mlsanityData to 14 Oct 2026

Papers

New on arXiv

Mon 27 Oct 2025

407 papers

  1. Quantifying Document Impact in RAG-LLMsRetrieval-augmented generation → Privacy and security of RAG
  2. Probing Knowledge Holes in Unlearned LLMsLLM safety and security → Machine unlearning
  3. Magentic Marketplace: An Open-Source Environment for Studying Agentic MarketsLLM agents and tool use → Financial trading and forecasting agents
  4. StreetMath: Study of LLMs' Approximation BehaviorsLLM reasoning → Mathematical reasoning
  5. A Survey on Efficient Vision-Language-Action ModelsVision-language-action models → Generalist VLA models and benchmarks
  6. MR-Align: Meta-Reasoning Informed Factuality Alignment for Large Reasoning ModelsLLM reasoning → Test-time compute and efficient thinking
  7. PISA-Bench: The PISA Index as a Multilingual and Multimodal Metric for the Evaluation of Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
  8. Semantic Communications with World ModelsWorld models → Video-generation world models and simulators
  9. TurboPortrait3D: Single-step diffusion-based fast portrait novel-view synthesisDiffusion models → 3D, point cloud and scene generation
  10. Latent Chain-of-Thought for Visual ReasoningLLM reasoning → Multimodal reasoning +1
  11. Agent-based Automated Claim Matching with Instruction-following LLMsLLM agents and tool use → Social simulation and multi-agent debate
  12. Revisiting Value Iteration: Unified Analysis of Discounted and Average-Reward CasesDeep reinforcement learning methods → RL theory and sample complexity
  13. AfriMTEB and AfriE5: Benchmarking and Adapting Text Embedding Models for African LanguagesRetrieval-augmented generation → Generation and context integration
  14. PRO: Enabling Precise and Robust Text Watermark for Open-Source LLMsLLM safety and security → Watermarking generated content and models
  15. Agentic AI Security: Threats, Defenses, Evaluation, and Open ChallengesLLM agents and tool use → Agent threats, guardrails and governance
  16. Large Language Model Agent Personality and Response Appropriateness: Evaluation by Human Linguistic Experts, LLM-as-Judge, and Natural Language Processing ModelLLM agents and tool use → Social simulation and multi-agent debate
  17. OraPlan-SQL: A Planning-Centric Framework for Complex Bilingual NL2SQL ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
  18. GIFT: Group-Relative Implicit Fine-Tuning Integrates GRPO with DPO and UNALLM reasoning → Reinforcement learning for reasoning +1
  19. A PDE-Informed Latent Diffusion Model for 2-m Temperature DownscalingDiffusion models → Flow matching, time series and science
  20. Your LLM Agents are Temporally Blind: The Misalignment Between Tool Use Decisions and Human Time PerceptionLLM agents and tool use → Tool learning and function calling
  21. Decentralized Multi-Agent Goal Assignment for Path Planning using Large Language ModelsLLM agents and tool use → General LLM agent frameworks and benchmarks
  22. ReCAP: Recursive Context-Aware Reasoning and Planning for Large Language Model AgentsLLM reasoning → Test-time compute and efficient thinking +1
  23. Semantic-Guided Cross-Sensor Super Resolution of Remote Sensing Images: A Gated Dual Conditioning Flow Matching ModelDiffusion models → Inverse problems and image restoration
  24. Learning Interpretable Features in Audio Latent Spaces via Sparse AutoencodersMechanistic interpretability → Activation steering methods
  25. Explainable Detection of AI-Generated Images with Artifact Localization Using Faster-Than-Lies and Vision-Language Models for Edge DevicesMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  26. BitSkip: An Empirical Analysis of Quantization and Early Exit Composition in TransformersEfficient LLM inference and serving → Early exit and edge inference
  27. RoboOmni: Proactive Robot Manipulation in Omni-modal ContextMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  28. TDFlow: Agentic Workflows for Test Driven DevelopmentLLM agents and tool use → Software engineering coding agents
  29. Debiasing Reward Models by Representation Learning with GuaranteesLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  30. Game-TARS: Pretrained Foundation Models for Scalable Generalist Multimodal Game AgentsLLM agents and tool use → Reinforcement learning for LLM agents
  31. Beyond Prompt Engineering: Neuro-Symbolic-Causal Architecture for Robust Multi-Objective AI AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  32. QueryIPI: Query-agnostic Indirect Prompt Injection on Coding AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  33. MCPGuard : Automatically Detecting Vulnerabilities in MCP ServersLLM agents and tool use → Agent threats, guardrails and governance
  34. Variational Masked Diffusion ModelsDiffusion models → Discrete and text diffusion
  35. PixelRefer: A Unified Framework for Spatio-Temporal Object Referring with Arbitrary GranularityMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  36. Alita-G: Self-Evolving Generative Agent for Agent GenerationLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  37. Think Twice: Branch-and-Rethink Reasoning Reward ModelLLM reasoning → Reinforcement learning for reasoning +1
  38. Multi-Agent Evolve: LLM Self-Improve through Co-evolutionLLM reasoning → Reasoning for agents, planning and code +2
