mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sun 28 Sep 2025

369 papers

  1. Efficient Turing Machine Simulation with TransformersLLM reasoning → Prompting and chain-of-thought reasoning
  2. WAREX: Web Agent Reliability Evaluation on Existing BenchmarksLLM agents and tool use → Web, search, and research agents
  3. MACE: A Hybrid LLM Serving System with Colocated SLO-aware Continuous Retraining AlignmentEfficient LLM inference and serving → Serving systems and request scheduling
  4. Discovering Transformer Circuits via a Hybrid Attribution and Pruning FrameworkMechanistic interpretability → Circuits and mechanistic analysis
  5. Training Optimal Large Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  6. MemMamba: Rethinking Memory Patterns in State Space ModelState-space sequence models (S4, Mamba) → Core SSM architectures for language
  7. Spiral of Silence in Large Language Model AgentsLLM agents and tool use → Social simulation and multi-agent debate
  8. Emission-GPT: A domain-specific language model agent for knowledge retrieval, emission inventory and data analysisLLM agents and tool use → Multimodal and embodied agents
  9. DiffuSpec: Unlocking Diffusion Language Models for Speculative DecodingDiffusion models → Discrete and text diffusion +1
  10. HiDe: Rethinking The Zoom-IN method in High Resolution MLLMs via Hierarchical DecouplingLLM reasoning → Multimodal reasoning +1
  11. RADAR: A Risk-Aware Dynamic Multi-Agent Framework for LLM Safety Evaluation via Role-Specialized CollaborationLLM agents and tool use → Agent threats, guardrails and governance +1
  12. Dynamic Policy Induction for Adaptive Prompt Optimization: Bridging the Efficiency-Accuracy Gap via Lightweight Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning +1
  13. GANji: A Framework for Introductory AI Image GenerationDiffusion models → Diffusion foundations and sampling
  14. Transparent, Evaluable, and Accessible Data Agents: A Proof-of-Concept FrameworkLLM agents and tool use → Web, search, and research agents
  15. HyMaTE: A Hybrid Mamba and Transformer Model for EHR Representation LearningState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  16. GeoFunFlow: Geometric Function Flow Matching for Inverse Operator Learning over Complex GeometriesDiffusion models → Flow matching, time series and science
  17. Dual-Scale World Models for LLM Agents Towards Hard-Exploration ProblemsWorld models → World models for language agents +1
  18. Fathom-DeepResearch: Unlocking Long Horizon Information Retrieval and Synthesis for SLMsLLM agents and tool use → Web, search, and research agents
  19. From Training to Generalization: Improving Moral Reasoning Through Pragmatic InferenceLLM reasoning → Reasoning benchmarks and evaluation
  20. Unified Multi-Modal Interactive & Reactive 3D Motion Generation via Rectified FlowDiffusion models → Video generation
  21. GEAR: A General Evaluation Framework for Abductive ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  22. CORRECT: COndensed eRror RECognition via knowledge Transfer in multi-agent systemsLLM agents and tool use → Software engineering coding agents
  23. Uncovering Grounding IDs: How External Cues Shape Multimodal BindingMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  24. In-Context Compositional Q-Learning for Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
  25. Bridging On-Device and Cloud LLMs for Collaborative Reasoning: A Unified Methodology for Local Routing and Post-TrainingLLM reasoning → Reasoning for agents, planning and code
  26. Analyzing and Evaluating Unbiased Language Model WatermarkLLM safety and security → Watermarking generated content and models
  27. PartnerMAS: An LLM Hierarchical Multi-Agent Framework for Business Partner Selection on High-Dimensional FeaturesLLM agents and tool use → Financial trading and forecasting agents
  28. An Ensemble Framework for Unbiased Language Model WatermarkingLLM safety and security → Watermarking generated content and models
  29. Hazy Pedestrian Trajectory Prediction via Physical Priors and Graph-MambaState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
  30. SparseD: Sparse Attention for Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  31. Sequential Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  32. SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear AttentionDiffusion models → Video generation
  33. Policy-as-Prompt: Turning AI Governance Rules into Guardrails for AI AgentsLLM safety and security → Prompt injection and agent security
  34. Advancing Multi-agent Traffic Simulation via R1-Style Reinforcement Fine-TuningLLM agents and tool use → Multimodal and embodied agents
  35. LLM/Agent-as-Data-Analyst: A SurveyLLM agents and tool use → Web, search, and research agents
  36. TusoAI: Agentic Optimization for Scientific MethodsLLM agents and tool use → Web, search, and research agents
  37. Toward Preference-aligned Large Language Models via Residual-based Model SteeringLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  38. Towards Redundancy Reduction in Diffusion Models for Efficient Video Super-ResolutionDiffusion models → Inverse problems and image restoration
  39. ByteSized32Refactored: Towards an Extensible Interactive Text Games Corpus for LLM World Modeling and EvaluationWorld models → World models for language agents
  40. Curriculum-Guided Reinforcement Learning for Synthesizing Gas-Efficient Financial Derivatives ContractsDeep reinforcement learning methods → Adversarial robustness and RL in finance
  41. VFSI: Validity First Spatial Intelligence for Constraint-Guided Traffic DiffusionDiffusion models → Diffusion and flow policies for robotics
  42. HiPO: Hybrid Policy Optimization for Dynamic Reasoning in LLMsLLM reasoning → Reinforcement learning for reasoning
