mlsanityData to 14 Oct 2026

Papers

New on arXiv

Mon 19 May 2025

552 papers

  1. Sandwich: Joint Configuration Search and Hot-Switching for Efficient CPU LLM ServingEfficient LLM inference and serving → Serving systems and request scheduling
  2. Modular Diffusion Policy Training: Decoupling and Recombining Guidance and Diffusion for Offline RLDiffusion models → Diffusion and flow policies for robotics +1
  3. Generating Realistic Multi-Beat ECG SignalsDiffusion models → Medical imaging and segmentation
  4. Safety Alignment Can Be Not Superficial With Explicit Safety SignalsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  5. CoIn: Counting the Invisible Reasoning Tokens in Commercial Opaque LLM APIsLLM reasoning → Test-time compute and efficient thinking
  6. Beyond Semantics: The Unreasonable Effectiveness of Reasonless Intermediate TokensLLM reasoning → Prompting and chain-of-thought reasoning
  7. Measuring the Faithfulness of Thinking Drafts in Large Reasoning ModelsLLM reasoning → Test-time compute and efficient thinking
  8. Simulation Agent: A Framework for Integrating Simulation and Large Language Models for Enhanced Decision-MakingLLM agents and tool use → General LLM agent frameworks and benchmarks
  9. Improving Compositional Generation with Diffusion Models Using Lift ScoresDiffusion models → Diffusion foundations and sampling
  10. Benchmarking MOEAs for solving continuous multi-objective RL problemsDeep reinforcement learning methods → RL for games and combinatorial optimization
  11. SQLForge: Synthesizing Reliable and Diverse Data to Enhance Text-to-SQL Reasoning in LLMsLLM reasoning → Knowledge- and tool-augmented reasoning
  12. Warm Up Before You Train: Unlocking General Reasoning in Resource-Constrained SettingsLLM reasoning → Reinforcement learning for reasoning
  13. Policy-Driven World Model Adaptation for Robust Offline Model-based Reinforcement LearningWorld models → Latent dynamics models and model-based RL +1
  14. RL in Name Only? Analyzing the Structural Assumptions in RL post-training for LLMsLLM reasoning → Reinforcement learning for reasoning
  15. Building spatial world models from sparse transitional episodic memoriesWorld models → World models for navigation
  16. A*-Decoding: Token-Efficient Inference ScalingLLM reasoning → Test-time compute and efficient thinking
  17. Guided Search Strategies in Non-Serializable Environments with Applications to Software Engineering AgentsLLM reasoning → Reasoning for agents, planning and code +1
  18. 4Hammer: a board-game reinforcement learning environment for the hour long time frameDeep reinforcement learning methods → RL for games and combinatorial optimization
  19. RAR: Setting Knowledge Tripwires for Retrieval Augmented RejectionRetrieval-augmented generation → Privacy and security of RAG
  20. Language and Thought: The View from LLMsLLM reasoning → Reasoning benchmarks and evaluation
  21. AMAQA: A Metadata-based QA Dataset for RAG SystemsRetrieval-augmented generation → RAG robustness and adaptive retrieval
  22. Multi-head Temporal Latent AttentionEfficient LLM inference and serving → KV cache optimization
  23. CIE: Controlling Language Model Text Generations Using Continuous SignalsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  24. ChartMuseum: Testing Visual Reasoning Capabilities of Large Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
  25. Optimizing Anytime Reasoning via Budget Relative Policy OptimizationLLM reasoning → Test-time compute and efficient thinking
  26. KinTwin: Imitation Learning with Torque and Muscle Driven Biomechanical Models Enables Precise Replication of Able-Bodied and Impaired Movement from Markerless Motion CaptureOffline RL and imitation learning from data → Real-world robot offline RL
  27. A Practical Guide for Incorporating Symmetry in Diffusion PolicyDiffusion models → Diffusion and flow policies for robotics
  28. MM-PRM: Enhancing Multimodal Mathematical Reasoning with Scalable Step-Level SupervisionLLM reasoning → Multimodal reasoning +1
  29. G1: Bootstrapping Perception and Reasoning Abilities of Vision-Language Model via Reinforcement LearningLLM reasoning → Multimodal reasoning +2
  30. Make Still Further Progress: Chain of Thoughts for Tabular Data LeaderboardLLM reasoning → Knowledge- and tool-augmented reasoning
  31. FEALLM: Advancing Facial Emotion Analysis in Multimodal Large Language Models with Emotional Synergy and ReasoningLLM reasoning → Audio-language model reasoning +1
  32. AdaptThink: Reasoning Models Can Learn When to ThinkLLM reasoning → Test-time compute and efficient thinking
  33. Joint Velocity-Growth Flow Matching for Single-Cell Dynamics ModelingDiffusion models → Flow matching, time series and science
  34. CoT-Kinetics: A Theoretical Modeling Assessing LRM Reasoning ProcessLLM reasoning → Prompting and chain-of-thought reasoning
  35. A Dataless Reinforcement Learning Approach to Rounding Hyperplane Optimization for Max-CutDeep reinforcement learning methods → RL theory and sample complexity
  36. MR. Judge: Multimodal Reasoner as a JudgeLLM reasoning → Multimodal reasoning +2
  37. Advancing Generalization Across a Variety of Abstract Visual Reasoning TasksLLM reasoning → Multimodal reasoning
  38. VSA: Faster Video Diffusion with Trainable Sparse AttentionDiffusion models → Video generation
  39. R3: Robust Rubric-Agnostic Reward ModelsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  40. CompeteSMoE -- Statistically Guaranteed Mixture of Experts Training via CompetitionMixture-of-experts → Expert routing strategies
  41. Thinkless: LLM Learns When to ThinkLLM reasoning → Test-time compute and efficient thinking
  42. Minimum-Excess-Work GuidanceDiffusion models → Flow matching, time series and science
  43. Exploiting Symbolic Heuristics for the Synthesis of Domain-Specific Temporal Planning Guidance using Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  44. Dynamic Probabilistic Noise Injection for Membership Inference DefenseLLM safety and security → Membership inference attacks
  45. One-Step Offline Distillation of Diffusion-based Models via Koopman ModelingDiffusion models → Diffusion foundations and sampling
  46. J4R: Learning to Judge with Equivalent Initial State Group Relative Policy OptimizationLLM reasoning → Reinforcement learning for reasoning
  47. Occult: Optimizing Collaborative Communication across Experts for Accelerated Parallel MoE Training and InferenceMixture-of-experts → Efficient MoE training and inference systems
  48. RoPECraft: Training-Free Motion Transfer with Trajectory-Guided RoPE Optimization on Diffusion TransformersDiffusion models → Video generation
  49. Rethinking Stateful Tool Use in Multi-Turn Dialogues: Benchmarks and ChallengesLLM reasoning → Reasoning for agents, planning and code +1
  50. Thinking Short and Right Over Thinking Long: Serving LLM Reasoning Efficiently and AccuratelyLLM reasoning → Test-time compute and efficient thinking
  51. Unlabeled Data vs. Pre-trained Knowledge: Rethinking SSL in the Era of Large ModelsLLM reasoning → Multimodal reasoning
  52. Denoising Diffusion Probabilistic Model for Point Cloud Compression at Low Bit-RatesDiffusion models → 3D, point cloud and scene generation
  53. GUARD: Generation-time LLM Unlearning via Adaptive Restriction and DetectionLLM safety and security → Machine unlearning
  54. Seek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient in Latent SpaceLLM reasoning → Test-time compute and efficient thinking
  55. RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought ReasoningLLM reasoning → Prompting and chain-of-thought reasoning
  56. Images Amplify Misinformation Sharing in Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  57. TimeSeriesGym: A Scalable Benchmark for (Time Series) Machine Learning Engineering AgentsLLM agents and tool use → Financial trading and forecasting agents