  39. PRISM-Bench: A Benchmark of Puzzle-Based Visual Tasks with CoT Error DetectionLLM reasoning → Multimodal reasoning +1
  40. Lightweight Robust Direct Preference OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  41. A Survey of Data Agents: Emerging Paradigm or Overstated Hype?LLM agents and tool use → Web, search, and research agents
  42. UrbanVLA: A Vision-Language-Action Model for Urban MicromobilityVision-language-action models → VLA for autonomous driving
  43. More Than Generation: Unifying Generation and Depth Estimation via Text-to-Image Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
  44. RobotArena ∞: Scalable Robot Benchmarking via Real-to-Sim TranslationVision-language-action models → Failure recovery and robustness
  45. EgoThinker: Unveiling Egocentric Reasoning with Spatio-Temporal CoTLLM reasoning → Spatial and embodied reasoning
  46. LimRank: Less is More for Reasoning-Intensive Information RerankingLLM reasoning → Knowledge- and tool-augmented reasoning
  47. Dexbotic: Open-Source Vision-Language-Action ToolboxVision-language-action models → Generalist VLA models and benchmarks
  48. Logic-Guided Socially-aware Robot Navigation World ModelWorld models → World models for navigation +1
  49. Emotion-Coherent Reasoning for Multimodal LLMs via Emotional Rationale VerifierLLM reasoning → Audio-language model reasoning +1
  50. VOLD: Reasoning Transfer from LLMs to Vision-Language Models via On-Policy DistillationLLM reasoning → Multimodal reasoning +2
  51. Yesnt: Are Diffusion Relighting Models Ready for Capture Stage Compositing? A Hybrid Alternative to Bridge the GapDiffusion models → 3D, point cloud and scene generation
  52. Are Agents Probabilistic Automata? A Trace-Based, Memory-Constrained Theory of Agentic AILLM agents and tool use → General LLM agent frameworks and benchmarks
  53. Learning to Reason Efficiently with Discounted Reinforcement LearningLLM reasoning → Test-time compute and efficient thinking +1
  54. On the Faithfulness of Visual Thinking: Measurement and EnhancementLLM reasoning → Multimodal reasoning +1
  55. MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal UnderstandingMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  56. Video-Thinker: Sparking "Thinking with Videos" via Reinforcement LearningLLM reasoning → Multimodal reasoning +2
  57. BrowseConf: Confidence-Guided Test-Time Scaling for Web AgentsLLM reasoning → Reasoning for agents, planning and code +1
  58. Omni-Reward: Towards Generalist Omni-Modal Reward Modeling with Free-Form PreferencesLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  59. An Information-Theoretic Analysis of OOD Generalization in Meta-Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  60. Causal Deep Q NetworkDeep reinforcement learning methods → Deep RL algorithms and representations
  61. VideoTG-R1: Boosting Video Temporal Grounding via Curriculum Reinforcement Learning on Reflected Boundary AnnotationsDeep reinforcement learning methods → RL training of language and agent models
  62. EMTSF:Extraordinary Mixture of SOTA Models for Time Series ForecastingMixture-of-experts → MoE for time series and graphs
  63. An Efficient Remote Sensing Super Resolution Method Exploring Diffusion Priors and Multi-Modal Constraints for Crop Type MappingDiffusion models → Inverse problems and image restoration
  64. BaZi-Based Character Simulation Benchmark: Evaluating AI on Temporal and Persona ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  65. Adaptive Blockwise Search: Inference-Time Alignment for Large Language ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  66. Quadratic Truncated Random Return in Distributional LQR: Positive Definiteness, Density, and Log-ConcavityDeep reinforcement learning methods → RL for games and combinatorial optimization
  67. Transferable Deep Reinforcement Learning for Cross-Domain Navigation: from Farmland to the MoonDeep reinforcement learning methods → RL for robot navigation and UAV control
  68. CNOT Minimal Circuit Synthesis: A Reinforcement Learning ApproachDeep reinforcement learning methods → Quantum reinforcement learning
  69. Adaptive Stochastic Coefficients for Accelerating Diffusion SamplingDiffusion models → Diffusion foundations and sampling
  70. Code Aesthetics with Agentic Reward FeedbackLLM agents and tool use → Software engineering coding agents
  71. PAHQ: Accelerating Automated Circuit Discovery through Mixed-Precision Inference OptimizationMechanistic interpretability → Circuits and mechanistic analysis
  72. Deep Active Inference with Diffusion Policy and Multiple Timescale World Model for Real-World Exploration and NavigationWorld models → World models for navigation +1
  73. A Video Is Not Worth a Thousand WordsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  74. Multi-Stakeholder Alignment in LLM-Powered Collaborative AI Systems: A Multi-Agent Framework for Intelligent TutoringLLM agents and tool use → Educational agents and math problem solving
  75. Process Reward Models for Sentence-Level Verification of LVLM Radiology ReportsLLM reasoning → Hallucination detection and mitigation +2
  76. Human-Like Goalkeeping in a Realistic Football Simulation: a Sample-Efficient Reinforcement Learning ApproachDeep reinforcement learning methods → RL for games and combinatorial optimization