  43. Conditional Advantage Estimation for Reinforcement Learning in Large Reasoning ModelsLLM reasoning → Reinforcement learning for reasoning
  44. Reinforcement Learning with Inverse Rewards for World Model Post-trainingWorld models → Latent dynamics models and model-based RL +2
  45. HunyuanImage 3.0 Technical ReportMixture-of-experts → Multimodal MoE models
  46. Explore-Execute Chain: Towards an Efficient Structured Reasoning ParadigmLLM reasoning → Reasoning for agents, planning and code
  47. On the Separability of Information in Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  48. Beyond Benchmarks: Understanding Mixture-of-Experts Models through Internal MechanismsMixture-of-experts → MoE theory and gating functions
  49. AutoPrune: Each Complexity Deserves a Pruning PolicyMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  50. HiViS: Hiding Visual Tokens from the Drafter for Speculative Decoding in Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  51. FUSAR-KLIP: Towards Multimodal Foundation Models for Remote SensingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  52. Taming Masked Diffusion Language Models via Consistency Trajectory Reinforcement Learning with Fewer Decoding StepDiffusion models → Discrete and text diffusion +1
  53. DriveE2E: Closed-Loop Benchmark for End-to-End Autonomous Driving through Real-to-SimulationEnd-to-end autonomous driving → End-to-end system architecture
  54. Bridging the Task Gap: Multi-Task Adversarial Transferability in CLIP and Its DerivativesMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  55. Continual Learning to Generalize Forwarding Strategies for Diverse Mobile Wireless NetworksDeep reinforcement learning methods → RL for energy, networks and operations
  56. EditScore: Unlocking Online RL for Image Editing via High-Fidelity Reward ModelingLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  57. EWC-Guided Diffusion Replay for Exemplar-Free Continual Learning in Medical ImagingDiffusion models → Robustness, privacy and adversarial aspects
  58. Preserving Cross-Modal Stability for Visual Unlearning in Multimodal ScenariosLLM safety and security → Machine unlearning
  59. Towards Understanding Subliminal Learning: When and How Hidden Biases TransferKnowledge distillation → On-policy and self-distillation for LLMs
  60. Quant Fever, Reasoning Blackholes, Schrodinger's Compliance, and More: Probing GPT-OSS-20BLLM reasoning → Reasoning for agents, planning and code
  61. PCRI: Measuring Context Robustness in Multimodal Models for Enterprise ApplicationsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  62. Multi-Value-Product Retrieval-Augmented Generation for Industrial Product Attribute Value IdentificationRetrieval-augmented generation → RAG pipeline design and evaluation
  63. Winning the Pruning Gamble: A Unified Approach to Joint Sample and Token Pruning for Efficient Supervised Fine-TuningLLM alignment / RLHF / preference optimisation → LLM preference optimization methods +1
  64. Taught Well Learned Ill: Towards Distillation-conditional Backdoor AttackKnowledge distillation → Federated, robust and private distillation
  65. Gradient Coupling: The Hidden Barrier to Generalization in Agentic Reinforcement LearningLLM agents and tool use → Reinforcement learning for LLM agents
  66. Efficient Multi-turn RL for GUI Agents via Decoupled Training and Adaptive Data CurationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +2
  67. AgentGuard: Runtime Verification of AI AgentsLLM agents and tool use → Agent threats, guardrails and governance
  68. SPELL: Self-Play Reinforcement Learning for Evolving Long-Context Language ModelsLLM reasoning → Test-time compute and efficient thinking +1
  69. Adversarial Diffusion for Robust Reinforcement LearningDiffusion models → Diffusion and flow policies for robotics +1
  70. Bayesian Mixture-of-Experts: Towards Making LLMs Know What They Don't KnowMixture-of-experts → Expert routing strategies
  71. Uni4D-LLM: A Unified SpatioTemporal-Aware VLM for 4D Understanding and GenerationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  72. Assessing Visual Privacy Risks in Multimodal AI: A Novel Taxonomy-Grounded Evaluation of Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  73. Space Group Conditional Flow MatchingDiffusion models → Flow matching, time series and science
  74. Semantic-Space Exploration and Exploitation in RLVR for LLM ReasoningLLM reasoning → Reinforcement learning for reasoning
  75. FedAgentBench: Towards Automating Real-world Federated Medical Image Analysis with Server-Client LLM AgentsLLM agents and tool use → Medical and scientific domain agents
  76. STAIR: Addressing Stage Misalignment through Temporal-Aligned Preference Reinforcement LearningLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
  77. Sample-Efficient Optimisation over the Outputs of Generative ModelsDiffusion models → Diffusion foundations and sampling
  78. Enhancing LLM Steering through Sparse Autoencoder-Based Vector RefinementMechanistic interpretability → SAE features and their applications
  79. Transformer Tafsir at QIAS 2025 Shared Task: Hybrid Retrieval-Augmented Generation for Islamic Knowledge Question AnsweringRetrieval-augmented generation → RAG robustness and adaptive retrieval
  80. CaRe-BN: Precise Moving Statistics for Stabilizing Spiking Neural Networks in Reinforcement LearningDeep reinforcement learning methods → Spiking and neuromorphic RL
  81. Visual CoT Makes VLMs Smarter but More FragileLLM reasoning → Multimodal reasoning +1
  82. GroupCoOp: Group-robust Fine-tuning via Group Prompt LearningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  83. Trained Mamba Emulates Online Gradient Descent in In-Context Linear RegressionState-space sequence models (S4, Mamba) → Core SSM architectures for language
