71. Are Optimal Algorithms Still Optimal? Rethinking Sorting in LLM-Based Pairwise Ranking with Batching and CachingLLM reasoning → Knowledge- and tool-augmented reasoning
  72. Reasoning Models Hallucinate More: Factuality-Aware Reinforcement Learning for Large Reasoning ModelsLLM reasoning → Hallucination detection and mitigation
  73. Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry PriorsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  74. Mixture-of-Experts for Personalized and Semantic-Aware Next Location PredictionMixture-of-experts → MoE for time series and graphs
  75. Decoding Knowledge Attribution in Mixture-of-Experts: A Framework of Basic-Refinement Collaboration and Efficiency AnalysisMixture-of-experts → Expert routing strategies
  76. AutoChemSchematic AI: Agentic Physics-Aware Automation for Chemical Manufacturing Scale-UpLLM agents and tool use → Medical and scientific domain agents
  77. A Composite Predictive-Generative Approach to Monaural Universal Speech EnhancementDiffusion models → Audio, speech and music
  78. NexusSum: Hierarchical LLM Agents for Long-Form Narrative SummarizationLLM agents and tool use → Multimodal and embodied agents
  79. Fine-tuning for Data-enabled Predictive Control of Noisy Systems by Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  80. CREFT: Sequential Multi-Agent LLM for Character Relation ExtractionLLM agents and tool use → Multimodal and embodied agents
  81. A*-Thought: Efficient Reasoning via Bidirectional Compression for Low-Resource SettingsLLM reasoning → Test-time compute and efficient thinking
  82. Cross-Attention Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  83. Mixpert: Mitigating Multimodal Learning Conflicts with Efficient Mixture-of-Vision-ExpertsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  84. CHIP: Chameleon Hash-based Irreversible Passport for Robust Deep Model Ownership Verification and Active Usage ControlLLM safety and security → Watermarking generated content and models
  85. UniGeo: Taming Video Diffusion for Unified Consistent Geometry EstimationDiffusion models → 3D, point cloud and scene generation
  86. AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak DefendersMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  87. Can Slow-thinking LLMs Reason Over Time? Empirical Studies in Time Series ForecastingLLM reasoning → Time series reasoning
  88. Reason-SVG: Enhancing Structured Reasoning for Vector Graphics Generation with Reinforcement LearningLLM reasoning → Multimodal reasoning
  89. ACM-UNet: Adaptive Integration of CNNs and Mamba for Efficient Medical Image SegmentationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  90. Optimizing the Interface Between Knowledge Graphs and LLMs for Complex ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
  91. Period-LLM: Extending the Periodic Capability of Multimodal Large Language ModelMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  92. Train One Sparse Autoencoder Across Multiple Sparsity Budgets to Preserve Interpretability and AccuracyMechanistic interpretability → Sparse autoencoder training and evaluation
  93. SEAR: A Multimodal Dataset for Analyzing AR-LLM-Driven Social Engineering BehaviorsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  94. LPASS: Linear Probes as Stepping Stones for vulnerability detection using compressed LLMsMechanistic interpretability → Steering and probing for LLM safety
  95. When Large Multimodal Models Confront Evolving Knowledge: Challenges and ExplorationsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  96. Learning Safety Constraints for Large Language ModelsLLM safety and security → Safety alignment, refusal and guardrails
  97. RMoA: Optimizing Mixture-of-Agents through Diversity Maximization and Residual CompensationLLM agents and tool use → General LLM agent frameworks and benchmarks
  98. Graph Flow Matching: Enhancing Image Generation with Neighbor-Aware Flow FieldsDiffusion models → Flow matching, time series and science
  99. Model Unlearning via Sparse Autoencoder Subspace Guided ProjectionsLLM safety and security → Machine unlearning +1
  100. Advancing Compositional Awareness in CLIP with Efficient Fine-TuningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
All 536
  1. MMAFFBen: A Multilingual and Multimodal Affective Analysis Benchmark for Evaluating LLMs and VLMsMultimodal LLMs / vision-language models → Multimodal emotion understanding
  2. EasyText: Controllable Diffusion Transformer for Multilingual Text RenderingDiffusion models → Image generation, text-to-image and editing
  3. When Language Shapes Thought: Cross-Lingual Transfer of Factual Knowledge in Question AnsweringLLM reasoning → Reasoning benchmarks and evaluation
  4. IRBridge: Solving Image Restoration Bridge with Pre-trained Generative Diffusion ModelsDiffusion models → Inverse problems and image restoration
  5. Reactive Aerobatic Flight via Reinforcement LearningDeep reinforcement learning methods → RL for robot navigation and UAV control
  6. ClueAnchor: Clue-Anchored Knowledge Reasoning Exploration and Optimization for Retrieval-Augmented GenerationLLM reasoning → Knowledge- and tool-augmented reasoning +1
  7. Unlearned but Not Forgotten: Data Extraction after Exact Unlearning in LLMLLM safety and security → Machine unlearning
  8. Mastering Massive Multi-Task Reinforcement Learning via Mixture-of-Expert Decision TransformerMixture-of-experts → MoE in reinforcement learning and robotics +2
  9. LLM Inference Enhanced by External Knowledge: A SurveyLLM reasoning → Reasoning benchmarks and evaluation
  10. Adversarial Preference Learning for Robust LLM AlignmentLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks
  11. Knowing Before Saying: LLM Representations Encode Information About Chain-of-Thought Success Before CompletionLLM reasoning → Prompting and chain-of-thought reasoning
  12. Revisiting Cross-Modal Knowledge Distillation: A Disentanglement Approach for RGBD Semantic SegmentationKnowledge distillation → Detection and dense prediction distillation
  13. Interpreting Large Text-to-Image Diffusion Models with Dictionary LearningDiffusion models → Diffusion foundations and sampling +1