  58. Computer Vision Models Show Human-Like Sensitivity to Geometric and Topological ConceptsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  59. FlowPure: Continuous Normalizing Flows for Adversarial PurificationDiffusion models → Robustness, privacy and adversarial aspects
  60. EMoE: Training-Free Expert Disagreement for Uncertainty-Aware Text-to-Image DiffusionDiffusion models → Image generation, text-to-image and editing +1
  61. CSC-SQL: Corrective Self-Consistency in Text-to-SQL via Reinforcement LearningLLM reasoning → Knowledge- and tool-augmented reasoning +1
  62. Unlocking the Potential of Difficulty Prior in RL-based Multimodal ReasoningLLM reasoning → Multimodal reasoning
  63. Towards Transparent RAG: Fostering Evidence Traceability in LLM Generation via Reinforcement LearningRetrieval-augmented generation → Agentic RAG, agents and memory
  64. Is Active Persona Inference Necessary for Aligning Small Models to Personal Preferences?LLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  65. Policy Contrastive Decoding for Robotic Foundation ModelsVision-language-action models → Reinforcement learning and post-training
  66. HeteroSpec: Leveraging Contextual Heterogeneity for Efficient Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  67. Composing Dextrous Grasping and In-hand Manipulation via Scoring with a Reinforcement Learning CriticDeep reinforcement learning methods → RL for robot locomotion and manipulation
  68. A Reality Check of Language Models as Formalizers on Constraint Satisfaction ProblemsLLM reasoning → Reasoning benchmarks and evaluation
  69. Agentic publications: redesigning scientific publishing in the age of thinking large language modelsLLM reasoning → Knowledge- and tool-augmented reasoning +1
  70. SAKURA: On the Multi-hop Reasoning of Large Audio-Language Models Based on Speech and Audio InformationLLM reasoning → Audio-language model reasoning
  71. From Local Details to Global Context: Advancing Vision-Language Models with Attention-Based SelectionMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  72. Scaling Computer-Use Grounding via User Interface Decomposition and SynthesisLLM agents and tool use → GUI and mobile agents
  73. PiT: Progressive Diffusion TransformerDiffusion models → Diffusion foundations and sampling
  74. Diffusion Models with Double Guidance: Generate with aggregated datasetsDiffusion models → Diffusion foundations and sampling
  75. MAGI-1: Autoregressive Video Generation at ScaleWorld models → Video-generation world models and simulators
  76. Alignment-Augmented Speculative Decoding with Alignment Sampling and Conditional VerificationEfficient LLM inference and serving → Speculative decoding
  77. A Malliavin-Gamma calculus approach to Score Based Diffusion Generative models for random fieldsDiffusion models → Diffusion foundations and sampling
  78. When a Reinforcement Learning Agent Encounters Unknown UnknownsDeep reinforcement learning methods → RL theory and sample complexity
  79. ViPlan: A Benchmark for Visual Planning with Symbolic Predicates and Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  80. Higher fidelity perceptual image and video compression with a latent conditioned residual denoising diffusion modelDiffusion models → Diffusion for compression and wireless
  81. Temporal Distance-aware Transition Augmentation for Offline Model-based Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
  82. Auditing Meta-Cognitive Hallucinations in Reasoning Large Language ModelsLLM reasoning → Hallucination detection and mitigation
  83. Neurosymbolic Diffusion ModelsLLM reasoning → Reasoning benchmarks and evaluation +1
  84. Constraint-Aware Diffusion Guidance for Robotics: Real-Time Obstacle Avoidance for Autonomous RacingDiffusion models → Diffusion and flow policies for robotics
  85. Optimizing Retrieval Augmented Generation for Object Constraint LanguageRetrieval-augmented generation → RAG pipeline design and evaluation
  86. Benchmarking and Confidence Evaluation of LALMs For Temporal ReasoningLLM reasoning → Audio-language model reasoning
  87. Why Knowledge Distillation Works in Generative Models: A Minimal Working ExplanationKnowledge distillation → Knowledge distillation for LLMs
  88. FreeKV: Boosting KV Cache Retrieval for Efficient LLM InferenceEfficient LLM inference and serving → KV cache optimization
  89. Touch2Shape: Touch-Conditioned 3D Diffusion for Shape Exploration and ReconstructionDiffusion models → Diffusion and flow policies for robotics
  90. Walking the Tightrope: Disentangling Beneficial and Detrimental Drifts in Non-Stationary Custom-TuningLLM reasoning → Reinforcement learning for reasoning +1
  91. The Hidden Dangers of Browsing AI AgentsLLM agents and tool use → Agent threats, guardrails and governance
  92. Hearing from Silence: Reasoning Audio Descriptions from Silent Videos via Vision-Language ModelMultimodal LLMs / vision-language models → Video understanding with MLLMs
  93. Model Selection for Gaussian-gated Gaussian Mixture of Experts Using Dendrograms of Mixing MeasuresMixture-of-experts → MoE theory and gating functions
  94. CAIM: Development and Evaluation of a Cognitive AI Memory Framework for Long-Term Interaction with Intelligent AgentsLLM agents and tool use → Agent memory systems
  95. MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their MixLLM reasoning → Audio-language model reasoning
  96. MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPOLLM reasoning → Multimodal reasoning +1
  97. Evaluating the efficacy of LLM Safety Solutions : The Palit Benchmark DatasetLLM safety and security → Prompt injection and agent security
  98. Step-wise Adaptive Integration of Supervised Fine-tuning and Reinforcement Learning for Task-Specific LLMsLLM reasoning → Reinforcement learning for reasoning
  99. Adversarial Reasoning for Repair Based on Inferred Program IntentLLM reasoning → Reasoning for agents, planning and code
  100. Evaluating the Performance of RAG Methods for Conversational AI in the Airport DomainRetrieval-augmented generation → Conversational and speech RAG
All 552
  1. ExTrans: Multilingual Deep Reasoning Translation via Exemplar-Enhanced Reinforcement LearningLLM reasoning → Reasoning benchmarks and evaluation +1
  2. Fractured Chain-of-Thought ReasoningLLM reasoning → Prompting and chain-of-thought reasoning
  3. Multi-parameter Control for the (1+(λ,λ))-GA on OneMax via Deep Reinforcement LearningDeep reinforcement learning methods → RL for games and combinatorial optimization
  4. From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance
  5. A Non-Interventionist Approach to Causal Reasoning based on Lewisian CounterfactualsLLM reasoning → Causal reasoning in LLMs
  6. DGRO: Enhancing LLM Reasoning via Exploration-Exploitation Control and Reward Variance ManagementLLM reasoning → Reinforcement learning for reasoning
  7. A3 : an Analytical Low-Rank Approximation Framework for AttentionEfficient LLM inference and serving → KV cache optimization
  8. LatentINDIGO: An INN-Guided Latent Diffusion Algorithm for Image RestorationDiffusion models → Inverse problems and image restoration
  9. Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMsLLM reasoning → Reinforcement learning for reasoning
  10. The Traitors: Deception and Trust in Multi-Agent Language Model SimulationsLLM agents and tool use → Social simulation and multi-agent debate
  11. Uniformity First: Uniformity-aware Test-time Adaptation of Vision-language Models against Image CorruptionMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  12. Power Allocation for Delay Optimization in Device-to-Device Networks: A Graph Reinforcement Learning ApproachDeep reinforcement learning methods → RL for energy, networks and operations
  13. On the Thinking-Language Modeling Gap in Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  14. TIME: A Multi-level Benchmark for Temporal Reasoning of LLMs in Real-World ScenariosLLM reasoning → Knowledge- and tool-augmented reasoning