  84. ReLumix: Extending Image Relighting to Video via Video Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
  85. From What to Why: A Multi-Agent System for Evidence-based Chemical Reaction Condition ReasoningLLM reasoning → Clinical and biomedical applications +1
  86. Knowledge-Level Consistency Reinforcement Learning: Dual-Fact Alignment for Long-Form FactualityLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  87. UniAlignment: Semantic Alignment for Unified Image Generation, Understanding, Manipulation and PerceptionDiffusion models → Image generation, text-to-image and editing
  88. Transparent Visual Reasoning via Object-Centric Agent CollaborationLLM reasoning → Multimodal reasoning
  89. An Investigation of Batch Normalization in Off-Policy Actor-Critic AlgorithmsDeep reinforcement learning methods → Deep RL algorithms and representations
  90. Poivre: Self-Refining Visual Pointing with Reinforcement LearningMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  91. Compose and Fuse: Revisiting the Foundational Bottlenecks in Multimodal ReasoningLLM reasoning → Multimodal reasoning +1
  92. GUI-Shepherd: Reliable Process Reward and Verification for Long-Sequence GUI TasksLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  93. Demystifying the Lifecycle of Failures in Platform-Orchestrated Agentic WorkflowsLLM agents and tool use → Software engineering coding agents
  94. EAPO: Enhancing Policy Optimization with On-Demand Expert AssistanceLLM reasoning → Reinforcement learning for reasoning
  95. LUQ: Layerwise Ultra-Low Bit Quantization for Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  96. MedLA: A Logic-Driven Multi-Agent Framework for Complex Medical Reasoning with Large Language ModelsLLM reasoning → Clinical and biomedical applications +1
  97. DiffPCN: Latent Diffusion Model Based on Multi-view Depth Images for Point Cloud CompletionDiffusion models → 3D, point cloud and scene generation
  98. Diff-3DCap: Shape Captioning with Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
  99. Measuring Sparse Autoencoder Feature SensitivityMechanistic interpretability → SAE features and their applications
  100. Deterministic Policy Gradient for Reinforcement Learning with Continuous Time and StateDeep reinforcement learning methods → RL theory and sample complexity
All 369
  1. StrucADT: Generating Structure-controlled 3D Point Clouds with Adjacency Diffusion TransformerDiffusion models → 3D, point cloud and scene generation
  2. CrimEdit: Controllable Editing for Counterfactual Object Removal, Insertion, and MovementDiffusion models → 3D, point cloud and scene generation
  3. VIVA+: Human-Centered Situational Decision-MakingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  4. SafeSearch: Automated Red-Teaming of LLM-Based Search AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  5. HomeSafeBench: Benchmarking Embodied Vision-Language Models in Free-Exploration Home Safety InspectionMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  6. Evaluating Program Semantics Reasoning with Type Inference in System FLLM reasoning → Reasoning for agents, planning and code
  7. QuantSparse: Comprehensively Compressing Video Diffusion Transformer with Model Quantization and Attention SparsificationDiffusion models → Video generation
  8. Towards a Comprehensive Scaling Law of Mixture-of-ExpertsMixture-of-experts → MoE large language models
  9. MSD-KMamba: Bidirectional Spatial-Aware Multi-Modal 3D Brain Segmentation via Multi-scale Self-Distilled Fusion StrategyKnowledge distillation → Distillation for medical imaging
  10. From Reasoning to Answer: Empirical, Attention-Based and Mechanistic Insights into Distilled DeepSeek R1 ModelsLLM reasoning → Test-time compute and efficient thinking
  11. PAT-Agent: Autoformalization for Model CheckingLLM agents and tool use → General LLM agent frameworks and benchmarks
  12. RCI: A Score for Evaluating Global and Local Reasoning in Multimodal BenchmarksLLM reasoning → Multimodal reasoning +1
  13. Why Alignment Must Precede Distillation: A Minimal Working ExplanationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  14. Beyond Greedy Exits: Improved Early Exit Decisions for Risk Control and ReliabilityEfficient LLM inference and serving → Early exit and edge inference
  15. HIVTP: A Training-Free Method to Improve VLMs Efficiency via Hierarchical Visual Token Pruning Using Middle-Layer-Based Importance ScoreMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  16. LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal TrainingMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  17. Beyond English-Centric Training: How Reinforcement Learning Improves Cross-Lingual Reasoning in LLMsLLM reasoning → Reasoning benchmarks and evaluation
  18. Focusing on What Matters: Object-Agent-centric Tokenization for Vision Language Action modelsVision-language-action models → Generalist VLA models and benchmarks +1
  19. Don't Settle Too Early: Self-Reflective Remasking for Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  20. ReWatch-R1: Boosting Complex Video Reasoning in Large Vision-Language Models through Agentic Data SynthesisLLM reasoning → Multimodal reasoning +3
  21. From Static to Dynamic: a Survey of Topology-Aware Perception in Autonomous DrivingEnd-to-end autonomous driving → VLMs for autonomous driving
  22. EfficientMIL: Efficient Linear-Complexity MIL Method for WSI ClassificationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  23. LightFair: Towards an Efficient Alternative for Fair T2I Diffusion via Debiasing Pre-trained Text EncodersDiffusion models → Image generation, text-to-image and editing