  14. ReCalKV: Low-Rank KV Cache Compression via Head Reordering and Offline CalibrationEfficient LLM inference and serving → KV cache optimization
  15. Unifying Language Agent Algorithms with Graph-based Orchestration Engine for Reproducible Agent ResearchLLM agents and tool use → General LLM agent frameworks and benchmarks
  16. Imitation Learning-Based Path Generation for the Complex Assembly of Deformable ObjectsOffline RL and imitation learning from data → Robot manipulation imitation learning
  17. DeepDiver: Adaptive Search Intensity Scaling via Open-Web Reinforcement LearningLLM reasoning → Knowledge- and tool-augmented reasoning +1
  18. ROAD: Responsibility-Oriented Reward Design for Reinforcement Learning in Autonomous DrivingEnd-to-end autonomous driving → Reinforcement learning for driving +1
  19. Progressive Class-level DistillationKnowledge distillation → General knowledge distillation methods
  20. AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language ReasoningLLM reasoning → Reinforcement learning for reasoning
  21. How Much Backtracking is Enough? Exploring the Interplay of SFT and RL in Enhancing LLM ReasoningLLM reasoning → Reinforcement learning for reasoning
  22. MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample SelectionDiffusion models → Robustness, privacy and adversarial aspects +1
  23. Generative AI for Urban Design: A Stepwise Approach Integrating Human Expertise with Multimodal Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
  24. Out of Sight, Not Out of Context? Egocentric Spatial Reasoning in VLMs Across Disjoint FramesLLM reasoning → Spatial and embodied reasoning
  25. Effects of Theory of Mind and Prosocial Beliefs on Steering Human-Aligned Behaviors of LLMs in Ultimatum GamesLLM reasoning → Reasoning for agents, planning and code
  26. Interactive Video Generation via Domain AdaptationDiffusion models → Video generation
  27. A Reward-driven Automated Webshell Malicious-code Generator for Red-teamingLLM safety and security → Prompt injection and agent security
  28. Mamba Knockout for Unraveling Factual Information FlowState-space sequence models (S4, Mamba) → Core SSM architectures for language
  29. An Adversary-Resistant Multi-Agent LLM System via Credibility ScoringLLM agents and tool use → Agent threats, guardrails and governance
  30. MIRAGE: Assessing Hallucination in Multimodal Reasoning Chains of MLLMLLM reasoning → Hallucination detection and mitigation +1
  31. From Hallucinations to Jailbreaks: Rethinking the Vulnerability of Large Foundation ModelsLLM safety and security → Jailbreaking
  32. Light as Deception: GPT-driven Natural Relighting Against Vision-Language Pre-training ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  33. E^2GraphRAG: Streamlining Graph-based RAG for High Efficiency and EffectivenessRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  34. Reasoning Can Hurt the Inductive Abilities of Large Language ModelsLLM reasoning → Prompting and chain-of-thought reasoning
  35. Unleashing High-Quality Image Generation in Diffusion Sampling Using Second-Order Levenberg-Marquardt-LangevinDiffusion models → Diffusion foundations and sampling
  36. Semi-structured LLM Reasoners Can Be Rigorously AuditedLLM reasoning → Reasoning benchmarks and evaluation
  37. Benchmarking Foundation Models for Zero-Shot Biometric TasksMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  38. STORK: Faster Diffusion And Flow Matching Sampling By Resolving Both Stiffness And Structure-DependenceDiffusion models → Diffusion foundations and sampling
  39. Bootstrapping LLM Robustness for VLM Safety via Reducing the Pretraining Modality GapMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  40. On the Expressive Power of Mixture-of-Experts for Structured Complex TasksMixture-of-experts → MoE theory and gating functions
  41. SentinelAgent: Graph-based Anomaly Detection in Multi-Agent SystemsLLM agents and tool use → Agent threats, guardrails and governance +1
  42. Intuitionistic Fuzzy Sets for Large Language Model Data Annotation: A Novel Approach to Side-by-Side Preference LabelingLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  43. Learning API Functionality from In-Context Demonstrations for Tool-based AgentsLLM agents and tool use → Tool learning and function calling
  44. CLaSp: In-Context Layer Skip for Self-Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  45. Beyond Exponential Decay: Rethinking Error Accumulation in Large Language ModelsLLM reasoning → Test-time compute and efficient thinking
  46. QiMeng-CodeV-R1: Reasoning-Enhanced Verilog GenerationLLM reasoning → Reasoning for agents, planning and code
  47. Seeing is Not Reasoning: MVPBench for Graph-based Evaluation of Multi-path Visual Physical CoTLLM reasoning → Spatial and embodied reasoning +1
  48. SCOUT: Teaching Pre-trained Language Models to Enhance Reasoning via Flow Chain-of-ThoughtLLM reasoning → Prompting and chain-of-thought reasoning
  49. DrVD-Bench: Do Vision-Language Models Reason Like Human Doctors in Medical Image Diagnosis?LLM reasoning → Clinical and biomedical applications +1
  50. Tag-Evol: Achieving Efficient Instruction Evolving via Tag InjectionSynthetic data and self-improvement for LLMs → Code and instruction data synthesis
  51. Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language ModelsLLM reasoning → Multimodal reasoning +1
  52. Proxy Target: Bridging the Gap Between Discrete Spiking Neural Networks and Continuous ControlDeep reinforcement learning methods → Spiking and neuromorphic RL
  53. Threading Keyframe with Narratives: MLLMs as Strong Long Video ComprehendersMultimodal LLMs / vision-language models → Video understanding with MLLMs
  54. Towards a Generalizable Bimanual Foundation Policy via Flow-based Video PredictionVision-language-action models → Human-video and latent-action pretraining
  55. Biological Pathway Guided Gene Selection Through Collaborative Reinforcement LearningDeep reinforcement learning methods → RL for energy, networks and operations
  56. Autoregressive regularized score-based diffusion models for multi-scenarios fluid flow predictionDiffusion models → Flow matching, time series and science