  77. VR-Drive: Viewpoint-Robust End-to-End Driving with Feed-Forward 3D Gaussian SplattingEnd-to-end autonomous driving → Generative simulation for driving
  78. Introducing physics-informed generative models for targeting structural novelty in the exploration of chemical spaceDiffusion models → Flow matching, time series and science
  79. Guiding Skill Discovery with Foundation ModelsDeep reinforcement learning methods → Deep RL algorithms and representations
  80. Adapting Interleaved Encoders with PPO for Language-Guided Reinforcement Learning in BabyAIDeep reinforcement learning methods → RL for robot locomotion and manipulation
  81. Revisiting Multimodal Positional Encoding in Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  82. Smaller Models, Smarter Rewards: A Two-Sided Approach to Process and Outcome RewardsLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  83. Think before Recommendation: Autonomous Reasoning-enhanced RecommenderLLM reasoning → LLM reasoning for recommendation
  84. Fast-MIA: Efficient and Scalable Membership Inference for LLMsLLM safety and security → Membership inference attacks
  85. Quality-Aware Translation Tagging in Multilingual RAG systemRetrieval-augmented generation → Generation and context integration
  86. Advantage Shaping as Surrogate Reward Maximization: Unifying Pass@K Policy GradientsLLM reasoning → Reinforcement learning for reasoning +1
  87. HieraMamba: Video Temporal Grounding via Hierarchical Anchor-Mamba PoolingState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
  88. LLM Meets Diffusion: A Hybrid Framework for Crystal Material GenerationDiffusion models → Flow matching, time series and science
  89. Incentivizing Agentic Reasoning in LLM Judges via Tool-Integrated Reinforcement LearningLLM reasoning → Reasoning for agents, planning and code +1
  90. Nested AutoRegressive ModelsDiffusion models → Image generation, text-to-image and editing
  91. Towards Stable and Effective Reinforcement Learning for Mixture-of-ExpertsLLM reasoning → Reinforcement learning for reasoning +2
  92. ManiDP: Manipulability-Aware Diffusion Policy for Posture-Dependent Bimanual ManipulationDiffusion models → Diffusion and flow policies for robotics
  93. Coupled Flow MatchingDiffusion models → Flow matching, time series and science
  94. MoEMeta: Mixture-of-Experts Meta Learning for Few-Shot Relational LearningMixture-of-experts → Mixture of LoRA experts
  95. TALM: Dynamic Tree-Structured Multi-Agent Framework with Long-Term Memory for Scalable Code GenerationLLM agents and tool use → Software engineering coding agents
  96. Exploring Semantic-constrained Adversarial Example with Instruction Uncertainty ReductionDiffusion models → Robustness, privacy and adversarial aspects
  97. Reasoning About Reasoning: Towards Informed and Reflective Use of LLM Reasoning in HCILLM reasoning → Reasoning benchmarks and evaluation
  98. The Reasoning Trap: How Enhancing LLM Reasoning Amplifies Tool HallucinationLLM reasoning → Hallucination detection and mitigation
  99. VALA: Learning Latent Anchors for Training-Free and Temporally ConsistentDiffusion models → Video generation
  100. Multi-Agent Conditional Diffusion Model with Mean Field Communication as Wireless Resource Allocation PlannerDiffusion models → Diffusion for compression and wireless
All 407
  1. MAD-Fact: A Multi-Agent Debate Framework for Long-Form Factuality Evaluation in LLMsLLM agents and tool use → Web, search, and research agents
  2. When Compression Becomes an Attack Surface: Black-Box Attacks on Prompt-Compressed LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance +2
  3. DiffRhythm 2: Efficient and High Fidelity Song Generation via Block Flow MatchingDiffusion models → Audio, speech and music
  4. GTR-Mamba: Geometry-to-Tangent Routing Mamba for Hyperbolic POI RecommendationState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
  5. Generating Auxiliary Tasks with Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  6. PPE: Positional Preservation Embedding for Token Compression in Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  7. Robust Uncertainty Quantification for Self-Evolving Large Language Models via Continual Domain PretrainingSynthetic data and self-improvement for LLMs → Synthetic reasoning data and bootstrapping
  8. Diffuse to Detect: A Generalizable Framework for Anomaly Detection with Diffusion Models Applications to UAVs and BeyondDiffusion models → Flow matching, time series and science
  9. Simple Denoising Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  10. Improving Human Verification of LLM Reasoning through Interactive Explanation InterfacesLLM reasoning → Prompting and chain-of-thought reasoning
  11. Rethinking Inference Placement for Deep Learning across Edge and Cloud Platforms: A Multi-Objective Optimization Perspective and Future DirectionsLLM reasoning → Reasoning for agents, planning and code
  12. Reinforcement Learning from Compiler and Language Server FeedbackLLM agents and tool use → Software engineering coding agents +1
  13. On the Anisotropy of Score-Based Generative ModelsDiffusion models → Diffusion foundations and sampling
  14. On Generalization in Agentic Tool Calling: CoreThink Agentic Reasoner and MAVEN DatasetLLM reasoning → Reasoning for agents, planning and code +1