  24. LayerScope: Predictive Cross-Layer Scheduling for Efficient Multi-Batch MoE Inference on Legacy ServersMixture-of-experts → Efficient MoE training and inference systems
  25. Fast Thinking for Large Language ModelsLLM reasoning → Test-time compute and efficient thinking
  26. Emergent Slow Thinking in LLMs as Inverse Tree FreezingLLM reasoning → Reinforcement learning for reasoning
  27. RIV: Recursive Introspection Mask Diffusion Vision Language ModelMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  28. DiffInk: Glyph- and Style-Aware Latent Diffusion Transformer for Text to Online Handwriting GenerationDiffusion models → Image generation, text-to-image and editing
  29. Reasoning Scaffolding: Distilling the Flow of Thought from LLMsLLM reasoning → Prompting and chain-of-thought reasoning +1
  30. PSG-Agent: Personality-Aware Safety Guardrail for LLM-based AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  31. FlowLUT: Efficient Image Enhancement via Differentiable LUTs and Iterative Flow MatchingDiffusion models → Inverse problems and image restoration
  32. MAN: Latent Diffusion Enhanced Multistage Anti-Noise Network for Efficient and High-Quality Low-Dose CT Image DenoisingDiffusion models → Medical imaging and segmentation
  33. VAMamba: An Efficient Visual Adaptive Mamba for Image RestorationState-space sequence models (S4, Mamba) → Mamba for image restoration
  34. StolenLoRA: Exploring LoRA Extraction Attacks via Synthetic DataSynthetic data and self-improvement for LLMs → Safety of self-evolving systems
  35. Avoid Catastrophic Forgetting with Rank-1 Fisher from Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
  36. Foundation Model-Based Adaptive Semantic Image Transmission for Dynamic Wireless EnvironmentsDiffusion models → Diffusion for compression and wireless
  37. BridgeDrive: Diffusion Bridge Policy for Closed-Loop Trajectory Planning in Autonomous DrivingDiffusion models → Diffusion and flow policies for robotics +1
  38. Reducing Cost of LLM Agents with Trajectory ReductionLLM agents and tool use → Software engineering coding agents
  39. VividFace: High-Quality and Efficient One-Step Diffusion For Video Face EnhancementDiffusion models → Inverse problems and image restoration
  40. RobuQ: Pushing DiTs to W1.58A2 via Robust Activation QuantizationDiffusion models → Diffusion foundations and sampling
  41. Towards Efficient CoT Distillation: Self-Guided Rationale Selector for Better Performance with Fewer RationalesLLM reasoning → Prompting and chain-of-thought reasoning
  42. Clean First, Align Later: Benchmarking Preference Data Cleaning for Reliable LLM AlignmentLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  43. Formalization Driven LLM Prompt Jailbreaking via Reinforcement LearningLLM safety and security → Jailbreaking
  44. Zero-shot Whole-Body Manipulation with a Large-Scale Soft Robotic Torso via Guided Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  45. On the Shelf Life of Fine-Tuned LLM-Judges: Future-Proofing, Backward-Compatibility, and Question GeneralizationLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  46. Beyond the Strongest LLM: Multi-Turn Multi-Agent Orchestration vs. Single LLMs on BenchmarksLLM agents and tool use → Social simulation and multi-agent debate
  47. AmarDoctor: An AI-Driven, Multilingual, Voice-Interactive Digital Health Application for Primary Care Triage and Patient Management to Bridge the Digital Health Divide for Bengali Speakers
  48. CLARAE: Clarity Preserving Reconstruction AutoEncoder for Denoising and Rhythm Classification of Intracardiac Electrograms
  49. Performance of Machine Learning Methods for Gravity Inversion: Successes and Challenges
  50. SAC-Opt: Semantic Anchors for Iterative Correction in Optimization Modeling
  51. Edge-FIT: Federated Instruction Tuning of Quantized LLMs for Privacy-Preserving Smart Home Environments
  52. Mathematically rigorous proofs for Shapley explanations
  53. Quantifying constraint hierarchies in Bayesian PINNs via per-constraint Hessian decomposition
  54. Quantile-Scaled Bayesian Optimization Using Rank-Only Feedback
  55. QuadEnhancer: Leveraging Quadratic Transformations to Enhance Deep Neural Networks
  56. A Cross-Lingual Analysis of Bias in Large Language Models Using Romanian History
  57. ChunkLLM: A Lightweight Pluggable Framework for Accelerating LLMs Inference
  58. Privacy in the Age of AI: A Taxonomy of Data Risks
  59. Variable Rate Image Compression via N-Gram Context based Swin-transformer
  60. Adapting Large Language Models to Mitigate Skin Tone Biases in Clinical Dermatology Tasks: A Mixed-Methods Study
  61. DPsurv: Dual-Prototype Evidential Fusion for Uncertainty-Aware and Interpretable Whole-Slide Image Survival Prediction
  62. A Recall-First CNN for Sleep Apnea Screening from Snoring Audio
  63. Latent Representation Learning from 3D Brain MRI for Interpretable Prediction in Multiple Sclerosis
  64. VoiceBridge: General Speech Restoration with One-step Latent Bridge Models
  65. DNABERT-2: Fine-Tuning a Genomic Language Model for Colorectal Gene Enhancer Classification
  66. InfMasking: Unleashing Synergistic Information by Contrastive Multimodal Interactions
  67. Position-Blind Ptychography: Viability of image reconstruction via data-driven variational inference
  68. A Weather Foundation Model for the Power Grid
  69. Cognifying Education: Mapping AI's transformative role in emotional, creative, and collaborative learning
  70. Evaluating the Impact of Radiographic Noise on Chest X-ray Semantic Segmentation and Disease Classification Using a Scalable Noise Injection Framework
  71. GeoSQL-Eval: First Evaluation of LLMs on PostGIS-Based NL2GeoSQL Queries
  72. How Effective Are Time-Series Models for Precipitation Nowcasting? A Comprehensive Benchmark for GNSS-based Precipitation Nowcasting