  57. S4-Driver: Scalable Self-Supervised Driving Multimodal Large Language Modelwith Spatio-Temporal Visual RepresentationMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
  58. R-KV: Redundancy-aware KV Cache Compression for Reasoning ModelsLLM reasoning → Test-time compute and efficient thinking +1
  59. CSVQA: A Chinese Multimodal Benchmark for Evaluating STEM Reasoning Capabilities of VLMsLLM reasoning → Multimodal reasoning +1
  60. The State of Multilingual LLM Safety Research: From Measuring the Language Gap to Mitigating ItLLM safety and security → Safety alignment, refusal and guardrails
  61. Training LLMs for EHR-Based Reasoning Tasks via Reinforcement LearningLLM reasoning → Clinical and biomedical applications
  62. HardTests: Synthesizing High-Quality Test Cases for LLM CodingLLM reasoning → Reasoning for agents, planning and code
  63. Practical Bayes-Optimal Membership Inference AttacksLLM safety and security → Membership inference attacks
  64. Shadow defense against gradient inversion attack in federated learning
  65. Studying and Improving Graph Neural Network-based Motif Estimation
  66. Refined Causal Graph Structure Learning via Curvature for Brain Disease Classification
  67. Generalisation Bounds of Zero-Shot Economic Forecasting using Time Series Foundation Models
  68. Learn from the Past: Fast Sparse Indexing for Large Language Model Decoding
  69. Federated Incomplete Multi-view Clustering with Globally Fused Graph Guidance
  70. LittleBit: Ultra Low-Bit Quantization via Latent Factorization
  71. Towards Unified Neural Decoding with Brain Functional Network Modeling
  72. Recipes for Pre-training LLMs with MXFP8
  73. TIP-Search: Time-Predictable Inference Scheduling for Market Prediction under Uncertain Load
  74. The Hype Index: an NLP-driven Measure of Market News Attention
  75. Is BERTopic Better than PLSA for Extracting Key Topics in Aviation Safety Reports?
  76. Wine Quality Prediction with Ensemble Trees: A Unified, Leak-Free Comparative Study
  77. Evolutionary model for energy trading in community microgrids using Hawk-Dove strategies
  78. Mapping Human-Agent Co-Learning and Co-Adaptation: A Scoping Review
  79. An Independent Discriminant Network Towards Identification of Counterfeit Images and Videos
  80. State Estimation and Control of Dynamic Systems from High-Dimensional Image Data
  81. Multi-Analyte, Swab-based Automated Wound Monitor with AI
  82. Lightweight Convolutional Neural Networks for Retinal Disease Classification
  83. DLiPath: A Benchmark for the Comprehensive Assessment of Donor Liver Based on Histopathological Image Dataset
  84. Impact of Tuning Parameters in Deep Convolutional Neural Network Using a Crack Image Dataset
  85. Edge Computing for Physics-Driven AI in Computational MRI: A Feasibility Study
  86. Towards Secure MLOps: Surveying Attacks, Mitigation Strategies, and Research Challenges
  87. An evaluation of LLMs for generating movie reviews: GPT-4o, Gemini-2.0 and DeepSeek-V3
  88. Evaluation of LLMs for mathematical problem solving
  89. MythTriage: Scalable Detection of Opioid Use Disorder Myths on a Video-Sharing Platform
  90. Learning Aerodynamics for the Control of Flying Humanoid Robots
  91. Can LLMs Understand Unvoiced Speech? Exploring EMG-to-Text Conversion with LLMs
  92. Beyond Atomic Geometry Representations in Materials Science: A Human-in-the-Loop Multimodal Framework
  93. Improving Protein Sequence Design through Designability Preference Optimization
  94. Applying Vision Transformers on Spectral Analysis of Astronomical Objects
  95. Emergent Abilities of Large Language Models under Continued Pretraining for Language Adaptation
  96. 3D Gaussian Splat Vulnerabilities
  97. Sleep Brain and Cardiac Activity Predict Cognitive Flexibility and Conceptual Reasoning Using Deep Learning
  98. Hierarchical Level-Wise News Article Clustering via Multilingual Matryoshka Embeddings
  99. RoboMoRe: LLM-based Robot Co-design via Joint Optimization of Morphology and Reward
  100. SoundSculpt: Direction and Semantics Driven Ambisonic Target Sound Extraction
  101. Bayesian Data Sketching for Varying Coefficient Regression Models
  102. CASPER: A Large Scale Spontaneous Speech Dataset
  103. MultiHoax: A Dataset of Multi-hop False-Premise Questions
  104. PerFormer: A Permutation Based Vision Transformer for Remaining Useful Life Prediction
  105. The Impact of Disability Disclosure on Fairness and Bias in LLM-Driven Candidate Selection
  106. How hard is learning to cut? Trade-offs and sample complexity
  107. PersianMedQA: Evaluating Large Language Models on a Persian-English Bilingual Medical Question Answering Benchmark
  108. Performance Analysis of Convolutional Neural Network By Applying Unconstrained Binary Quadratic Programming
  109. Beyond Semantic Entropy: Boosting LLM Uncertainty Quantification with Pairwise Semantic Similarity
  110. DeGLIF for Label Noise Robust Node Classification using GNNs
  111. Whispers of Many Shores: Cultural Alignment through Collaborative Cultural Expertise
  112. Balancing Efficiency and Empathy: Healthcare Providers' Perspectives on AI-Supported Workflows for Serious Illness Conversations in the Emergency Department
  113. SmellNet: A Large-scale Dataset for Real-world Smell Recognition
  114. ZeShot-VQA: Zero-Shot Visual Question Answering Framework with Answer Mapping for Natural Disaster Damage Assessment
  115. Localized LoRA: A Structured Low-Rank Approximation for Efficient Fine-Tuning
  116. Ethical AI: Towards Defining a Collective Evaluation Framework
  117. Sorrel: A simple and flexible framework for multi-agent reinforcement learning
  118. Riemannian Principal Component Analysis
  119. Understanding while Exploring: Semantics-driven Active Mapping
  120. Enhancing Drug Discovery: Autoencoder-Based Latent Space Augmentation for Improved Molecular Solubility Prediction using LatMixSol
  121. Scaling Electronic Health Record Foundation Models for Population Health Management
  122. FastCAR: Fast Classification And Regression for Task Consolidation in Multi-Task Learning to Model a Continuous Property Variable of Detected Object Class
