mlsanityData to 14 Oct 2026

Papers

New on arXiv

Mon 16 Jun 2025

423 papers

  1. From General Reasoning to Domain Expertise: Uncovering the Limits of Generalization in Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  2. SRKD: Towards Efficient 3D Point Cloud Segmentation via Structure- and Relation-aware Knowledge DistillationKnowledge distillation → Detection and dense prediction distillation
  3. EchoShot: Multi-Shot Portrait Video GenerationDiffusion models → Audio, speech and music
  4. Implicit Constraint-Aware Off-Policy Correction for Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
  5. Discovering Temporal Structure: An Overview of Hierarchical Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  6. An Interdisciplinary Review of Commonsense Reasoning and Intent DetectionLLM reasoning → Reasoning benchmarks and evaluation
  7. Load Balancing Mixture of Experts with Similarity Preserving RoutersMixture-of-experts → Expert routing strategies
  8. Bures-Wasserstein Flow Matching for Graph GenerationDiffusion models → Flow matching, time series and science
  9. Disentangling 3D from Large Vision-Language Models for Controlled Portrait GenerationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  10. GRaD-Nav++: Vision-Language Model Enabled Visual Drone Navigation with Gaussian Radiance Fields and Differentiable DynamicsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  11. Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model OutputsLLM safety and security → Machine unlearning
  12. Taming Polysemanticity in LLMs: Provable Feature Recovery via Sparse AutoencodersMechanistic interpretability → SAE features and their applications
  13. Membership Inference Attacks as Privacy Tools: Reliability, Disparity and EnsembleLLM safety and security → Membership inference attacks
  14. Comparison of ConvNeXt and Vision-Language Models for Breast Density Assessment in Screening MammographyMultimodal LLMs / vision-language models → Medical vision-language models
  15. Toward Explainable Offline RL: Analyzing Representations in Intrinsically Motivated Decision TransformersOffline RL and imitation learning from data → Decision transformers and sequence modeling
  16. ReinDSplit: Reinforced Dynamic Split Learning for Pest Recognition in Precision AgricultureDeep reinforcement learning methods → RL for energy, networks and operations
  17. Code Reasoning for Software Engineering Tasks: A Survey and A Call to ActionLLM reasoning → Reasoning for agents, planning and code
  18. Segmenting Visuals With Querying Words: Language Anchors For Semi-Supervised Image SegmentationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  19. Adaptive Guidance Accelerates Reinforcement Learning of Reasoning ModelsLLM reasoning → Reinforcement learning for reasoning
  20. DynaGuide: Steering Diffusion Polices with Active Dynamic GuidanceDiffusion models → Diffusion and flow policies for robotics
  21. Alignment Quality Index (AQI) : Beyond Refusals: AQI as an Intrinsic Alignment Diagnostic via Latent Geometry, Cluster Divergence, and Layer wise Pooled RepresentationsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods +1
  22. Scaling Algorithm Distillation for Continuous Control with MambaState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models +1
  23. Investigating the interaction of linguistic and mathematical reasoning in language models using multilingual number puzzlesLLM reasoning → Mathematical reasoning
  24. StaQ: a Finite Memory Approach to Discrete Action Policy Mirror DescentDeep reinforcement learning methods → RL theory and sample complexity
  25. Fake it till You Make it: Reward Modeling as Discriminative PredictionLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment +1
  26. LocationReasoner: Evaluating LLMs on Real-World Site Selection ReasoningLLM reasoning → Spatial and embodied reasoning
  27. Robustness of Reinforcement Learning-Based Traffic Signal Control under Incidents: A Comparative StudyDeep reinforcement learning methods → RL for autonomous driving and traffic
  28. A Survey on World Models Grounded in Acoustic Physical InformationWorld models → Latent predictive world models
  29. Diagnosing and Improving Diffusion Models by Estimating the Optimal Loss ValueDiffusion models → Diffusion foundations and sampling
  30. Touch begins where vision ends: Generalizable policies for contact-rich manipulationOffline RL and imitation learning from data → Robot manipulation imitation learning +1
  31. Prompting with the Future: Open-World Model Predictive Control with Interactive Digital TwinsWorld models → Embodied and robot world models +1
  32. Discrete Diffusion in Large Language and Multimodal Models: A SurveyMultimodal LLMs / vision-language models → Image editing and quality assessment +1
  33. AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-TuningLLM reasoning → Chain-of-thought reasoning for driving +2
  34. VideoPDE: Unified Generative PDE Solving via Video Inpainting Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  35. Steering LLM Thinking with Budget GuidanceLLM reasoning → Test-time compute and efficient thinking
  36. LeVERB: Humanoid Whole-Body Control with Latent Vision-Language InstructionVision-language-action models → Tactile, force-aware and humanoid VLA
  37. Evaluating Large Language Models for Phishing Detection, Self-Consistency, Faithfulness, and ExplainabilityLLM reasoning → Reasoning for agents, planning and code
  38. PB2: Preference Space Exploration via Population-Based Methods in Preference-Based Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  39. Attribution-Guided Pruning for Insight and Control: Circuit Discovery and Targeted Correction in Small-scale LLMsMechanistic interpretability → Circuits and mechanistic analysis
  40. Weakest Link in the Chain: Security Vulnerabilities in Advanced Reasoning ModelsLLM reasoning → Reasoning for agents, planning and code
  41. CEED-VLA: Consistency Vision-Language-Action Model with Early-Exit DecodingVision-language-action models → Efficient VLA inference and adaptation
  42. Sharpness-Aware Machine UnlearningLLM safety and security → Machine unlearning