  73. Heterogeneous Multi-agent Collaboration in UAV-assisted Mobile Crowdsensing Networks
  74. Internal Planning in Language Models: Characterizing Horizon and Branch Awareness
  75. Beyond Magic Words: Sharpness-Aware Prompt Evolving for Robust Large Language Models with TARE
  76. Mash, Spread, Slice! Learning to Manipulate Object States via Visual Spatial Progress
  77. BOSfM: A View Planning Framework for Optimal 3D Reconstruction of Agricultural Scenes
  78. The Impossibility of Inverse Permutation Learning in Transformer Models
  79. Ancestry Tree Clustering for Particle Filter Diversity Maintenance
  80. Echo Flow Networks
  81. EduVidQA: Generating and Evaluating Long-form Answers to Student Questions based on Lecture Videos
  82. ADAPT: Lightweight, Long-Range Machine Learning Force Fields Without Graphs
  83. SVAC: Scaling Is All You Need For Referring Video Object Segmentation
  84. BTC-SAM: Leveraging LLMs for Generation of Bias Test Cases for Sentiment Analysis Models
  85. SpeedCP: Fast Kernel-based Conditional Conformal Prediction
  86. Singleton-Optimized Conformal Prediction
  87. Clebsch-Gordan Transformer: Fast and Global Equivariant Attention
  88. PerfBench: Can Agents Resolve Real-World Performance Bugs?
  89. Large-Scale Constraint Generation -- Can LLMs Parse Hundreds of Constraints?
  90. Do Repetitions Matter? Strengthening Reliability in LLM Evaluations
  91. PEARL: Peer-Enhanced Adaptive Radio via On-Device LLM
  92. Autoregressive Video Generation beyond Next Frames Prediction
  93. Ensembling Multilingual Transformers for Robust Sentiment Analysis of Tweets
  94. Demographic-Agnostic Fairness without Harm
  95. A Family of Kernelized Matrix Costs for Multiple-Output Mixture Neural Networks
  96. ResFormer: All-Time Reservoir Memory for Long Sequence Classification
  97. AQUAIR: A High-Resolution Indoor Environmental Quality Dataset for Smart Aquaculture Monitoring
  98. A Small Math Model: Recasting Strategy Choice Theory in an LLM-Inspired Architecture
  99. A Second-Order Perspective on Pruning at Initialization and Knowledge Transfer
  100. On The Variability of Concept Activation Vectors
  101. Optimism as Risk-Seeking in Multi-Agent Reinforcement Learning
  102. Topographic Constraints Shape Brain-Like Component Structure in Auditory Models
  103. GPS-MTM: Capturing Pattern of Normalcy in GPS-Trajectories with self-supervised learning
  104. From Edge to HPC: Investigating Cross-Facility Data Streaming Architectures
  105. Joint Superpixel and Self-Representation Learning for Scalable Hyperspectral Image Clustering
  106. The Role of Logic and Automata in Understanding Transformers
  107. R3: Reconstruction, Raw, and Rain: Deraining Directly in the Bayer Domain
  108. Generalized Category Discovery in Hyperspectral Images via Prototype Subspace Modeling
  109. Pretraining Scaling Laws for Generative Evaluations of Language Models
  110. FrameMind: Frame-Interleaved Video Reasoning via Reinforcement Learning
  111. Does Weak-to-strong Generalization Happen under Spurious Correlations?
  112. SIE3D: Single-Image Expressive 3D Avatar Generation via Semantic Embedding and Perceptual Expression Loss
  113. MCPMark: A Benchmark for Stress-Testing Realistic and Comprehensive MCP Use
  114. Gaze Estimation for Human-Robot Interaction: Analysis Using the NICO Platform
  115. TREAT-Net: Tabular-Referenced Echocardiography Analysis for Acute Coronary Syndrome Treatment Prediction
  116. Future-Proofing Programmers: Optimal Knowledge Tracing for AI-Assisted Personalized Education
  117. Guide: Generalized-Prior and Data Encoders for DAG Estimation
  118. RPG360: Robust 360 Depth Estimation with Perspective Foundation Models and Graph Optimization
  119. The Hidden Costs of Translation Accuracy: Distillation, Quantization, and Environmental Impact
  120. Automatic selection of primary studies in systematic reviews with evolutionary rule-based classification
  121. Equation-Free Coarse Control of Distributed Parameter Systems via Local Neural Operators
  122. A Novel Hybrid Deep Learning and Chaotic Dynamics Approach for Thyroid Cancer Classification
  123. Detecting and Rectifying Noisy Labels: A Similarity-based Approach
  124. Evaluating the Robustness of Chinchilla Compute-Optimal Scaling