  15. Detection and Mitigation of Hallucination in Large Reasoning Models: A Mechanistic PerspectiveLLM reasoning → Hallucination detection and mitigation
  16. TinyAlign: Boosting Lightweight Vision-Language Models by Mitigating Modal Alignment BottlenecksMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  17. PhyDA: Physics-Guided Diffusion Models for Data Assimilation in Atmospheric SystemsDiffusion models → Flow matching, time series and science
  18. Does Low Rank Adaptation Lead to Lower Robustness against Training-Time Attacks?LLM safety and security → Backdoor and data poisoning attacks
  19. LEXam: Benchmarking Legal Reasoning on 340 Law ExamsLLM reasoning → Reasoning for agents, planning and code
  20. RMMSS: Towards Advanced Robust Multi-Modal Semantic Segmentation with Hybrid Prototype Distillation and Feature SelectionKnowledge distillation → Detection and dense prediction distillation
  21. Multi-Level Aware Preference Learning: Enhancing RLHF for Complex Multi-Instruction TasksLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  22. Bias Fitting to Mitigate Length Bias of Reward Model in RLHFLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  23. GEM: Gaussian Embedding Modeling for Out-of-Distribution Detection in GUI AgentsLLM agents and tool use → GUI and mobile agents
  24. FlightGPT: Towards Generalizable and Interpretable UAV Vision-and-Language Navigation with Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  25. Reasoning BO: Enhancing Bayesian Optimization with Long-Context Reasoning Power of LLMsLLM reasoning → Test-time compute and efficient thinking
  26. Mitigating Hallucination in VideoLLMs via Temporal-Aware Activation EngineeringMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  27. OZSpeech: One-step Zero-shot Speech Synthesis with Learned-Prior-Conditioned Flow MatchingDiffusion models → Audio, speech and music
  28. FRABench and UFEval: Unified Fine-grained Evaluation with Task and Aspect GeneralizationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  29. Mixture Policy based Multi-Hop Reasoning over N-tuple Temporal Knowledge GraphsLLM reasoning → Knowledge- and tool-augmented reasoning
  30. AdaToken-3D: Dynamic Spatial Gating for Efficient 3D Large Multimodal-Models ReasoningMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  31. A Token is Worth over 1,000 Tokens: Efficient Knowledge Distillation through Low-Rank CloneKnowledge distillation → Knowledge distillation for LLMs
  32. ReEx-SQL: Reasoning with Execution-Aware Reinforcement Learning for Text-to-SQLLLM reasoning → Knowledge- and tool-augmented reasoning
  33. Reasoning-OCR: Can Large Multimodal Models Solve Complex Logical Reasoning Problems from OCR Cues?LLM reasoning → Multimodal reasoning +1
  34. Rethinking Reward Model Evaluation Through the Lens of Reward OveroptimizationLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  35. IDEAL: Data Equilibrium Adaptation for Multi-Capability Language Model AlignmentLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  36. Correspondence of high-dimensional emotion structures elicited by video clips between humans and Multimodal LLMsMultimodal LLMs / vision-language models → Multimodal emotion understanding
  37. Incentivizing Multimodal Reasoning in Large Models for Direct Robot ManipulationLLM reasoning → Spatial and embodied reasoning +1
  38. Language Model Networks: Supervision-Efficient Learning through Dense CommunicationLLM reasoning → Test-time compute and efficient thinking
  39. Option-aware Temporally Abstracted Value for Offline Goal-Conditioned Reinforcement LearningOffline RL and imitation learning from data → Diffusion and flow policies for offline RL
  40. Accelerating Adaptive Retrieval Augmented Generation via Instruction-Driven Representation Reduction of Retrieval OverlapsRetrieval-augmented generation → RAG pipeline design and evaluation
  41. SpecFLASH: A Latent-Guided Semi-autoregressive Speculative Decoding Framework for Efficient Multimodal GenerationMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  42. On-Policy Optimization with Group Equivalent Preference for Multi-Programming Language UnderstandingLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  43. ToTRL: Unlock LLM Tree-of-Thoughts Reasoning Potential through Puzzles SolvingLLM reasoning → Test-time compute and efficient thinking
  44. DreamGen: Unlocking Generalization in Robot Learning through Video World ModelsWorld models → Embodied and robot world models
  45. Counterfactual Explanations for Continuous Action Reinforcement LearningDeep reinforcement learning methods → Interpretable and logic-guided RL
  46. Towards A Generalist Code Embedding Model Based On Massive Data SynthesisRetrieval-augmented generation → RAG for code
  47. Mamba-Adaptor: State Space Model Adaptor for Visual RecognitionState-space sequence models (S4, Mamba) → Vision Mamba backbones
  48. Ineq-Comp: Benchmarking Human-Intuitive Compositional Reasoning in Automated Theorem Proving on InequalitiesLLM reasoning → Mathematical reasoning
  49. CURE: Concept Unlearning via Orthogonal Representation Editing in Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
  50. Few-Step Diffusion via Score identity DistillationDiffusion models → Diffusion foundations and sampling
  51. TS-VLM: Text-Guided SoftSort Pooling for Vision-Language Models in Multi-View Driving ReasoningLLM reasoning → Chain-of-thought reasoning for driving +2
  52. Safe-Sora: Safe Text-to-Video Generation via Graphical WatermarkingLLM safety and security → Watermarking generated content and models
  53. Know3-RAG: A Knowledge-aware RAG Framework with Adaptive Retrieval, Generation, and FilteringRetrieval-augmented generation → RAG pipeline design and evaluation
  54. SafeMove-RL: A Certifiable Reinforcement Learning Framework for Dynamic Motion Constraints in Trajectory PlanningDeep reinforcement learning methods → Safe and constrained RL
  55. Scalable Video-to-Dataset Generation for Cross-Platform Mobile AgentsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  56. Dual-Agent Reinforcement Learning for Automated Feature GenerationDeep reinforcement learning methods → RL with diffusion and flow models
  57. R1dacted: Investigating Local Censorship in DeepSeek's R1 Language ModelLLM reasoning → Reasoning benchmarks and evaluation
  58. Adaptive Graph UnlearningLLM safety and security → Graph unlearning
  59. Action-Dependent Optimality-Preserving Reward ShapingDeep reinforcement learning methods → Deep RL algorithms and representations
  60. Temporal-Oriented Recipe for Transferring Large Vision-Language Model to Video UnderstandingMultimodal LLMs / vision-language models → Video understanding with MLLMs
  61. Rethinking Predictive Modeling for LLM Routing: When Simple kNN Beats Complex Learned RoutersLLM reasoning → Test-time compute and efficient thinking
  62. AD-AGENT: A Multi-agent Framework for End-to-end Anomaly DetectionLLM agents and tool use → Agent threats, guardrails and governance
  63. Counting with Confidence: Accurate Pest Monitoring in Water Traps
  64. Non-planar Object Detection and Identification by Features Matching and Triangulation Growth
  65. Security Degradation in Iterative AI Code Generation -- A Systematic Analysis of the Paradox
  66. Bi-level Unbalanced Optimal Transport for Partial Domain Adaptation
  67. Gridding Forced Displacement using Semi-Supervised Learning
  68. Large Language Models and Their Applications in Roadway Safety and Mobility Enhancement: A Comprehensive Review
  69. LT-PINN: Lagrangian Topology-conscious Physics-informed Neural Network for Boundary-focused Engineering Optimization
  70. Re-experiment Smart: a Novel Method to Enhance Data-driven Prediction of Mechanical Properties of Epoxy Polymers
  71. Complexity counts: global and local perspectives on Indo-Aryan numeral systems
  72. Multi-Modal Artificial Intelligence of Embryo Grading and Pregnancy Prediction in Assisted Reproductive Technology: A Review