  15. MGFRec: Towards Reinforced Reasoning Recommendation with Multiple Groundings and FeedbackLLM reasoning → LLM reasoning for recommendation
  16. Offline Preference Optimization via Maximum Marginal Likelihood EstimationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  17. AI-Assisted Authoring for Transparent, Data-Driven Documents
  18. Assessing the Human-Likeness of LLM-Driven Digital Twins in Simulating Health Care System Trust
  19. TimeStampEval: A Simple LLM Eval and a Little Fuzzy Matching Trick to Improve Search Accuracy
  20. Sound Logical Explanations for Mean Aggregation Graph Neural Networks
  21. sMRI-based Brain Age Estimation in MCI using Persistent Homology
  22. Retracing the Past: LLMs Emit Training Data When They Get Lost
  23. Automatizaci'on de Informes Geot'ecnicos para Macizos Rocosos con IA
  24. Friction on Demand: A Generative Framework for the Inverse Design of Metainterfaces
  25. ECGXtract: Deep Learning-based ECG Feature Extraction for Automated CVD Diagnosis
  26. Multi-Personality Generation of LLMs at Decoding-time
  27. Benchmarking Federated Learning Frameworks for Medical Imaging Deployment: A Comparative Study of NVIDIA FLARE, Flower, and Owkin Substra
  28. Neural Architecture Search for global multi-step Forecasting of Energy Production Time Series
  29. On the Fundamental Limitations of Decentralized Learnable Reward Shaping in Cooperative Multi-Agent Reinforcement Learning
  30. STRIDER: Navigation via Instruction-Aligned Structural Decision Space Optimization
  31. From Uniform to Adaptive: General Skip-Block Mechanisms for Efficient PDE Neural Operators
  32. Towards Gaussian processes modelling to study the late effects of radiotherapy in children and young adults with brain tumours
  33. Impact of clinical decision support systems (cdss) on clinical outcomes and healthcare delivery in low- and middle-income countries: protocol for a systematic review and meta-analysis
  34. Review Based Entity Ranking using Fuzzy Logic Algorithmic Approach: Analysis
  35. Sustained Performance and Energy Accounting for Nonlinear Forecasting Across Classical and Simulated Quantum Models
  36. SFMS-ALR: Script-First Multilingual Speech Synthesis with Adaptive Locale Resolution
  37. Fortytwo: Swarm Inference with Peer-Ranked Consensus
  38. Large Language Models Report Subjective Experience Under Self-Referential Processing
  39. Mutual Wanting in Human--AI Interaction: Empirical Evidence from Large-Scale Analysis of GPT Model Transitions
  40. SwiftEmbed: Ultra-Fast Text Embeddings via Static Token Lookup for Real-Time Applications
  41. A Re-node Self-training Approach for Deep Graph-based Semi-supervised Classification on Multi-view Image Data
  42. Cross-Lingual Summarization as a Black-Box Watermark Removal Attack
  43. The Underappreciated Power of Vision Models for Graph Structural Understanding
  44. ESCA: Enabling Seamless Codec Avatar Execution through Algorithm and Hardware Co-Optimization for Virtual Reality
  45. Leveraging LLMs for Early Alzheimer's Prediction
  46. Adaptive Training of INRs via Pruning and Densification
  47. Decentralized Causal Discovery using Judo Calculus
  48. Auto prompting without training labels: An LLM cascade for product quality assessment in e-commerce catalogs
  49. Modeling Biological Multifunctionality with Echo State Networks
  50. Scalable GPU-Based Integrity Verification for Large Machine Learning Models
  51. A data free neural operator enabling fast inference of 2D and 3D Navier Stokes equations
  52. Understanding Fairness and Prediction Error through Subspace Decomposition and Influence Analysis
  53. MFiSP: A Multimodal Fire Spread Prediction Framework
  54. Differential Privacy: Gradient Leakage Attacks in Federated Learning Environments
  55. PlanarGS: High-Fidelity Indoor 3D Gaussian Splatting Guided by Vision-Language Planar Priors
  56. Adaptive Keyframe Selection for Scalable 3D Scene Reconstruction in Dynamic Environments
  57. Improving the Straight-Through Estimator with Zeroth-Order Information
  58. Breaking the Benchmark: Revealing LLM Bias via Minimal Contextual Augmentation
  59. Key and Value Weights Are Probably All You Need: On the Necessity of the Query, Key, Value weight Triplet in Self-Attention Transformers
  60. DynaStride: Dynamic Stride Windowing with MMCoT for Instructional Multi-Scene Captioning
  61. Group Interventions on Deep Networks for Causal Discovery in Subsystems
  62. Inferring Group Intent as a Cooperative Game. An NLP-based Framework for Trajectory Analysis
  63. RS-ORT: A Reduced-Space Branch-and-Bound Algorithm for Optimal Regression Trees
  64. Improving Visual Discriminability of CLIP for Training-Free Open-Vocabulary Semantic Segmentation
  65. Evaluating the effectiveness of LLM-based interoperability
  66. Language Models for Longitudinal Clinical Prediction
  67. Hybrid Modeling, Sim-to-Real Reinforcement Learning, and Large Language Model Driven Control for Digital Twins
  68. Generating Creative Chess Puzzles
  69. TRELLISWorld: Training-Free World Generation from Object Generators
  70. Artificial Intelligence Based Predictive Maintenance for Electric Buses
  71. From Benchmarks to Business Impact: Deploying IBM Generalist Agent in Enterprise Production
  72. Can LLMs Narrate Tabular Data? An Evaluation Framework for Natural Language Representations of Text-to-SQL System Outputs