  125. Learning-Based Testing for Deep Learning: Enhancing Model Robustness with Adversarial Input Prioritization
  126. MAD-PINN: A Decentralized Physics-Informed Machine Learning Framework for Safe and Optimal Multi-Agent Control
  127. Vision-Grounded Machine Interpreting: Improving the Translation Process through Visual Cues
  128. ColLab: A Collaborative Spatial Progressive Data Engine for Referring Expression Comprehension and Generation
  129. Monotonic Transformation Invariant Multi-task Learning
  130. CrashSplat: 2D to 3D Vehicle Damage Segmentation in Gaussian Splatting
  131. Efficient Identification of High Similarity Clusters in Polygon Datasets
  132. Brain-language fusion enables interactive neural readout and in-silico experimentation
  133. Easy Turn: Integrating Acoustic and Linguistic Modalities for Robust Turn-Taking in Full-Duplex Spoken Dialogue Systems
  134. Do Language Models Update their Forecasts with New Information?
  135. A University of Texas Medical Branch Case Study on Aortic Calcification Detection
  136. Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks
  137. Graph Mixing Additive Networks
  138. Asymptotic Expansion for Nonlinear Filtering in the Small System Noise Regime
  139. Token Painter: Training-Free Text-Guided Image Inpainting via Mask Autoregressive Models
  140. Revisit the Imbalance Optimization in Multi-task Learning: An Experimental Analysis
  141. From Neural Networks to Logical Theories: The Correspondence between Fibring Modal Logics and Fibring Neural Networks
  142. MoReact: Generating Reactive Motion from Textual Descriptions
  143. Adversarial Versus Federated: An Adversarial Learning based Multi-Modality Cross-Domain Federated Medical Segmentation
  144. Integrated Communication and Control for Energy-Efficient UAV Swarms: A Multi-Agent Reinforcement Learning Approach
  145. Interpreting deep learning-based stellar mass estimation via causal analysis and mutual information decomposition
  146. LifeCLEF Plant Identification Task 2014
  147. Q-FSRU: Quantum-Augmented Frequency-Spectral For Medical Visual Question Answering
  148. Differentiable Sparsity via D-Gating: Simple and Versatile Structured Penalization
  149. Dynamic Orthogonal Continual Fine-tuning for Mitigating Catastrophic Forgettings
  150. LifeCLEF Plant Identification Task 2015
  151. AssemblyHands-X: Modeling 3D Hand-Body Coordination for Understanding Bimanual Human Activities
  152. Gradient Flow Convergence Guarantee for General Neural Network Architectures
  153. Extendable Generalization Self-Supervised Diffusion for Low-Dose CT Reconstruction
  154. DocPruner: A Storage-Efficient Framework for Multi-Vector Visual Document Retrieval via Adaptive Patch-Level Embedding Pruning
  155. Learning Adaptive Pseudo-Label Selection for Semi-Supervised 3D Object Detection
  156. Disentangling Score Content and Performance Style for Joint Piano Rendering and Transcription
  157. Rethinking Visual Autoregressive Sampling with Information-Grounding Guidance
  158. Sim-DETR: Unlock DETR for Temporal Sentence Grounding
  159. GSID: Generative Semantic Indexing for E-Commerce Product Understanding
  160. FairViT-GAN: A Hybrid Vision Transformer with Adversarial Debiasing for Fair and Explainable Facial Beauty Prediction
  161. CE-FAM: Concept-Based Explanation via Fusion of Activation Maps
  162. Towards Fine-Grained Text-to-3D Quality Assessment: A Benchmark and A Two-Stage Rank-Learning Metric
  163. 2nd Place Report of MOSEv2 Challenge 2025: Concept Guided Video Object Segmentation via SeC
  164. Mix-Ecom: Towards Mixed-Type E-Commerce Dialogues with Complex Domain Rules
  165. HFuzzer: Testing Large Language Models for Package Hallucinations via Phrase-based Fuzzing
  166. AISHELL6-whisper: A Chinese Mandarin Audio-visual Whisper Speech Dataset with Speech Recognition Baselines
  167. Electric Currents for Discrete Data Generation
  168. Test-time GNN Model Evaluation on Dynamic Graphs
  169. A Multi-Camera Vision-Based Approach for Fine-Grained Assembly Quality Control
  170. IndexNet: Timestamp and Variable-Aware Modeling for Time Series Forecasting
  171. Navigating the Labyrinth: Path-Sensitive Unit Test Generation with Large Language Models
  172. AnveshanaAI: A Multimodal Platform for Adaptive AI/ML Education through Automated Question Generation and Interactive Assessment