  73. Quantifying the Generalization Gap in Seizure Detection: A Large-Scale Empirical Benchmark via the SzCORE Challenge
  74. PhySense: Sensor Placement Optimization for Accurate Physics Sensing
  75. Improving Generative Inverse Design of Rectangular Patch Antennas with Test Time Optimization
  76. What's in a prompt? Language models encode literary style in prompt embeddings
  77. Improving endpoint detection in end-to-end streaming ASR for conversational speech
  78. Predictively Combatting Toxicity in Health-related Online Discussions through Machine Learning
  79. Unveil Multi-Picture Descriptions for Multilingual Mild Cognitive Impairment Detection via Contrastive Learning
  80. What Lives? A meta-analysis of diverse opinions on the definition of life
  81. Graph Neural Networks Based Anomalous RSSI Detection
  82. Adaptive Tokenization: On the Hop-Overpriority Problem in Tokenized Graph Learning Models
  83. HR-VILAGE-3K3M: A Human Respiratory Viral Immunization Longitudinal Gene Expression Dataset for Systems Immunity
  84. QUADS: QUAntized Distillation Framework for Efficient Speech Language Understanding
  85. ComBAT Harmonization for diffusion MRI: Challenges and Best Practices
  86. MSVIT: Improving Spiking Vision Transformer Using Multi-scale Attention Fusion
  87. Enhancing Shape Perception and Segmentation Consistency for Industrial Image Inspection
  88. AneumoBench: A Source-Linked Benchmark for Synthetic-Geometry Transfer in Aneurysm CFD
  89. A Hybrid Quantum Classical Pipeline for X Ray Based Fracture Diagnosis
  90. Sat2Sound: A Unified Framework for Zero-Shot Soundscape Mapping
  91. Model Cards for AI Teammates: Comparing Human-AI Team Familiarization Methods for High-Stakes Environments
  92. Krikri: Advancing Open Large Language Models for Greek
  93. Score-Based Training for Energy-Based TTS Models
  94. Ice Cream Doesn't Cause Drowning: Benchmarking LLMs Against Statistical Pitfalls in Causal Inference
  95. Augmenting Online RL with Offline Data is All You Need: A Unified Hybrid RL Algorithm Design and Analysis
  96. A Blueprint for AI-Driven Software Quality: Integrating LLMs with Established Standards
  97. WIND: Accelerated RNN-T Decoding with Windowed Inference for Non-blank Detection
  98. Language Models Are Capable of Metacognitive Monitoring and Control of Their Internal Activations
  99. Consistency Conditions for Differentiable Surrogate Losses
  100. CoRank: LLM-Based Compact Reranking with Document Features for Scientific Retrieval
  101. Panda: A pretrained forecast model for chaotic dynamics
  102. Unsupervised Learning of Local Updates for Maximum Independent Set in Dynamic Graphs
  103. ReSW-VL: Representation Learning for Surgical Workflow Analysis Using Vision-Language Model
  104. Synthetic Non-stationary Data Streams for Recognition of the Unknown
  105. Understanding Task Representations in Neural Networks via Bayesian Ablation
  106. Frozen Backpropagation: Relaxing Weight Symmetry in Deep Spiking Neural Networks
  107. Power Lines: Scaling Laws for Weight Decay and Batch Size in LLM Pre-training
  108. Causal Head Gating: A Framework for Interpreting Roles of Attention Heads in Transformers
  109. Backward Conformal Prediction
  110. GeoRanker: Distance-Aware Ranking for Worldwide Image Geolocalization
  111. SayCoNav: Utilizing Large Language Models for Adaptive Collaboration in Decentralized Multi-Robot Navigation
  112. Turbocharging Gaussian Process Inference with Approximate Sketch-and-Project
  113. Robust learning of halfspaces under log-concave marginals
  114. Are Large Language Models Good at Detecting Propaganda?
  115. Unsupervised anomaly detection in MeV ultrafast electron diffraction
  116. HarmonE: A Self-Adaptive Approach to Architecting Sustainable MLOps
  117. GeoVLM: Improving Automated Vehicle Geolocalisation Using Vision-Language Matching
  118. MAFA: A multi-agent framework for annotation
  119. Assessing GPT Performance in a Proof-Based University-Level Course Under Blind Grading
  120. Sobolev Gradient Ascent for Optimal Transport: Barycenter Optimization and Convergence Analysis
  121. Clarifying orthography: Orthographic transparency as compressibility
  122. Optimal Client Sampling in Federated Learning with Client-Level Heterogeneous Differential Privacy
  123. Traceable Black-box Watermarks for Federated Learning
  124. Self-Reinforced Graph Contrastive Learning
  125. Collapsing Taylor Mode Automatic Differentiation
  126. FedCTTA: A Collaborative Approach to Continual Test-Time Adaptation in Federated Learning
  127. Incentivizing Truthful Language Models via Peer Elicitation Games
  128. IPENS:Interactive Unsupervised Framework for Rapid Plant Phenotyping Extraction via NeRF-SAM2 Fusion
  129. Learning (Approximately) Equivariant Networks via Constrained Optimization
  130. Cross-Lingual Representation Alignment Through Contrastive Image-Caption Tuning
  131. Spiking Neural Networks with Random Network Architecture
  132. Direction-Aware Neural Acoustic Fields for Few-Shot Interpolation of Ambisonic Impulse Responses
  133. Deterministic Bounds and Random Estimates of Metric Tensors on Neuromanifolds
  134. Half Search Space is All You Need
  135. Scalable Bayesian Monte Carlo: fast uncertainty estimation beyond deep ensembles
  136. Self-Supervised Learning for Image Segmentation: A Comprehensive Survey
  137. Uncovering Critical Sets of Deep Neural Networks via Sample-Independent Critical Lifting
  138. OMGPT: A Sequence Modeling Framework for Data-driven Operational Decision Making
  139. Learning Wavelet-Sparse FDK for 3D Cone-Beam CT Reconstruction
  140. Symmetry-Breaking Descent for Invariant Cost Functionals
  141. VocalAgent: Large Language Models for Vocal Health Diagnostics with Safety-Aware Evaluation
  142. FlexFed: Mitigating Catastrophic Forgetting in Heterogeneous Federated Learning in Pervasive Computing Environments
  143. An Overview of Arithmetic Adaptations for Inference of Convolutional Neural Networks on Re-configurable Hardware
  144. FreeMesh: Boosting Mesh Generation with Coordinates Merging
  145. Q2Forge: Minting Competency Questions and SPARQL Queries for Question-Answering Over Knowledge Graphs
  146. Autonomous nanoparticle synthesis by design
  147. Minimax Rates of Estimation for Optimal Transport Map between Infinite-Dimensional Spaces
  148. Surrogate Modeling of 3D Rayleigh-Benard Convection with Equivariant Autoencoders
  149. Learning Dynamics of RNNs in Closed-Loop Environments
  150. Aligning Trustworthy AI with Democracy: A Dual Taxonomy of Opportunities and Risks
  151. Online Decision-Focused Learning
  152. Breaking the Compression Ceiling: Data-Free Pipeline for Ultra-Efficient Delta Compression
  153. Randomised Optimism via Competitive Co-Evolution for Matrix Games with Bandit Feedback
  154. CS-Sum: A Benchmark for Code-Switching Dialogue Summarization and the Limits of Large Language Models