  73. A Neural Model for Contextual Biasing Score Learning and Filtering
  74. CRADLE Bench: A Clinician-Annotated Benchmark for Multi-Faceted Mental Health Crisis and Safety Risk Detection
  75. How Pragmatics Shape Articulation: A Computational Case Study in STEM ASL Discourse
  76. Testing-driven Variable Selection in Bayesian Modal Regression
  77. Beyond Understanding: Evaluating the Pragmatic Gap in LLMs' Cultural Processing of Figurative Language
  78. ScaLoRA: Optimally Scaled Low-Rank Adaptation for Efficient High-Rank Fine-Tuning
  79. Combining SHAP and Causal Analysis for Interpretable Fault Detection in Industrial Processes
  80. A Physics-informed Multi-resolution Neural Operator
  81. Beyond the Failures: Rethinking Foundation Models in Pathology
  82. How do simple rotations affect the implicit bias of Adam?
  83. A geometric and deep learning reproducible pipeline for monitoring floating anthropogenic debris in urban rivers using in situ cameras
  84. Revealing the Potential of Learnable Perturbation Ensemble Forecast Model for Tropical Cyclone Prediction
  85. Relaxed Sequence Sampling for Diverse Protein Design
  86. CountFormer: A Transformer Framework for Learning Visual Repetition and Structure in Class-Agnostic Object Counting
  87. Evaluating In Silico Creativity: An Expert Review of AI Chess Compositions
  88. Explaining Robustness to Catastrophic Forgetting Through Incremental Concept Formation
  89. Re-envisioning Euclid Galaxy Morphology: Identifying and Interpreting Features with Sparse Autoencoders
  90. Test-Time Tuned Language Models Enable End-to-end De Novo Molecular Structure Generation from MS/MS Spectra
  91. Bayesian neural networks with interpretable priors from Mercer kernels
  92. Multi-Environment POMDPs: Discrete Model Uncertainty Under Partial Observability
  93. A Neural Network Framework for Discovering Closed-form Solutions to Quadratic Programs with Linear Constraints
  94. AI and the Decentering of Disciplinary Creativity
  95. Evaluating Long-Term Memory for Long-Context Question Answering
  96. MUStReason: A Benchmark for Diagnosing Pragmatic Reasoning in Video-LMs for Multimodal Sarcasm Detection
  97. In Search of the Unknown Unknowns: A Multi-Metric Distance Ensemble for Out of Distribution Anomaly Detection in Astronomical Surveys
  98. On the Societal Impact of Machine Learning
  99. Parallel BiLSTM-Transformer networks for forecasting chaotic dynamics
  100. VIKING: Deep variational inference with stochastic projections
  101. Informed Initialization for Bayesian Optimization and Active Learning
  102. RefleXGen:The unexamined code is not worth using
  103. DBLoss: Decomposition-based Loss Function for Time Series Forecasting
  104. Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations
  105. Track, Inpaint, Resplat: Subject-driven 3D and 4D Generation with Progressive Texture Infilling
  106. InFlux: A Benchmark for Self-Calibration of Dynamic Intrinsics of Video Cameras
  107. FARMER: Flow AutoRegressive Transformer over Pixels
  108. Hope Speech Detection in Social Media English Corpora: Performance of Traditional and Transformer Models
  109. Lookahead Anchoring: Preserving Character Identity in Audio-Driven Human Animation
  110. Reduced AI Acceptance After the Generative AI Boom: Evidence From a Two-Wave Survey Study
  111. ReCode: Unify Plan and Action for Universal Granularity Control
  112. Revising Second Order Terms in Deep Animation Video Coding
  113. ISA-Bench: Benchmarking Instruction Sensitivity for Large Audio Language Models
  114. Minimizing Human Intervention in Online Classification
  115. A U-Net and Transformer Pipeline for Multilingual Image Translation
  116. OntoPret: An Ontology for the Interpretation of Human Behavior
  117. Bayesian Nonlinear PDE Inference via Gaussian Process Collocation with Application to the Richards Equation
  118. JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence
  119. IPQA: A Benchmark for Core Intent Identification in Personalized Question Answering
  120. Sequential Multi-Agent Dynamic Algorithm Configuration
  121. Direct Debiased Machine Learning via Bregman Divergence Minimization
  122. When No Paths Lead to Rome: Benchmarking Systematic Neural Relational Reasoning
  123. Learning Linearity in Audio Consistency Autoencoders via Implicit Regularization
  124. DPGLA: Bridging the Gap between Synthetic and Real Data for Unsupervised Domain Adaptation in 3D LiDAR Semantic Segmentation
  125. Toward Carbon-Neutral Human AI: Rethinking Data, Computation, and Learning Paradigms for Sustainable Intelligence
  126. FreeFuse: Multi-Subject LoRA Fusion via Adaptive Token-Level Routing at Test Time
  127. Localising under the drape: proprioception in the era of distributed surgical robotic system
  128. M4FC: a Multimodal, Multilingual, Multicultural, Multitask Real-World Fact-Checking Dataset
  129. A Deep Latent Factor Graph Clustering with Fairness-Utility Trade-off Perspective
  130. iPac: Incorporating Intra-image Patch Context into Graph Neural Networks for Medical Image Classification
  131. Bayes-Split-Edge: Bayesian Optimization for Constrained Collaborative Inference in Wireless Edge Systems