  173. Tequila: Trapping-free Ternary Quantization for Large Language Models
  174. Influence-Guided Concolic Testing of Transformer Robustness
  175. Open-DeBias: Toward Mitigating Open-Set Bias in Language Models
  176. Controllable Generation of Large-Scale 3D Urban Layouts with Semantic and Structural Guidance
  177. From Frustration to Fun: An Adaptive Problem-Solving Puzzle Game Powered by Genetic Algorithm
  178. From Unstable to Playable: Stabilizing Angry Birds Levels via Object Segmentation
  179. Falcon: A Cross-Modal Evaluation Dataset for Comprehensive Safety Perception
  180. Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions
  181. Sequence Pathfinder for Multi-Agent Pickup and Delivery in the Warehouse
  182. Texture Vector-Quantization and Reconstruction Aware Prediction for Generative Super-Resolution
  183. Knowledge Homophily in Large Language Models
  184. A Modality-Tailored Graph Modeling Framework for Urban Region Representation via Contrastive Learning
  185. GenView++: Unifying Adaptive Generative Augmentation and Quality-Driven Supervision for Contrastive Representation Learning
  186. From Personal to Collective: On the Role of Local and Global Memory in LLM Personalization
  187. Quantifying How Training Gradient Sparsity Affect Spiking Neural Network Accuracy And Robustness
  188. VioPTT: Violin Technique-Aware Transcription from Synthetic Data Augmentation
  189. SHAPoint: Task-Agnostic, Efficient, and Interpretable Point-Based Risk Scoring via Shapley Values
  190. Understanding Textual Capability Degradation in Speech LLMs via Parameter Importance Analysis
  191. Anchored Supervised Fine-Tuning
  192. PVTAdpNet: Polyp Segmentation using Pyramid vision transformer with a novel Adapter block
  193. Time-Shifted Token Scheduling for Symbolic Music Generation
  194. Beyond Game Theory Optimal: Profit-Maximizing Poker Agents for No-Limit Holdem
  195. LocoFormer: Generalist Locomotion via Long-context Adaptation
  196. GBSK: Skeleton Clustering via Granular-ball Computing and Multi-Sampling for Large-Scale Data
  197. ResAD++: Towards Class Agnostic Anomaly Detection via Residual Feature Learning
  198. GRS-SLAM3R: Real-Time Dense SLAM with Gated Recurrent State
  199. HieraTok: Multi-Scale Visual Tokenizer Improves Image Reconstruction and Generation
  200. FastViDAR: Real-Time Omnidirectional Depth Estimation via Alternative Hierarchical Attention
  201. M3DLayout: A Multi-Source Dataset of 3D Indoor Layouts and Structured Descriptions for 3D Generation
  202. AudioMoG: Guiding Audio Generation with Mixture-of-Guidance
  203. Video Panels for Long Video Understanding
  204. OctoPipe: Reducing Pipeline Bubbles for Heterogeneous Models via Co-Optimizing Partitioning, Placement, and Scheduling
  205. A Self-Adaptive Frequency Domain Network for Continuous Intraoperative Hypotension Prediction
  206. PD-Diag-Net: Clinical-Priors guided Network on Brain MRI for Auxiliary Diagnosis of Parkinson's Disease
  207. Do LLMs Understand Romanian Driving Laws? A Study on Multimodal and Fine-Tuned Question Answering
  208. Collaboration of Fusion and Independence: Hypercomplex-driven Robust Multi-Modal Knowledge Graph Completion
  209. FraudTransformer: Time-Aware GPT for Transaction Fraud Detection
  210. DFG-PCN: Point Cloud Completion with Degree-Flexible Point Graph
  211. INSTINCT: Instance-Level Interaction Architecture for Query-Based Collaborative Perception
  212. Confidence Aware SSD Ensemble with Weighted Boxes Fusion for Weapon Detection
  213. Estimating Time Series Foundation Model Transferability via In-Context Learning
  214. Merge Now, Regret Later: The Hidden Cost of Model Merging Is Adversarial Transferability
  215. FedDAPL: Toward Client-Private Generalization in Federated Learning
  216. Joint Hybrid Beamforming and Artificial Noise Design for Secure Multi-UAV ISAC Networks
  217. Hedonic Neurons: A Mechanistic Mapping of Latent Coalitions in Transformer MLPs
  218. Decentralized Dynamic Cooperation of Personalized Models for Federated Continual Learning
  219. Token Merging via Spatiotemporal Information Mining for Surgical Video Understanding
  220. Graph Neural Networks with Diversity-aware Neighbor Selection and Dynamic Multi-scale Fusion for Multivariate Time Series Forecasting