  123. Unlocking the Power of Rehearsal in Continual Learning: A Theoretical Perspective
  124. Structure-Aware Fill-in-the-Middle Pretraining for Code
  125. The World As Large Language Models See It: Exploring the reliability of LLMs in representing geographical features
  126. What do professional software developers need to know to succeed in an age of Artificial Intelligence?
  127. Structuring Radiology Reports: Challenging LLMs with Lightweight Models
  128. MOFGPT: Generative Design of Metal-Organic Frameworks using Language Models
  129. When GPT Spills the Tea: Comprehensive Assessment of Knowledge File Leakage in GPTs
  130. Heterogeneous Graph Backdoor Attack
  131. Cluster-Aware Causal Mixer for Online Anomaly Detection in Multivariate Time Series
  132. Pushing the Limits of Beam Search Decoding for Transducer-based ASR models
  133. Overfitting has a limitation: a model-independent generalization gap bound based on R'enyi entropy
  134. On the Interaction of Batch Noise, Adaptivity, and Compression, under (L0,L1)-Smoothness: An SDE Approach
  135. Empirical Validation of the Independent Chip Model
  136. Tournament of Prompts: Evolving LLM Instructions Through Structured Debates and Elo Ratings
  137. Who Gets Credit or Blame? Attributing Accountability in Modern AI Systems
  138. Constrained Bayesian Optimization under Bivariate Gaussian Process with Application to Cure Process Optimization
  139. Minimax Rates for the Estimation of Eigenpairs of Weighted Laplace-Beltrami Operators on Manifolds
  140. Utilizing AI for Aviation Post-Accident Analysis Classification
  141. SSRCA: a novel machine learning pipeline to perform sensitivity analysis for agent-based models
  142. Randomized Dimensionality Reduction for Euclidean Maximization and Diversity Measures
  143. Efficient Endangered Deer Species Monitoring with UAV Aerial Imagery and Deep Learning
  144. Privacy Amplification in Differentially Private Zeroth-Order Optimization with Hidden States
  145. Detection of Endangered Deer Species Using UAV Imagery: A Comparative Study Between Efficient Deep Learning Approaches
  146. Supporting architecture evaluation for ATAM scenarios with LLMs
  147. Vedavani: A Benchmark Corpus for ASR on Vedic Sanskrit Poetry
  148. Balancing Profit and Fairness in Risk-Based Pricing Markets
  149. LaMP-QA: A Benchmark for Personalized Long-form Question Answering
  150. Tradeoffs between Mistakes and ERM Oracle Calls in Online and Transductive Online Learning
  151. Spurious Correlations and Beyond: Understanding and Mitigating Shortcut Learning in SDOH Extraction with Large Language Models
  152. A Reinforcement Learning-Based Telematic Routing Protocol for the Internet of Underwater Things
  153. Geo-Sign: Hyperbolic Contrastive Regularisation for Geometrically Aware Sign Language Translation
  154. Applying Large Language Models to Issue Classification: Revisiting with Extended Data and New Models
  155. Generator Based Inference (GBI)
  156. Gated Multimodal Graph Learning for Personalized Recommendation
  157. Tensor Network for Anomaly Detection in the Latent Space of Proton Collision Events at the LHC
  158. EgoVIS@CVPR: What Changed and What Could Have Changed? State-Change Counterfactuals for Procedure-Aware Video Representation Learning
  159. Children's Voice Privacy: First Steps And Emerging Challenges
  160. PathGene: Benchmarking Driver Gene Mutations and Exon Prediction Using Multicenter Lung Cancer Histopathology Image Dataset
  161. ClinBench-HPB: A Clinical Benchmark for Evaluating LLMs in Hepato-Pancreato-Biliary Diseases
  162. Feeling Guilty Being a c(ai)borg: Navigating the Tensions Between Guilt and Empowerment in AI Use
  163. TRAPDOC: Deceiving LLM Users by Injecting Imperceptible Phantom Tokens into Documents
  164. HD-NDEs: Neural Differential Equations for Hallucination Detection in LLMs
  165. SwitchLingua: The First Large-Scale Multilingual and Multi-Ethnic Code-Switching Dataset
  166. COSMIC: Generalized Refusal Direction Identification in LLM Activations
  167. Hi-Dyna Graph: Hierarchical Dynamic Scene Graph for Robotic Autonomy in Human-Centric Environments
  168. Artificial Empathy: AI based Mental Health
  169. Bottom-Up Perspectives on AI Governance: Insights from User Reviews of AI Products
  170. AdaHuman: Animatable Detailed 3D Human Generation with Compositional Multiview Diffusion
  171. The Road to Generalizable Neuro-Symbolic Learning Should be Paved with Foundation Models
  172. GenSpace: Benchmarking Spatially-Aware Image Generation
  173. Consistent line clustering using geometric hypergraphs
  174. TalkingHeadBench: A Multi-Modal Benchmark & Analysis of Talking-Head DeepFake Detection
  175. ViStoryBench: Comprehensive Benchmark Suite for Story Visualization
  176. MetaFaith: Faithful Natural Language Uncertainty Expression in LLMs
  177. DexMachina: Functional Retargeting for Bimanual Dexterous Manipulation
  178. Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data
  179. Statistical mechanics of extensive-width Bayesian neural networks near interpolation
  180. Reading Recognition in the Wild
  181. Chameleon: A Flexible Data-mixing Framework for Language Model Pretraining and Finetuning
  182. From Invariant Representations to Invariant Data: Provable Robustness to Spurious Correlations via Noisy Counterfactual Matching