  132. Training Deep Physics-Informed Kolmogorov-Arnold Networks
  133. Mixed Precision Training of Neural ODEs
  134. Quantum Phase Classification of Rydberg Atom Systems Using Resource-Efficient Variational Quantum Circuits and Classical Shadows
  135. Tighter CMI-Based Generalization Bounds via Stochastic Projection and Quantization
  136. T-REGS: Minimum Spanning Tree Regularization for Self-Supervised Learning
  137. UrbanIng-V2X: A Large-Scale Multi-Vehicle, Multi-Infrastructure Dataset Across Multiple Intersections for Cooperative Perception
  138. MMTutorBench: The First Multimodal Benchmark for AI Math Tutoring
  139. Human-AI Collaborative Uncertainty Quantification
  140. Policy-Aware Generative AI for Safe, Auditable Data Access Governance
  141. BBOPlace-Bench: Benchmarking Black-Box Optimization for Chip Placement
  142. Robust Decision Making with Partially Calibrated Forecasts
  143. Towards Fair Graph Prompting: A Dual-Prompt Mechanism for Mitigating Attribute and Structural Bias
  144. Evaluating Large Language Models for Stance Detection on Financial Targets from SEC Filing Reports and Earnings Call Transcripts
  145. Differential Privacy as a Perk: Federated Learning over Multiple-Access Fading Channels with a Multi-Antenna Base Station
  146. SGFusion: Stochastic Geographic Gradient Fusion in Federated Learning
  147. What are the odds? Risk and uncertainty about AI existential risk
  148. Schrodinger Neural Network and Uncertainty Quantification: Quantum Machine
  149. FRBNet: Revisiting Low-Light Vision through Frequency-Domain Radial Basis Network
  150. A Neuro-Symbolic Multi-Agent Approach to Legal-Cybersecurity Knowledge Integration
  151. CURVETE: Curriculum Learning and Progressive Self-supervised Training for Medical Image Classification
  152. Coresets for Clustering Under Stochastic Noise
  153. MiCADangelo: Fine-Grained Reconstruction of Constrained CAD Models from 3D Scans
  154. Improving Predictions of Molecular Properties with Graph Featurisation and Heterogeneous Ensemble Models
  155. PrivacyGuard: A Modular Framework for Privacy Auditing in Machine Learning
  156. Quantifying Systemic Vulnerability in the Foundation Model Industry
  157. Quality-controlled registration of urban MLS point clouds reducing drift effects by adaptive fragmentation
  158. Towards Generalisable Foundation Models for Brain MRI
  159. Symmetria: A Synthetic Dataset for Learning in Point Clouds
  160. Bid2X: Revealing Dynamics of Bidding Environment in Online Advertising from A Foundation Model Lens
  161. Eigen-Value: Efficient Domain-Robust Data Valuation via Eigenvalue-Based Approach
  162. AutoStreamPipe: LLM Assisted Automatic Generation of Data Stream Processing Pipelines
  163. Color and Frequency Correction for Image Colorization
  164. Detecting Religious Language in Climate Discourse
  165. The Best of N Worlds: Aligning Reinforcement Learning with Best-of-N Sampling via max@k Optimisation
  166. Floating-Point Neural Network Verification at the Software Level
  167. Opinion Mining Based Entity Ranking using Fuzzy Logic Algorithmic Approach
  168. Symbolic Neural Generation with Applications to Lead Discovery in Drug Design
  169. Towards a Generalizable AI for Materials Discovery: Validation through Immersion Coolant Screening
  170. PlanarTrack: A high-quality and challenging benchmark for large-scale planar object tracking
  171. ZeroFlood: Flood Hazard Mapping from Single-Modality SAR Using Geo-Foundation Models
  172. Interpretable Tile-Based Classification of Paclitaxel Exposure
  173. Robust Non-negative Proximal Gradient Algorithm for Inverse Problems
  174. How AI Forecasts AI Jobs: Benchmarking LLM Predictions of Labor Market Changes
  175. Macroeconomic Forecasting for the G7 countries under Uncertainty Shocks
  176. Block-Diagonal LoRA for Eliminating Communication Overhead in Tensor Parallel LoRA Serving
  177. LightKGG: Simple and Efficient Knowledge Graph Generation from Textual Data
  178. Planning Ahead with RSA: Efficient Signalling in Dynamic Environments by Projecting User Awareness across Future Timesteps
  179. The First Star-by-star N-body/Hydrodynamics Simulation of Our Galaxy Coupling with a Surrogate Model
  180. GRAD: Real-Time Gated Recurrent Anomaly Detection in Autonomous Vehicle Sensors Using Reinforced EMA and Multi-Stage Sliding Window Techniques
  181. Multitask Multimodal Self-Supervised Learning for Medical Images
  182. LibriConvo: Simulating Conversations from Read Literature for ASR and Diarization
  183. Arabic Little STT: Arabic Children Speech Recognition Dataset
  184. ReconViaGen: Towards Accurate Multi-view 3D Object Reconstruction via Generation
  185. MDReID: Modality-Decoupled Learning for Any-to-Any Multi-Modal Object Re-Identification
  186. MMSD3.0: A Multi-Image Benchmark for Real-World Multimodal Sarcasm Detection
  187. Predicting symbolic ODEs from multiple trajectories
  188. Learning from Frustration: Torsor CNNs on Graphs
  189. DCMM-SQL: Automated Data-Centric Pipeline and Multi-Model Collaboration Training for Text-to-SQL Model
  190. hYOLO Model: Enhancing Object Classification with Hierarchical Context in YOLOv8