  221. Hermes: A Multi-Scale Spatial-Temporal Hypergraph Network for Stock Time Series Forecasting
  222. Calibration Meets Reality: Making Machine Learning Predictions Trustworthy
  223. Pure Node Selection for Imbalanced Graph Node Classification
  224. Virtual Nodes based Heterogeneous Graph Convolutional Neural Network for Efficient Long-Range Information Aggregation
  225. Aligning LLMs for Multilingual Consistency in Enterprise Applications
  226. From Past To Path: Masked History Learning for Next-Item Prediction in Generative Recommendation
  227. Color-Pair Guided Robust Zero-Shot 6D Pose Estimation and Tracking of Cluttered Objects on Edge Devices
  228. Sparse-Up: Learnable Sparse Upsampling for 3D Generation with High-Fidelity Textures
  229. Griffin: Generative Reference and Layout Guided Image Composition
  230. MotionVerse: A Unified Multimodal Framework for Motion Comprehension, Generation and Editing
  231. Leakage-Free Evaluation and Distribution-Robust Spatio-Temporal Graph Learning for Inductive Kriging
  232. Game-Oriented ASR Error Correction via RAG-Enhanced LLM
  233. Efficient Domain-Adaptive Multi-Task Dense Prediction with Vision Foundation Models
  234. Communication-aware Wide-Area Damping Control using Risk-Constrained Reinforcement Learning
  235. Generalizable Speech Deepfake Detection via Information Bottleneck Enhanced Adversarial Alignment
  236. BioVessel-Net and RetinaMix: Unsupervised Retinal Vessel Segmentation from OCTA Images
  237. GraphIFE: Rethinking Graph Imbalance Node Classification via Invariant Learning
  238. InteractMove: Text-Controlled Human-Object Interaction Generation in 3D Scenes with Movable Objects
  239. Spatially Parallel All-optical Neural Networks
  240. Efficient Audio-Visual Speech Separation with Discrete Lip Semantics and Multi-Scale Global-Local Attention
  241. Large Language Models and Futures Price Factors in China
  242. ZeroScene: A Zero-Shot Framework for 3D Scene Generation from a Single Image and Controllable Texture Editing
  243. VMDiff: Visual Mixing Diffusion for Limitless Cross-Object Synthesis
  244. Deep Taxonomic Networks for Unsupervised Hierarchical Prototype Discovery
  245. Characteristic Root Analysis and Regularization for Linear Time Series Forecasting
  246. Multi-Level Heterogeneous Knowledge Transfer Network on Forward Scattering Center Model for Limited Samples SAR ATR
  247. Timber: Training-free Instruct Model Refining with Base via Effective Rank
  248. Toward a Holistic Approach to Continual Model Merging
  249. Sketching Low-Rank Plus Diagonal Matrices
  250. EVO-LRP: Evolutionary Optimization of LRP for Interpretable Model Explanations
  251. LLM Hallucination Detection: HSAD
  252. Jackal: A Real-World Execution-Based Benchmark Evaluating Large Language Models on Text-to-JQL Tasks
  253. ML-Asset Management: Curation, Discovery, and Utilization
  254. Uncovering Vulnerabilities of LLM-Assisted Cyber Threat Intelligence
  255. Automated design of compound lenses with discrete-continuous optimization
  256. Benchmarking LLM-Assisted Blue Teaming via Standardized Threat Hunting
  257. Improving constraint-based discovery with robust propagation and reliable LLM priors
  258. Node Classification via Simplicial Interaction with Augmented Maximal Clique Selection
  259. Towards Interpretable Visual Decoding with Attention to Brain Representations
  260. RAVEN: Resilient Aerial Navigation via Open-Set Semantic Memory and Behavior Adaptation
  261. Pancreas Part Segmentation under Federated Learning Paradigm
  262. A Hierarchical Structure-Enhanced Personalized Recommendation Model for Traditional Chinese Medicine Formulas Based on KG Diffusion Guidance
  263. From Fields to Splats: A Cross-Domain Survey of Real-Time Neural Scene Representations
  264. Fusing Sequence Motifs and Pan-Genomic Features: Antimicrobial Resistance Prediction using an Explainable Lightweight 1D CNN-XGBoost Ensemble
  265. Automatic Speech Recognition for Greek Medical Dictation
  266. Disentanglement of Variations with Multimodal Generative Modeling
  267. End-to-End Deep Learning for Predicting Metric Space-Valued Outputs
  268. OVSeg3R: Learn Open-vocabulary Instance Segmentation from 2D via 3D Reconstruction
  269. Calibrated and Resource-Aware Super-Resolution for Reliable Driver Behavior Analysis