  155. CATS: Clustering-Aggregated and Time Series for Business Customer Purchase Intention Prediction
  156. Learning collision risk proactively from naturalistic driving data at scale
  157. Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation
  158. Towards Functional Correctness of Large Code Models with Selective Generation
  159. Counter-Inferential Behavior in Natural and Artificial Cognitive Systems
  160. JIR-Arena: The First Benchmark Dataset for Just-in-time Information Recommendation
  161. Exploring Federated Pruning for Large Language Models
  162. Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems
  163. Know Or Not: a library for evaluating out-of-knowledge base robustness
  164. GANCompress: GAN-Enhanced Neural Image Compression with Binary Spherical Quantization
  165. Mean Flows for One-step Generative Modeling
  166. Unlocking Non-Invasive Brain-to-Text
  167. Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards
  168. Recollection from Pensieve: Novel View Synthesis via Learning from Uncalibrated Videos
  169. VTBench: Evaluating Visual Tokenizers for Autoregressive Image Generation
  170. FinePhys: Fine-grained Human Action Generation by Explicitly Incorporating Physical Laws for Effective Skeletal Guidance
  171. SMOTExT: SMOTE meets Large Language Models
  172. Synthetic-Powered Predictive Inference
  173. Fine-tuning Quantized Neural Networks with Zeroth-order Optimization
  174. Understanding Complexity in VideoQA via Visual Program Generation
  175. Learnware of Language Models: Specialized Small Language Models Can Do Big
  176. Machine learning the first stage in 2SLS: Practical guidance from bias decomposition and simulation
  177. Dementia Through Different Eyes: Explainable Modeling of Human and LLM Perceptions for Early Awareness
  178. Gluon: Making Muon & Scion Great Again! (Bridging Theory and Practice of LMO-based Optimizers for LLMs)
  179. GuidedMorph: Two-Stage Deformable Registration for Breast MRI
  180. Joint stochastic localization and applications
  181. AutoMathKG: The automated mathematical knowledge graph based on LLM and vector database
  182. Granary: Speech Recognition and Translation Dataset in 25 European Languages
  183. Robin: A multi-agent system for automating scientific discovery
  184. A Minimum Description Length Approach to Regularization in Neural Networks
  185. Learning by solving differential equations
  186. IG Parser: A Software Package for the Encoding of Institutional Statements using the Institutional Grammar
  187. How Adding Metacognitive Requirements in Support of AI Feedback in Practice Exams Transforms Student Learning Behaviors
  188. Score Distillation Beyond Acceleration: Generative Modeling from Corrupted Data
  189. A Kolmogorov-Arnold Neural Model for Cascading Extremes
  190. What Prompts Don't Say: Understanding and Managing Underspecification in LLM Prompts
  191. Introducing Instruction-Accurate Simulators for Performance Estimation of Autotuning Workloads
  192. Survey: Multi-Armed Bandits Meet Large Language Models
  193. Sense and Sensitivity: Examining the Influence of Semantic Recall on Long Context Code Understanding
  194. Investigating the Vulnerability of LLM-as-a-Judge Architectures to Prompt-Injection Attacks
  195. MRM3: Machine Readable ML Model Metadata
  196. Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels
  197. OPA-Pack: Object-Property-Aware Robotic Bin Packing
  198. Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation
  199. Scalable Importance Sampling in High Dimensions with Low-Rank Mixture Proposals
  200. Measuring Social Influence with Networked Synthetic Control
  201. Recommender Systems for Democracy: Toward Adversarial Robustness in Voting Advice Applications
  202. Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning
  203. Discretion in the Loop: Human Expertise in Algorithm-Assisted College Advising
  204. From What Ifs to Insights: Counterfactuals in Causal Inference vs. Explainable AI
  205. VesselGPT: Autoregressive Modeling of Vascular Geometry
  206. KHRONOS: a Kernel-Based Neural Architecture for Rapid, Resource-Efficient Scientific Computation
  207. eStonefish-Scenes: A Sim-to-Real Validated and Robot-Centric Event-based Optical Flow Dataset for Underwater Vehicles
  208. GMM-Based Comprehensive Feature Extraction and Relative Distance Preservation For Few-Shot Cross-Modal Retrieval
  209. DD-Ranking: Rethinking the Evaluation of Dataset Distillation
  210. Online simultaneous inference for quantiles via smoothed stochastic gradient descent
  211. Cross-Cloud Data Privacy Protection: Optimizing Collaborative Mechanisms of AI Systems by Integrating Federated Learning and LLMs
  212. RECON: Robust symmetry discovery via Explicit Canonical Orientation Normalization
  213. Level Generation with Quantum Reservoir Computing
  214. Rank, Chunk and Expand: Lineage-Oriented Reasoning for Taxonomy Expansion
  215. Event-Driven Dynamic Scene Depth Completion
  216. Hamiltonian Neural PDE Solvers through Functional Approximation
  217. Representation of perceived prosodic similarity of conversational feedback
  218. DB3D-L: Depth-aware BEV Feature Transformation for Accurate 3D Lane Detection
  219. Net-Zero: A Comparative Study on Neural Network Design for Climate-Economic PDEs Under Uncertainty
  220. From Automation to Autonomy: A Survey on Large Language Models in Scientific Discovery
  221. Stronger Together: Unleashing the Social Impact of Hate Speech Research
  222. Joint Depth and Reflectivity Estimation using Single-Photon LiDAR
  223. RN-F: A Novel Approach for Mitigating Contaminated Data in Large Language Models
  224. JNLP at SemEval-2025 Task 11: Cross-Lingual Multi-Label Emotion Detection Using Generative Models
  225. Conformalized Decision Risk Assessment
  226. Reconstructing Physics-Informed Machine Learning for Traffic Flow Modeling: a Multi-Gradient Descent and Pareto Learning Approach
  227. WriteViT: Handwritten Text Generation with Vision Transformer
  228. StarFT: Robust Fine-tuning of Zero-shot Models via Spuriosity Alignment
  229. Investigating Active Sampling for Hardness Classification with Vision-Based Tactile Sensors
  230. Implicit bias produces neural scaling laws in learning curves, from perceptrons to deep networks
  231. CoSeP: Complementary Separability Pruning via Class-Separability Clustering
  232. SeedBench: A Multi-task Benchmark for Evaluating Large Language Models in Seed Science
  233. Hybrid 3D-4D Gaussian Splatting for Fast Dynamic Scene Representation
  234. Semantic Change Detection of Roads and Bridges: A Fine-grained Dataset and Multimodal Frequency-driven Detector
  235. Picturized and Recited with Dialects: A Multimodal Chinese Representation Framework for Sentiment Analysis of Classical Chinese Poetry
  236. Efficient Generation of Parameterised Quantum Circuits from Large Texts