  191. A Cocktail-Party Benchmark: Multi-Modal dataset and Comparative Evaluation Results
  192. A Novel Framework for Multi-Modal Protein Representation Learning
  193. Mubeen AI: A Specialized Arabic Language Model for Heritage Preservation and User Intent Understanding
  194. Toward Interpretable Evaluation Measures for Time Series Segmentation
  195. GCAO: Group-driven Clustering via Gravitational Attraction and Optimization
  196. Optimal In-context Adaptivity and Distributional Robustness of Transformers
  197. Are ASR foundation models generalized enough to capture features of regional dialects for low-resource languages?
  198. Progressive Growing of Patch Size: Curriculum Learning for Accelerated and Improved Medical Image Segmentation
  199. Autoregressive Styled Text Image Generation, but Make it Reliable
  200. Robust Iterative Learning Hidden Quantum Markov Models
  201. Grassmanian Interpolation of Low-Pass Graph Filters: Theory and Applications
  202. Through the Lens: Benchmarking Deepfake Detectors Against Moir'e-Induced Distortions
  203. Accurate and Scalable Multimodal Pathology Retrieval via Attentive Vision-Language Alignment
  204. Accelerating IC Thermal Simulation Data Generation via Block Krylov and Operator Action
  205. Accelerating Eigenvalue Dataset Generation via Chebyshev Subspace Filter
  206. AUPO -- Abstracted Until Proven Otherwise: A Reward Distribution Based Abstraction Algorithm
  207. Increasing LLM Coding Capabilities through Diverse Synthetic Coding Tasks
  208. DecoDINO: 3D Human-Scene Contact Prediction with Semantic Classification
  209. Rate-optimal Design for Anytime Best Arm Identification
  210. PTPP-Aware Adaptation Scaling Laws: Predicting Domain-Adaptation Performance at Unseen Pre-Training Budgets
  211. Model-free filtering in high dimensions via projection and score-based diffusions
  212. The Benchmarking Epistemology: Validity Theory for Evaluating Machine Learning Models
  213. Evaluation of Vision-LLMs in Surveillance Video
  214. DREaM: Drug-Drug Relation Extraction via Transfer Learning Method
  215. Finding 3D Scene Analogies with Multimodal Foundation Models
  216. SI-Bench: Benchmarking Social Intelligence of Large Language Models in Human-to-Human Conversations
  217. TARC: Time-Adaptive Robotic Control
  218. Benchmarking VQE Configurations: Architectures, Initializations, and Optimizers for Silicon Ground State Energy
  219. MATCH: Task-Driven Code Evaluation through Contrastive Learning
  220. Beyond Direct Generation: A Decomposed Approach to Well-Crafted Screenwriting with LLMs
  221. Reclaiming Low-Quality Instruction Data with Rule-Guided LLM Reconstruction
  222. Enabling Vibration-Based Gesture Recognition on Everyday Furniture via Energy-Efficient FPGA Implementation of 1D Convolutional Networks
  223. AG-Fusion: adaptive gated multimodal fusion for 3d object detection in complex scenes
  224. Revisiting the Structure of Trend Premia: When Diversification Hides Redundancy
  225. Complexity Dependent Error Rates for Physics-informed Statistical Learning via the Small-ball Method
  226. Implicit Modeling for Transferability Estimation of Vision Foundation Models
  227. DQ3D: Depth-guided Query for Transformer-Based 3D Object Detection in Traffic Scenarios
  228. Rethinking GSPO: The Perplexity-Entropy Equivalence
  229. Treble10: A high-quality dataset for far-field speech recognition, dereverberation, and enhancement
  230. Fast Voxel-Wise Kinetic Modeling in Dynamic PET using a Physics-Informed CycleGAN
  231. Note on the Construction of Structure Tensor
  232. A method for outlier detection based on cluster analysis and visual expert criteria
  233. Corpus Frequencies in Morphological Inflection: Do They Matter?
  234. Lost in Tokenization: Context as the Key to Unlocking Biomolecular Understanding in Scientific LLMs
  235. DeepSalt: Bridging Laboratory and Satellite Spectra through Domain Adaptation and Knowledge Distillation for Large-Scale Soil Salinity Estimation
  236. Beyond Higher Rank: Token-wise Input-Output Projections for Efficient Low-Rank Adaptation
  237. Quantizing Space and Time: Fusing Time Series and Images for Earth Observation
  238. Seeing Structural Failure Before it Happens: An Image-Based Physics-Informed Neural Network (PINN) for Spaghetti Bridge Load Prediction
  239. Residual Diffusion Bridge Model for Image Restoration
  240. Flexing in 73 Languages: A Single Small Model for Multilingual Inflection
  241. GroupSHAP-Guided Integration of Financial News Keywords and Technical Indicators for Stock Price Prediction
  242. Neural Emulator Superiority: When Machine Learning for PDEs Surpasses its Training Data
  243. Sampling from Energy distributions with Target Concrete Score Identity
  244. Leveraging Hierarchical Organization for Medical Multi-document Summarization
  245. MAP4TS: A Multi-Aspect Prompting Framework for Time-Series Forecasting with Large Language Models
  246. EndoWave: 4D Gaussian Splatting with Rational Wavelet for Endoscopic Reconstruction
  247. A Survey on LLM Mid-Training
  248. Strategies for Robust Deep Learning Based Deformable Registration
  249. TLCD: A Deep Transfer Learning Framework for Cross-Disciplinary Cognitive Diagnosis