  183. Cascading Adversarial Bias from Injection to Distillation in Language Models
  184. The LLM Bottleneck: Why Open-Source Vision LLMs Struggle with Hierarchical Visual Recognition
  185. VideoCAD: A Dataset and Model for Learning Long-Horizon 3D CAD UI Interactions from Video
  186. Zero-Shot Chinese Character Recognition with Hierarchical Multi-Granularity Image-Text Aligning
  187. Timing is Important: Risk-aware Fund Allocation based on Time-Series Forecasting
  188. Multilinguality Does not Make Sense: Investigating Factors Behind Zero-Shot Transfer in Sense-Aware Tasks
  189. How much do language models memorize?
  190. LegalEval-Q: A New Benchmark for The Quality Evaluation of LLM-Generated Legal Text
  191. Segmenting France Across Four Centuries
  192. Bi-Manual Joint Camera Calibration and Scene Representation
  193. CL-LoRA: Continual Low-Rank Adaptation for Rehearsal-Free Class-Incremental Learning
  194. Guiding Generative Storytelling with Knowledge Graphs
  195. ByzFL: Research Framework for Robust Federated Learning
  196. Beyond Pretty Pictures: Combined Single- and Multi-Image Super-resolution for Sentinel-2 Images
  197. TC-GS: A Faster Gaussian Splatting Module Utilizing Tensor Cores
  198. Lightweight Relational Embedding in Task-Interpolated Few-Shot Networks for Enhanced Gastrointestinal Disease Classification
  199. Accelerating Inference of Discrete Autoregressive Normalizing Flows by Selective Jacobi Decoding
  200. Drop Dropout on Single-Epoch Language Model Pretraining
  201. DiG-Net: Enhancing Human-Robot Interaction through Hyper-Range Dynamic Gesture Recognition in Assistive Robotics
  202. EXP-Bench: Can AI Conduct AI Research Experiments?
  203. Efficient Estimation of Regularized Tyler's M-Estimator Using Approximate LOOCV
  204. QGAN-based data augmentation for hybrid quantum-classical neural networks
  205. Are Your Generated Instances Truly Useful? GenBench-MILP: A Benchmark Suite for MILP Instance Generation
  206. Revisiting Epistemic Markers in Confidence Estimation: Can Markers Accurately Reflect Large Language Models' Uncertainty?
  207. Diffusion-Based Symbolic Regression
  208. AFLoRA: Adaptive Federated Fine-Tuning of Large Language Models with Resource-Aware Low-Rank Adaption
  209. From Macro to Micro: Probing Dataset Diversity in Language Model Fine-Tuning
  210. A survey of using EHR as real-world evidence for discovering and validating new drug indications
  211. Supervised Quantum Machine Learning: A Future Outlook from Qubits to Enterprise Applications
  212. REASONING GYM: Reasoning Environments for Reinforcement Learning with Verifiable Rewards
  213. Unsupervised Evolutionary Cell Type Matching via Entropy-Minimized Optimal Transport
  214. LGAR: Zero-Shot LLM-Guided Neural Ranking for Abstract Screening in Systematic Literature Reviews
  215. Don't Reinvent the Wheel: Efficient Instruction-Following Text Embedding based on Guided Space Transformation
  216. SUMO: Subspace-Aware Moment-Orthogonalization for Accelerating Memory-Efficient LLM Training
  217. Tackling View-Dependent Semantics in 3D Language Gaussian Splatting
  218. Contrast-Invariant Self-supervised Segmentation for Quantitative Placental MRI
  219. Adapting to Linear Separable Subsets with Large-Margin in Differentially Private Learning
  220. "Dyadosyncrasy", Idiosyncrasy and Demographic Factors in Turn-Taking
  221. DreamDance: Animating Character Art via Inpainting Stable Gaussian Worlds
  222. Feature Attribution from First Principles
  223. Robust Federated Learning against Model Perturbation in Edge Networks
  224. Knockoff-Guided Compressive Sensing: A Statistical Machine Learning Framework for Support-Assured Signal Recovery
  225. HELM: Hyperbolic Large Language Models via Mixture-of-Curvature Experts
  226. Running Conventional Automatic Speech Recognition on Memristor Hardware: A Simulated Approach
  227. PDE-Transformer: Efficient and Versatile Transformers for Physics Simulations
  228. Towards Scalable Schema Mapping using Large Language Models
  229. CoRet: Improved Retriever for Code Editing
  230. Voice Conversion Improves Cross-Domain Robustness for Spoken Arabic Dialect Identification
  231. HESEIA: A community-based dataset for evaluating social biases in large language models, co-designed in real school settings in Latin America
  232. Causal-aware Large Language Models: Enhancing Decision-Making Through Learning, Adapting and Acting
  233. RT-X Net: RGB-Thermal cross attention network for Low-Light Image Enhancement
  234. K2IE: Kernel Method-based Kernel Intensity Estimators for Inhomogeneous Poisson Processes
  235. PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches
  236. Multi-Domain ABSA Conversation Dataset Generation via LLMs for Real-World Evaluation and Model Comparison
  237. Quick-Draw Bandits: Quickly Optimizing in Nonstationary Environments with Extremely Many Arms
  238. Learning reusable concepts across different egocentric video understanding tasks
  239. BPE Stays on SCRIPT: Structured Encoding for Robust Multilingual Pretokenization
  240. Disentangling Granularity: An Implicit Inductive Bias in Factorized VAEs
  241. Should I Share this Translation? Evaluating Quality Feedback for User Reliance on Machine Translation
  242. Generative Knowledge Production Pipeline Driven by Academic Influencers
  243. A Simple Linear Patch Revives Layer-Pruned Large Language Models
  244. Beyond FACS: Data-driven Facial Expression Dictionaries, with Application to Predicting Autism
  245. Predicting the Past: Estimating Historical Appraisals with OCR and Machine Learning