  237. Rapidly Varying Completely Random Measures for Modeling Extremely Sparse Networks
  238. MatPredict: a dataset and benchmark for learning material properties of diverse indoor objects
  239. Inferring stochastic dynamics with growth from cross-sectional data
  240. A Physics-Inspired Optimizer: Velocity Regularized Adam
  241. Adversarial Testing in LLMs: Insights into Decision-Making Vulnerabilities
  242. True Zero-Shot Inference of Dynamical Systems Preserving Long-Term Statistics
  243. Emergence of Fixational and Saccadic Movements in a Multi-Level Recurrent Attention Model for Vision
  244. Interpretable Robotic Friction Learning via Symbolic Regression
  245. Information Science Principles of Machine Learning: A Causal Chain Meta-Framework Based on Formalized Information Mapping
  246. Efficient Speech Language Modeling via Energy Distance in Continuous Latent Space
  247. ToolSpectrum : Towards Personalized Tool Utilization for Large Language Models
  248. Enhancing LLMs for Time Series Forecasting via Structure-Guided Cross-Modal Alignment
  249. FlowCut: Unsupervised Video Instance Segmentation via Temporal Mask Matching
  250. A Case Study of Cross-Lingual Zero-Shot Generalization for Classical Languages in LLMs
  251. Positional Fragility in LLMs: How Offset Effects Reshape Our Understanding of Memorization Risks
  252. RIFLES: Resource-effIcient Federated LEarning via Scheduling
  253. Role-Playing Evaluation for Large Language Models
  254. Tianyi: A Traditional Chinese Medicine all-rounder language model and its Real-World Clinical Practice
  255. Zero-Shot Adaptation of Behavioral Foundation Models to Unseen Dynamics
  256. What if Deception Cannot be Detected? A Cross-Linguistic Study on the Limits of Deception Detection from Text
  257. Parallel Layer Normalization for Universal Approximation
  258. Language-Specific Latent Process Hinders Cross-Lingual Performance
  259. CacheFlow: Fast Human Motion Prediction by Cached Normalizing Flow
  260. Learning to Adapt to Position Bias in Vision Transformer Classifiers
  261. New Encoders for German Trained from Scratch: Comparing ModernGBERT with Converted LLM2Vec Models
  262. Adaptive Image Restoration for Video Surveillance: A Real-Time Approach
  263. Iterative Formalization and Planning in Partially Observable Environments
  264. μPC: Scaling Predictive Coding to 100+ Layer Networks
  265. Just Dance with π! A Poly-modal Inductor for Weakly-supervised Video Anomaly Detection
  266. When majority rules, minority loses: bias amplification of gradient descent
  267. Unveil Sources of Uncertainty: Feature Contribution to Conformal Prediction Intervals
  268. Continuous Fair SMOTE -- Fairness-Aware Stream Learning from Imbalanced Data
  269. Attention-based clustering
  270. Lightweight and Interpretable Transformer via Mixed Graph Algorithm Unrolling for Traffic Forecast
  271. ARIW-Framework: Adaptive Robust Iterative Watermarking Framework
  272. Time series saliency maps: explaining models across multiple domains
  273. Industrial Synthetic Segment Pre-training
  274. LLM-KG-Bench 3.0: A Compass for SemanticTechnology Capabilities in the Ocean of LLMs
  275. Time-Frequency-Based Attention Cache Memory Model for Real-Time Speech Separation
  276. Treatment Effect Estimation for Optimal Decision-Making
  277. The Effect of Language Diversity When Fine-Tuning Large Language Models for Translation
  278. Systematic Generalization in Language Models Scales with Information Entropy
  279. Cross-modal feature fusion for robust point cloud registration with ambiguous geometry
  280. Graph Alignment for Benchmarking Graph Neural Networks and Learning Positional Encodings
  281. Universal Semantic Disentangled Privacy-preserving Speech Representation Learning
  282. MultiActor-Audiobook: Zero-Shot Audiobook Generation with Faces and Voices of Multiple Speakers
  283. Cross-modal Knowledge Transfer Learning as Graph Matching Based on Optimal Transport for ASR
  284. Advancing Sequential Numerical Prediction in Autoregressive Models
  285. Structure-Aware Corpus Construction and User-Perception-Aligned Metrics for Large-Language-Model Code Completion
  286. Orthogonal Survival Learners for Estimating Heterogeneous Treatment Effects from Time-to-Event Data
  287. OmniFC: Rethinking Federated Clustering via Lossless and Secure Distance Reconstruction
  288. Suicide Risk Assessment Using Multimodal Speech Features: A Study on the SW1 Challenge Dataset
  289. 3D Visual Illusion Depth Estimation
  290. Automatic mixed precision for optimizing gained time with constrained loss mean-squared-error based on model partition to sequential sub-graphs
  291. A Path to Universal Neural Cellular Automata
  292. Simplicity is Key: An Unsupervised Pretraining Approach for Sparse Radio Channels
  293. SNAPE-PM: Building and Utilizing Dynamic Partner Models for Adaptive Explanation Generation
  294. RGB-to-Polarization Estimation: A New Task and Benchmark Study
  295. PPTNet: A Hybrid Periodic Pattern-Transformer Architecture for Traffic Flow Prediction and Congestion Identification
  296. A Generalized Label Shift Perspective for Cross-Domain Gaze Estimation
  297. Expert-Like Reparameterization of Heterogeneous Pyramid Receptive Fields in Efficient CNNs for Fair Medical Image Classification
  298. KIT's Offline Speech Translation and Instruction Following Submission for IWSLT 2025
  299. topicwizard -- a Modern, Model-agnostic Framework for Topic Model Visualization and Interpretation
  300. TSPulse: Tiny Pre-Trained Models with Disentangled Representations for Rapid Time-Series Analysis
  301. Deconstructing Positional Information: From Attention Logits to Training Biases
  302. LiBOG: Lifelong Learning for Black-Box Optimizer Generation
  303. Anti-Inpainting: A Proactive Defense Approach against Malicious Diffusion-based Inpainters under Unknown Conditions
  304. The role of data partitioning on the performance of EEG-based deep learning models in supervised cross-subject analysis: a preliminary study
  305. Asymptotic Performance of Time-Varying Bayesian Optimization
  306. Unveiling and Steering Connectome Organization with Interpretable Latent Variables
  307. To Bias or Not to Bias: Detecting bias in News with bias-detector
  308. Latent Generative Modeling of Random Fields from Limited Training Data
  309. EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code
  310. A generalisable head MRI defacing pipeline: Evaluation on 2,566 meningioma scans
  311. A Skull-Adaptive Framework for AI-Based 3D Transcranial Focused Ultrasound Simulation
  312. Optimal Formats for Weight Quantisation
  313. An Empirical Study of Many-to-Many Summarization with Large Language Models
  314. Enhancing Diffusion-Weighted Images (DWI) for Diffusion MRI: Is it Enough without Non-Diffusion-Weighted B=0 Reference?