  250. Seq-DeepIPC: Sequential Sensing for End-to-End Control in Legged Robot Navigation
  251. AirFed: A Federated Graph-Enhanced Multi-Agent Reinforcement Learning Framework for Multi-UAV Cooperative Mobile Edge Computing
  252. Knocking-Heads Attention
  253. SwiftTS: A Swift Selection Framework for Time Series Pre-trained Models via Multi-task Meta-Learning
  254. A Survey of AI Scientists
  255. Sublinear Sketches for Approximate Nearest Neighbor and Kernel Density Estimation
  256. A high-capacity linguistic steganography based on entropy-driven rank-token mapping
  257. Efficient and Encrypted Inference using Binarized Neural Networks within In-Memory Computing Architectures
  258. Mixed-Density Diffuser: Efficient Planning with Non-Uniform Temporal Resolution
  259. UniAIDet: A Unified and Universal Benchmark for AI-Generated Image Content Detection and Localization
  260. M3T2IBench: A Large-Scale Multi-Category, Multi-Instance, Multi-Relation Text-to-Image Benchmark
  261. Sentinel: Dynamic Knowledge Distillation for Personalized Federated Intrusion Detection in Heterogeneous IoT Networks
  262. Softmax is 1/2-Lipschitz: A tight bound across all ℓp norms
  263. LangLingual: A Personalised, Exercise-oriented English Language Learning Tool Leveraging Large Language Models
  264. UGAE: Unified Geometry and Attribute Enhancement for G-PCC Compressed Point Clouds
  265. From Prompt Optimization to Multi-Dimensional Credibility Evaluation: Enhancing Trustworthiness of Chinese LLM-Generated Liver MRI Reports -- with Preliminary Extension to Lung Cancer
  266. CoMo: Compositional Motion Customization for Text-to-Video Generation
  267. Understanding In-Context Learning Beyond Transformers: An Investigation of State Space and Hybrid Architectures
  268. An Intelligent Water-Saving Irrigation System Based on Multi-Sensor Fusion and Visual Servoing Control
  269. ProfileXAI: User-Adaptive Explainable AI
  270. LoMix: Learnable Weighted Multi-Scale Logits Mixing for Medical Image Segmentation
  271. SceneDecorator: Towards Scene-Oriented Story Generation with Scene Planning and Scene Consistency
  272. Can Language Models Compose Skills In-Context?
  273. Adaptive Forests For Classification
  274. USF-MAE: Ultrasound Self-Supervised Foundation Model with Masked Autoencoding
  275. Equivariant Neural Networks for General Linear Symmetries on Lie Algebras
  276. QoSGMAA: A Robust Multi-Order Graph Attention and Adversarial Framework for Sparse QoS Prediction
  277. How Muon's Spectral Design Benefits Generalization: A Study on Imbalanced Data
  278. Analysis of accuracy and efficiency of neural networks to simulate Navier-Stokes fluid flows with obstacles
  279. VoMP: Predicting Volumetric Mechanical Property Fields
  280. Scaling Up Occupancy-centric Driving Scene Generation: Dataset and Method
  281. Measuring Teaching with LLMs
  282. Survey of Multimodal Geospatial Foundation Models: Techniques, Applications, and Challenges
  283. FAME: Fairness-aware Attention-modulated Video Editing
  284. Tagging-Augmented Generation: Assisting Language Models in Finding Intricate Knowledge In Long Contexts
  285. SARNet: A Spike-Aware consecutive validation Framework for Accurate Remaining Useful Life Prediction
  286. Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)
  287. Manifold Approximation leads to Robust Kernel Alignment
  288. Hankel Singular Value Regularization for Highly Compressible State Space Models
  289. PASS-Enhanced MEC: Joint Optimization of Task Offloading and Uplink PASS Beamforming
  290. LightFusion: A Light-weighted, Double Fusion Framework for Unified Multimodal Understanding and Generation
  291. Is Your Prompt Poisoning Code? Defect Induction Rates and Security Mitigation Strategies
  292. Switchable Token-Specific Codebook Quantization For Face Image Compression
  293. Hazard-Responsive Digital Twin for Climate-Driven Urban Resilience and Equity
  294. AQCat25: Unlocking spin-aware, high-fidelity machine learning potentials for heterogeneous catalysis
  295. Bi-Encoder Contrastive Learning for Fingerprint and Iris Biometrics
  296. Gen-LangSplat: Generalized Language Gaussian Splatting with Pre-Trained Feature Compression
  297. HyPerNav: Hybrid Perception for Object-Oriented Navigation in Unknown Environment
  298. Estimating Pasture Biomass from Top-View Images: A Dataset for Precision Agriculture
  299. Clinic-Oriented Feasibility of a Sensor-Fused Wearable for Upper-Limb Function
  300. Towards Personalized Treatment Plan: Geometrical Model-Agnostic Approach to Counterfactual Explanations
  301. Modeling Political Discourse with Sentence-BERT and BERTopic
  302. Charting the Design Space of Neural Graph Representations for Subgraph Matching
  303. Transforming volcanic monitoring: A dataset and benchmark for onboard volcano activity detection
  304. AI based signage classification for linguistic landscape studies
  305. Exploring Structures of Inferential Mechanisms through Simplistic Digital Circuits
  306. Learning Reconfigurable Representations for Multimodal Federated Learning with Missing Data
  307. Limits of Generative Pre-Training in Structured EMR Trajectories with Irregular Sampling