  246. 6D Pose Estimation on Point Cloud Data through Prior Knowledge Integration: A Case Study in Autonomous Disassembly
  247. Impact of Bottleneck Layers and Skip Connections on the Generalization of Linear Denoising Autoencoders
  248. Decoupled Competitive Framework for Semi-supervised Medical Image Segmentation
  249. Learning Geometry and Topology via Multi-Chart Flows
  250. Learning Distributions over Permutations and Rankings with Factorized Representations
  251. MSDA: Combining Pseudo-labeling and Self-Supervision for Unsupervised Domain Adaptation in ASR
  252. Adaptable Cardiovascular Disease Risk Prediction from Heterogeneous Data using Large Language Models
  253. Black-box Adversarial Attacks on CNN-based SLAM Algorithms
  254. PRISM: A Framework for Producing Interpretable Political Bias Embeddings with Political-Aware Cross-Encoder
  255. WILTing Trees: Interpreting the Distance Between MPNN Embeddings
  256. A Cross Branch Fusion-Based Contrastive Learning Framework for Point Cloud Self-supervised Learning
  257. Efficient Text Encoders for Labor Market Analysis
  258. Cloud Optical Thickness Retrievals Using Angle Invariant Attention Based Deep Learning Models
  259. Category-Level 6D Object Pose Estimation in Agricultural Settings Using a Lattice-Deformation Framework and Diffusion-Augmented Synthetic Data
  260. Disentangling Language and Culture for Evaluating Multilingual Large Language Models
  261. NUC-Net: Non-uniform Cylindrical Partition Network for Efficient LiDAR Semantic Segmentation
  262. Stop Guessing: Optimizing Goalkeeper Policies for Soccer Penalty Kicks
  263. Rethinking Neural Combinatorial Optimization for Vehicle Routing Problems with Different Constraint Tightness Degrees
  264. Hyperbolic Dataset Distillation
  265. Random Rule Forest (RRF): Interpretable and Manageable Ensembles of LLM-Generated Questions for Predicting Success from Unstructured Data
  266. Benchmarking Large Language Models for Cryptanalysis and Side-Channel Vulnerabilities
  267. Interpretable phenotyping of Heart Failure patients with Dutch discharge letters
  268. Eye of Judgement: Dissecting the Evaluation of Russian-speaking LLMs with POLLUX
  269. Harnessing Large Language Models for Scientific Novelty Detection
  270. When Harry Meets Superman: The Role of The Interlocutor in Persona-Based Dialogue Generation
  271. Multi-criteria Rank-based Aggregation for Explainable AI
  272. Explainable Depression Detection using Masked Hard Instance Mining
  273. GARLIC: GAussian Representation LearnIng for spaCe partitioning
  274. Model-Guided Network with Cluster-Based Operators for Spatio-Spectral Super-Resolution
  275. The Gaussian Mixing Mechanism: Renyi Differential Privacy via Gaussian Sketches
  276. Taxonomic Networks: A Representation for Neuro-Symbolic Pairing
  277. SARD: A Large-Scale Synthetic Arabic OCR Dataset for Book-Style Text Recognition
  278. BinConv: A Neural Architecture for Ordinal Encoding in Time-Series Forecasting
  279. A Flat Minima Perspective on Understanding Augmentations and Model Robustness
  280. Sample-optimal learning of quantum states using gentle measurements
  281. GATE: General Arabic Text Embedding for Enhanced Semantic Textual Similarity with Matryoshka Representation Learning and Hybrid Loss Training
  282. Adaptive Correction for Ensuring Conservation Laws in Neural Operators
  283. Neuro-Symbolic Operator for Interpretable and Generalizable Characterization of Complex Piezoelectric Systems
  284. Identifying Primary Stress Across Related Languages and Dialects with Transformer-based Speech Encoder Models
  285. Unleashing the Power of Intermediate Domains for Mixed Domain Semi-Supervised Medical Image Segmentation
  286. Improving Language and Modality Transfer in Translation by Character-level Modeling
  287. Optimal Weighted Convolution for Classification and Denosing
  288. Bench4KE: Benchmarking Automated Competency Question Generation
  289. Localizing Persona Representations in LLMs
  290. Don't Erase, Inform! Detecting and Contextualizing Harmful Language in Cultural Heritage Collections
  291. Beyond Linear Steering: Unified Multi-Attribute Control for Language Models
  292. HLSAD: Hodge Laplacian-based Simplicial Anomaly Detection
  293. Directional Non-Commutative Monoidal Structures with Interchange Law via Commutative Generators
  294. DeepQuestion: Systematic Generation of Real-World Challenges for Evaluating LLMs Performance
  295. Transformers Are Universally Consistent
  296. Geospatial Foundation Models to Enable Progress on Sustainable Development Goals
  297. Optimal Density Functions for Weighted Convolution in Learning Models
  298. Limited-Resource Adapters Are Regularizers, Not Linguists
  299. Stress-testing Machine Generated Text Detection: Shifting Language Models Writing Style to Fool Detectors
  300. un2CLIP: Improving CLIP's Visual Detail Capturing Ability via Inverting unCLIP
  301. Digital twins enable full-reference quality assessment of photoacoustic image reconstructions
  302. Airborne Neural Network
  303. Learning to Optimally Dispatch Power: Performance on a Nation-Wide Real-World Dataset
  304. Online Fair Division with Additional Information
  305. TimeHC-RL: Temporal-aware Hierarchical Cognitive Reinforcement Learning for Enhancing LLMs' Social Intelligence
  306. Efficient Neural and Numerical Methods for High-Quality Online Speech Spectrogram Inversion via Gradient Theorem
  307. MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge
  308. Object Centric Concept Bottlenecks
  309. Deformable Attention Mechanisms Applied to Object Detection, case of Remote Sensing