  315. Fast, Not Fancy: Rethinking G2P with Rich Data and Rule-Based Models
  316. A Structured Literature Review on Traditional Approaches in Current Natural Language Processing
  317. Calm-Whisper: Reduce Whisper Hallucination On Non-Speech By Calming Crazy Heads Down
  318. Augmented Regression Models using Neurochaos Learning
  319. Multiscale Adaptive Conflict-Balancing Model For Multimedia Deepfake Detection
  320. MA-COIR: Leveraging Semantic Search Index and Generative Models for Ontology-Driven Biomedical Concept Recognition
  321. Segmentation of temporomandibular joint structures on mri images using neural networks for diagnosis of pathologies
  322. Hardware-Adaptive and Superlinear-Capacity Memristor-based Associative Memory
  323. LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data
  324. GuRE:Generative Query REwriter for Legal Passage Retrieval
  325. Neural Morphological Tagging for Nguni Languages
  326. CALM-PDE: Continuous and Adaptive Convolutions for Latent Space Modeling of Time-dependent PDEs
  327. Multi-Level Monte Carlo Training of Neural Operators
  328. Leveraging LLM Inconsistency to Boost Pass@k Performance
  329. CPRet: A Dataset, Benchmark, and Model for Retrieval in Competitive Programming
  330. PyFCG: Fluid Construction Grammar in Python
  331. RGNMR: A Gauss-Newton method for robust matrix completion with theoretical guarantees
  332. Temporal Query Network for Efficient Multivariate Time Series Forecasting
  333. Active Learning on Synthons for Molecular Design
  334. HiERO: understanding the hierarchy of human behavior enhances reasoning on egocentric videos
  335. SourceDetMamba: A Graph-aware State Space Model for Source Detection in Sequential Hypergraphs
  336. Sinusoidal Initialization, Time for a New Start
  337. Dynamic Graph Induced Contour-aware Heat Conduction Network for Event-based Object Detection
  338. Efficient training for large-scale optical neural network using an evolutionary strategy and attention pruning
  339. The Computation of Generalized Embeddings for Underwater Acoustic Target Recognition using Contrastive Learning
  340. Towards Low-Latency Event Stream-based Visual Object Tracking: A Slow-Fast Approach
  341. AutoGEEval: A Multimodal and Automated Framework for Geospatial Code Generation on GEE with Large Language Models
  342. EPIC: Explanation of Pretrained Image Classification Networks via Prototype
  343. HyperDet: Source Detection in Hypergraphs via Interactive Relationship Construction and Feature-rich Attention Fusion