  310. Real-time Fall Prevention system for the Next-generation of Workers
  311. Rehearsal with Auxiliary-Informed Sampling for Audio Deepfake Detection
  312. Towards Effective Code-Integrated Reasoning
  313. Leveraging Knowledge Graphs and LLMs for Structured Generation of Misinformation
  314. Evaluating Gemini in an arena for learning
  315. SPPSFormer: High-quality Superpoint-based Transformer for Roof Plane Instance Segmentation from Point Clouds
  316. VietMix: A Naturally-Occurring Parallel Corpus and Augmentation Framework for Vietnamese-English Code-Mixed Machine Translation
  317. Smooth Model Compression without Fine-Tuning
  318. SA-Person: Text-Based Person Retrieval with Scene-aware Re-ranking
  319. Distributed gradient methods under heavy-tailed communication noise
  320. Logits-Based Finetuning
  321. CaMMT: Benchmarking Culturally Aware Multimodal Machine Translation
  322. Domain Pre-training Impact on Representations
  323. Stepsize anything: A unified learning rate schedule for budgeted-iteration training
  324. Exploring the Impact of Occupational Personas on Domain-Specific QA
  325. Diversify and Conquer: Open-set Disagreement for Robust Semi-supervised Learning with Outliers
  326. SORCE: Small Object Retrieval in Complex Environments
  327. Weisfeiler and Leman Follow the Arrow of Time: Expressive Power of Message Passing in Temporal Event Graphs
  328. Bridging 3D Anomaly Localization and Repair via High-Quality Continuous Geometric Representation
  329. Deep Learning Weather Models for Subregional Ocean Forecasting: A Case Study on the Canary Current Upwelling System
  330. Donate or Create? Comparing Data Collection Strategies for Emotion-labeled Multimodal Social Media Posts
  331. P: A Universal Measure of Predictive Intelligence
  332. Three Kinds of Negation in Knowledge and Their Mathematical Foundations
  333. pyMEAL: A Multi-Encoder Augmentation-Aware-Learning Toolbox for Robust Medical Image Translation
  334. Boosting Automatic Exercise Evaluation Through Musculoskeletal Simulation-Based IMU Data Augmentation
  335. Multi-task Learning for Heterogeneous Multi-source Block-Wise Missing Data
  336. PCIE_Pose Solution for EgoExo4D Pose and Proficiency Estimation Challenge
  337. Efficient RAW Image Deblurring with Adaptive Frequency Modulation
  338. PCIE_Interaction Solution for Ego4D Social Interaction Challenge
  339. On the Lipschitz Continuity of Set Aggregation Functions and Neural Networks for Sets
  340. Leveraging Intermediate Features of Vision Transformer for Face Anti-Spoofing
  341. S3CE-Net: Spike-guided Spatiotemporal Semantic Coupling and Expansion Network for Long Sequence Event Re-Identification
  342. LightSAM: Parameter-Agnostic Sharpness-Aware Minimization
  343. Leadership Assessment in Pediatric Intensive Care Unit Team Training
  344. Neural Drift Estimation for Ergodic Diffusions: Non-parametric Analysis and Numerical Exploration
  345. SASP: Strip-Aware Spatial Perception for Fine-Grained Bird Image Classification
  346. Spatiotemporal Analysis of Forest Machine Operations Using 3D Video Classification
  347. Beyond Quantity: Distribution-Aware Labeling for Visual Grounding
  348. Grid-LOGAT: Grid Based Local and Global Area Transcription for Video Question Answering
  349. Anomaly Detection and Improvement of Clusters using Enhanced K-Means Algorithm
  350. Multilingual Gloss-free Sign Language Translation: Towards Building a Sign Language Foundation Model
  351. Cartan Networks: Group theoretical Hyperbolic Deep Learning
  352. A Novel Coronary Artery Registration Method Based on Super-pixel Particle Swarm Optimization
  353. Fewer Hallucinations, More Verification: A Three-Stage LLM-Based Framework for ASR Error Correction
  354. VUDG: A Dataset for Video Understanding Domain Generalization
  355. VAEER: Visual Attention-Inspired Emotion Elicitation Reasoning
  356. Exploring Multimodal Challenges in Toxic Chinese Detection: Taxonomy, Benchmark, and Findings
  357. GeoVision Labeler: Zero-Shot Geospatial Classification with Vision and Language Models
  358. When Humans Growl and Birds Speak: High-Fidelity Voice Conversion from Human to Animal and Designed Sounds
  359. KairosAD: A SAM-Based Model for Industrial Anomaly Detection on Embedded Devices
  360. Two failure modes of deep transformers and how to avoid them: a unified theory of signal propagation at initialisation
  361. Context-Aware Sentiment Forecasting via LLM-based Multi-Perspective Role-Playing Agents
  362. DisTime: Distribution-based Time Representation for Video Large Language Models
  363. STAR-Net: An Interpretable Model-Aided Network for Remote Sensing Image Denoising
  364. SwiftEval: Developing a Language-Specific Benchmark for LLM-generated Code Evaluation
  365. HiCaM: A Hierarchical-Causal Modification Framework for Long-Form Text Modification
  366. InteractAnything: Zero-shot Human Object Interaction Synthesis via LLM Feedback and Object Affordance Parsing
  367. Weak-to-Strong Generalization via Bregman Bias-Variance Decomposition
  368. Equilibrium Distribution for t-Distributed Stochastic Neighbor Embedding with Generalized Kernels
  369. GridRoute: A Benchmark for LLM-Based Route Planning with Cardinal Movement in Grid Environments
  370. SR3D: Unleashing Single-view 3D Reconstruction for Transparent and Specular Object Grasping
  371. ScienceMeter: Tracking Scientific Knowledge Updates in Language Models
  372. Category-aware EEG image generation based on wavelet transform and contrast semantic loss
  373. Data Fusion for Partial Identification of Causal Effects
  374. Equivalent Linear Mappings of Large Language Models
  375. Mind the Quote: Enabling Quotation-Aware Dialogue in LLMs via Plug-and-Play Modules
  376. Discl-VC: Disentangled Discrete Tokens and In-Context Learning for Controllable Zero-Shot Voice Conversion
  377. EgoExOR: An Ego-Exo-Centric Operating Room Dataset for Surgical Activity Understanding
  378. LLM-powered Query Expansion for Enhancing Boundary Prediction in Language-driven Action Localization
  379. Multi-Task Learning with Covariate-Overlap Regularization
  380. GradPower: Powering Gradients for Faster Language Model Pre-Training
  381. INSIGHT: A Survey of In-Network Systems for Intelligent, High-Efficiency AI and Topology Optimization
  382. Faithful and Robust LLM-Driven Theorem Proving for NLI Explanations
  383. Simulating Training Data Leakage in Multiple-Choice Benchmarks for LLM Evaluation
  384. On Fairness of Task Arithmetic: The Role of Task Vectors
  385. Taming Hyperparameter Sensitivity in Data Attribution: Practical Selection Without Costly Retraining
  386. FABLE: A Novel Data-Flow Analysis Benchmark on Procedural Text for Large Language Model Evaluation
  387. Rethinking Continual Learning with Progressive Neural Collapse
  388. Proactive Guidance of Multi-Turn Conversation in Industrial Search
  389. Harnessing Foundation Models for Robust and Generalizable 6-DOF Bronchoscopy Localization
  390. 50 Years of Automated Face Recognition
  391. LTM3D: Bridging Token Spaces for Conditional 3D Generation with Auto-Regressive Diffusion Framework
  392. Model-Informed Flows for Bayesian Inference
  393. Advantageous Parameter Expansion Training Makes Better Large Language Models
  394. Alternate Groundwater Modelling Strategies: A Multi-Faceted Data-Driven Approach
  395. Dynamic Malware Classification of Windows PE Files using CNNs and Greyscale Images Derived from Runtime API Call Argument Conversion
  396. ProofNet++: A Neuro-Symbolic System for Formal Proof Verification with Self-Correction
  397. Dynamic Context-Aware Streaming Pretrained Language Model For Inverse Text Normalization
  398. Automated Structured Radiology Report Generation
  399. ERU-KG: Efficient Reference-aligned Unsupervised Keyphrase Generation
  400. Shuffle PatchMix Augmentation with Confidence-Margin Weighted Pseudo-Labels for Enhanced Source-Free Domain Adaptation
  401. Are Any-to-Any Models More Consistent Across Modality Transfers Than Specialists?
  402. Boosting All-in-One Image Restoration via Self-Improved Privilege Learning
  403. Aligning Protein Conformation Ensemble Generation with Physical Feedback
  404. Improving Multilingual Speech Models on ML-SUPERB 2.0: Fine-tuning with Data Augmentation and LID-Aware CTC
  405. WikiGap: Promoting Epistemic Equity by Surfacing Knowledge Gaps Between English Wikipedia and other Language Editions
  406. Improved Best-of-Both-Worlds Regret for Bandits with Delayed Feedback
  407. Provably Improving Generalization of Few-Shot Models with Synthetic Data
  408. Fine-Tune an SLM or Prompt an LLM? The Case of Generating Low-Code Workflows
  409. Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling
  410. SALE : Low-bit Estimation for Efficient Sparse Attention in Long-context LLM Prefilling
  411. Invariant Link Selector for Spatial-Temporal Out-of-Distribution Problem
  412. Adaptive LoRA Merge with Parameter Pruning for Low-Resource Generation
  413. Pretraining Deformable Image Registration Networks with Random Images
  414. LKD-KGC: Domain-Specific KG Construction via LLM-driven Knowledge Dependency Parsing
  415. Training-free zero-shot 3D symmetry detection with visual features back-projected to geometry
  416. Beyond the LUMIR challenge: The pathway to foundational registration models
  417. Experience-based Knowledge Correction for Robust Planning in Minecraft
  418. RCCDA: Adaptive Model Updates in the Presence of Concept Drift under a Constrained Resource Budget
  419. Rationales Are Not Silver Bullets: Measuring the Impact of Rationales on Model Performance and Reliability
  420. CrossICL: Cross-Task In-Context Learning via Unsupervised Demonstration Transfer
  421. The Butterfly Effect in Pathology: Exploring Security in Pathology Foundation Models
  422. AMSbench: A Comprehensive Benchmark for Evaluating MLLM Capabilities in AMS Circuits
  423. Sparsity-Driven Parallel Imaging Consistency for Improved Self-Supervised MRI Reconstruction
  424. A Mathematical Perspective On Contrastive Learning
  425. Information-theoretic machine learning for time-varying mode decomposition of separated aerodynamic flows
  426. Bounds on the Excess Minimum Risk via Generalized Information Divergence Measures
  427. A Constructive Framework for Nondeterministic Automata via Time-Shared, Depth-Unrolled Feedforward Networks
  428. Federated Foundation Model for GI Endoscopy Images
  429. Weakly-Supervised Affordance Grounding Guided by Part-Level Semantic Priors
  430. A SHAP-based explainable multi-level stacking ensemble learning method for predicting the length of stay in acute stroke
  431. Attractor learning for spatiotemporally chaotic dynamical systems using echo state networks with transfer learning
  432. Performative Risk Control: Calibrating Models for Reliable Deployment under Performativity
  433. Searching Clinical Data Using Generative AI
  434. Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting
  435. ComposeAnything: Composite Object Priors for Text-to-Image Generation
  436. DeepBoost-AF: A Novel Unsupervised Feature Learning and Gradient Boosting Fusion for Robust Atrial Fibrillation Detection in Raw ECG Signals