  344. Specialized Foundation Models for Intelligent Operating Rooms
  345. GAP: Graph-Assisted Prompts for Dialogue-based Medication Recommendation
  346. RetinaLogos: Fine-Grained Synthesis of High-Resolution Retinal Images Through Captions
  347. AdS-GNN -- a Conformally Equivariant Graph Neural Network
  348. Spline Dimensional Decomposition with Interpolation-based Optimal Knot Selection for Stochastic Dynamic Analysis
  349. From Grunts to Lexicons: Emergent Language from Cooperative Foraging
  350. Outsourced Privacy-Preserving Feature Selection Based on Fully Homomorphic Encryption
  351. Causality-Inspired Robustness for Nonlinear Models via Representation Learning
  352. Unified Cross-modal Translation of Score Images, Symbolic Music, and Performance Audio
  353. Towards a Universal Image Degradation Model via Content-Degradation Disentanglement
  354. Re-identification of De-identified Documents with Autoregressive Infilling
  355. The Way Up: A Dataset for Hold Usage Detection in Sport Climbing
  356. FLTG: Byzantine-Robust Federated Learning via Angle-Based Defense and Non-IID-Aware Weighting
  357. Accelerate TarFlow Sampling with GS-Jacobi Iteration
  358. A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design
  359. AGI-Elo: How Far Are We From Mastering A Task?
  360. The Hidden Structure -- Improving Legal Document Understanding Through Explicit Text Formatting
  361. The Gaussian Latent Machine: Efficient Prior and Posterior Sampling for Inverse Problems
  362. A Study on the Refining Handwritten Font by Mixing Font Styles
  363. Contrastive Prompting Enhances Sentence Embeddings in LLMs through Inference-Time Steering
  364. Theoretical Investigation on Inductive Bias of Isolation Forest
  365. Emergent Specialization: Rare Token Neurons in Language Models
  366. SynDec: A Synthesize-then-Decode Approach for Arbitrary Textual Style Transfer via Large Language Models
  367. Rethinking Features-Fused-Pyramid-Neck for Object Detection
  368. Learning In Chaos: Efficient Autoscaling and Self-Healing for Multi-Party Distributed Training
  369. PsyMem: Fine-grained psychological alignment and Explicit Memory Control for Advanced Role-Playing LLMs
  370. Dynamic Sight Range Selection in Multi-Agent Reinforcement Learning
  371. Koopman Autoencoders Learn Neural Representation Dynamics
  372. Decentralized Arena: Towards Democratic and Scalable Automatic Evaluation of Language Models
  373. FedSVD: Adaptive Orthogonalization for Private Federated Learning with LoRA
  374. Informed Mixing -- Improving Open Set Recognition via Attribution-based Augmentation
  375. Transportability without Graphs: A Bayesian Approach to Identifying s-Admissible Backdoor Sets
  376. EAVIT: Efficient and Accurate Human Value Identification from Text data via LLMs
  377. Unlearning for Federated Online Learning to Rank: A Reproducibility Study
  378. Enhancing Transformers Through Conditioned Embedded Tokens
  379. UniHM: Universal Human Motion Generation with Object Interactions in Indoor Scenes
  380. P2HCT: Plug-and-Play Hierarchical C2F Transformer for Multi-Scale Feature Fusion
  381. Language Models That Walk the Talk: A Framework for Formal Fairness Certificates
  382. Enhancing Channel-Independent Time Series Forecasting via Cross-Variate Patch Embedding
  383. Your Offline Policy is Not Trustworthy: Bilevel Reinforcement Learning for Sequential Portfolio Optimization
  384. Global urban visual perception varies across demographics and personalities
  385. ProDS: Preference-oriented Data Selection for Instruction Tuning
  386. LiDAR MOT-DETR: A LiDAR-based Two-Stage Transformer for 3D Multiple Object Tracking
  387. Structure-based Anomaly Detection and Clustering
  388. Malware families discovery via Open-Set Recognition on Android manifest permissions
  389. TeleOpBench: A Simulator-Centric Benchmark for Dual-Arm Dexterous Teleoperation
  390. PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization
  391. MVAR: Visual Autoregressive Modeling with Scale and Spatial Markovian Conditioning
  392. EpiLLM: Unlocking the Potential of Large Language Models in Epidemic Forecasting
  393. Deep Unfolding with Kernel-based Quantization in MIMO Detection
  394. SounDiT: Geo-Contextual Soundscape-to-Landscape Generation
  395. What is Stigma Attributed to? A Theory-Grounded, Expert-Annotated Interview Corpus for Demystifying Mental-Health Stigma
  396. Automated Bias Assessment in AI-Generated Educational Content Using CEAT Framework
  397. Shadow-FT: Tuning Instruct Model via Training on Paired Base Model
  398. VLC Fusion: Vision-Language Conditioned Sensor Fusion for Robust Object Detection
  399. IA-MVS: Instance-Focused Adaptive Depth Sampling for Multi-View Stereo
  400. Identifiability of Nonnegative Tucker Decompositions -- Part I: Theory
  401. Any-to-Any Learning in Computational Pathology via Triplet Multimodal Pretraining
  402. Confidence-Regulated Generative Diffusion Models for Reliable AI Agent Migration in Vehicular Metaverses
  403. Pave Your Own Path: Graph Gradual Domain Adaptation on Fused Gromov-Wasserstein Geodesics
  404. PLAICraft: Large-Scale Time-Aligned Vision-Speech-Action Dataset for Embodied AI
  405. SpatialLLM: From Multi-modality Data to Urban Spatial Intelligence
  406. Long-RVOS: A Comprehensive Benchmark for Long-term Referring Video Object Segmentation
  407. TACOcc:Target-Adaptive Cross-Modal Fusion with Volume Rendering for 3D Semantic Occupancy
  408. Bullying the Machine: How Personas Increase LLM Vulnerability
  409. RoVo: Robust Voice Protection Against Unauthorized Speech Synthesis with Embedding-Level Perturbations
  410. Towards Effective Federated Graph Foundation Model via Mitigating Knowledge Entanglement
  411. DimGrow: Memory-Efficient Field-level Embedding Dimension Search
  412. RAFP: Identifying LLM Lineages via Rare-Region Fingerprints
  413. On the Mechanisms of Adversarial Data Augmentation for Robust and Adaptive Transfer Learning
  414. TransferTraj: A Vehicle Trajectory Learning Model for Region and Task Transferability
  415. Text2midi-InferAlign: Improving Symbolic Music Generation with Inference-Time Alignment
  416. Multi-View Wireless Sensing via Conditional Generative Learning: Framework and Model Design
  417. Predicting Reaction Time to Comprehend Scenes with Foveated Scene Understanding Maps
  418. SPKLIP: Aligning Spike Video Streams with Natural Language
  419. Web Intellectual Property at Risk: Preventing Unauthorized Real-Time Retrieval by Large Language Models
  420. Predicting Turn-Taking and Backchannel in Human-Machine Conversations Using Linguistic, Acoustic, and Visual Signals
  421. textttDIAMONDs: A Dataset for mathbbDynamic mathbbInformation mathbbAnd mathbbMental modeling mathbbOf mathbbNumeric mathbbDiscussions
  422. AutoMat: Enabling Automated Crystal Structure Reconstruction from Microscopy via Agentic Tool Use
  423. Spiking Neural Network: a low power solution for physical layer authentication
  424. Use as Many Surrogates as You Want: Selective Ensemble Attack to Unleash Transferability without Sacrificing Resource Efficiency
  425. Two out of Three (ToT): using self-consistency to make robust predictions
  426. Single Image Reflection Separation via Dual Prior Interaction Transformer
  427. ChromFound: Towards A Universal Foundation Model for Single-Cell Chromatin Accessibility Data
  428. Revealing the Deceptiveness of Knowledge Editing: A Mechanistic Analysis of Superficial Editing
  429. MVPainter: Accurate and Detailed 3D Texture Generation via Multi-View Diffusion with Geometric Control
  430. Multi-Resolution Haar Network: Enhancing human motion prediction via Haar transform
  431. Degradation-Aware Feature Perturbation for All-in-One Image Restoration
  432. Enhancing Latent Computation in Transformers with Latent Tokens
  433. scSiameseClu: A Siamese Clustering Framework for Interpreting single-cell RNA Sequencing Data
  434. Lightweight and Effective Preference Construction in PIBT for Large-Scale Multi-Agent Pathfinding
  435. SAFE: Improving LLM Systems using Sentence-Level In-generation Attribution
  436. BusterX: MLLM-Powered AI-Generated Video Forgery Detection and Explanation
  437. Duluth at SemEval-2025 Task 7: TF-IDF with Optimized Vector Dimensions for Multilingual Fact-Checked Claim Retrieval
  438. Hamiltonian of polymatrix zero-sum games
  439. Diff-MM: Exploring Pre-trained Text-to-Image Generation Model for Unified Multi-modal Object Tracking
  440. Fast and Simple Densest Subgraph with Predictions
  441. Accelerated Markov Chain Monte Carlo Algorithms on Discrete States
  442. Learning Cross-Spectral Point Features with Task-Oriented Training
  443. PromptPrism: A Linguistically-Inspired Taxonomy for Prompts
  444. SurveillanceVQA-589K: A Benchmark for Comprehensive Surveillance Video-Language Understanding with Large Models
  445. Event-based Star Tracking under Spacecraft Jitter: the e-STURT Dataset
  446. CMLFormer: A Dual Decoder Transformer with Switching Point Learning for Code-Mixed Language Modeling
  447. A Few Large Shifts: Layer-Inconsistency Based Minimal Overhead Adversarial Example Detection
  448. Learning Robust Spectral Dynamics for Temporal Domain Generalization
  449. Improving Multilingual Language Models by Aligning Representations through Steering
  450. A Comprehensive Survey on Physical Risk Control in the Era of Foundation Model-enabled Robotics
  451. An approach based on class activation maps for investigating the effects of data augmentation on neural networks for image classification
  452. Coarse Attribute Prediction with Task Agnostic Distillation for Real World Clothes Changing ReID