  43. TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement LearningLLM reasoning → Time series reasoning +1
  44. Value-Free Policy Optimization via Reward PartitioningLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  45. Meta-learning how to Share Credit among Macro-ActionsDeep reinforcement learning methods → Deep RL algorithms and representations
  46. ROSA: Harnessing Robot States for Vision-Language and Action AlignmentMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  47. The Courage to Stop: Overcoming Sunk Cost Fallacy in Deep Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  48. MultiViT2: A Data-augmented Multimodal Neuroimaging Prediction Framework via Latent Diffusion ModelDiffusion models → Medical imaging and segmentation
  49. We Should Identify and Mitigate Third-Party Safety Risks in MCP-Powered Agent SystemsLLM agents and tool use → Agent threats, guardrails and governance +1
  50. Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video ReasoningLLM reasoning → Spatial and embodied reasoning
  51. Stream-Omni: Simultaneous Multimodal Interactions with Large Language-Vision-Speech ModelMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  52. DualEdit: Dual Editing for Knowledge Updating in Vision-Language ModelsMultimodal LLMs / vision-language models → Image editing and quality assessment
  53. Exploiting the Exact Denoising Posterior Score in Training-Free Guidance of Diffusion ModelsDiffusion models → Inverse problems and image restoration
  54. Tree-Based Text Retrieval via Hierarchical Clustering in RAGFrameworks: Application on Taiwanese RegulationsRetrieval-augmented generation → Legal and financial RAG
  55. CAMS: A CityGPT-Powered Agentic Framework for Urban Human Mobility SimulationLLM agents and tool use → Multimodal and embodied agents
  56. Dive3D: Diverse Distillation-based Text-to-3D Generation via Score Implicit MatchingDiffusion models → 3D, point cloud and scene generation
  57. AdaVideoRAG: Omni-Contextual Adaptive Retrieval-Augmented Efficient Long Video UnderstandingMultimodal LLMs / vision-language models → Video understanding with MLLMs +1
  58. MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning AttentionLLM reasoning → Test-time compute and efficient thinking +1
  59. Can you see how I learn? Human observers' inferences about Reinforcement Learning agents' learning processesDeep reinforcement learning methods → Interpretable and logic-guided RL
  60. Flexible-length Text Infilling for Discrete Diffusion ModelsDiffusion models → Discrete and text diffusion
  61. A Production Scheduling Framework for Reinforcement Learning Under Real-World ConstraintsDeep reinforcement learning methods → RL for energy, networks and operations
  62. State-Space Hierarchical Compression with Gated Attention and Learnable Sampling for Hour-Long Video Understanding in Large Multimodal ModelsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  63. Understand the Implication: Learning to Think for Pragmatic UnderstandingLLM reasoning → Reasoning benchmarks and evaluation
  64. X-Scene: Large-Scale Driving Scene Generation with High Fidelity and Flexible ControllabilityDiffusion models → Diffusion and flow policies for robotics +1
  65. Geometry-Guided Representations for Coherent Lane and Traffic Topology Reasoning in Driving ScenesEnd-to-end autonomous driving → VLMs for autonomous driving
  66. Limited-Angle CBCT Reconstruction via Geometry-Integrated Cycle-domain Denoising Diffusion Probabilistic ModelsDiffusion models → Medical imaging and segmentation
  67. Mixture of Weight-shared Heterogeneous Group Attention Experts for Dynamic Token-wise KV OptimizationMixture-of-experts → Expert routing strategies
  68. What Matters in Learning from Large-Scale Datasets for Robot ManipulationOffline RL and imitation learning from data → Robot manipulation imitation learning
  69. Seismic Acoustic Impedance Inversion Framework Based on Conditional Latent Generative Diffusion ModelDiffusion models → Flow matching, time series and science
  70. Safe-Child-LLM: A Developmental Benchmark for Evaluating LLM Safety in Child-LLM InteractionsLLM safety and security → Safety alignment, refusal and guardrails
  71. BOW: Training Language Models to Reason Over Plausible Next WordsLLM reasoning → Test-time compute and efficient thinking
  72. A Survey on Imitation Learning for Contact-Rich Tasks in RoboticsOffline RL and imitation learning from data → Robot manipulation imitation learning
  73. Watermarking LLM-Generated Datasets in Downstream TasksLLM safety and security → Watermarking generated content and models
  74. Deep Diffusion Models and Unsupervised Hyperspectral Unmixing for Realistic Abundance Map SynthesisDiffusion models → Inverse problems and image restoration
  75. Learning Swing-up Maneuvers for a Suspended Aerial Manipulation Platform in a Hierarchical Control FrameworkDeep reinforcement learning methods → RL for robot navigation and UAV control
  76. Language Agents for Hypothesis-driven Clinical Decision Making with Reinforcement LearningLLM agents and tool use → Medical and scientific domain agents +1
  77. Induce, Align, Predict: Zero-Shot Stance Detection via Cognitive Inductive ReasoningLLM reasoning → Causal reasoning in LLMs
  78. Leveraging Vision-Language Pre-training for Human Activity Recognition in Still ImagesMultimodal LLMs / vision-language models → Video understanding with MLLMs
  79. Block-wise Adaptive Caching for Accelerating Diffusion PolicyDiffusion models → Diffusion foundations and sampling
  80. Effective Learning for Small Reasoning Models: An Empirical Study on 0.5B Reasoning LLMsLLM reasoning → Reasoning benchmarks and evaluation
  81. Zero-Shot Solving of Imaging Inverse Problems via Noise-Refined Likelihood Guided Diffusion ModelsDiffusion models → Inverse problems and image restoration
  82. Uncertainty-Informed Active Perception for Open Vocabulary Object Goal NavigationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  83. Efficient Medical VIE via Reinforcement LearningDeep reinforcement learning methods → RL for clinical treatment and surgery
  84. Socratic RL: A Novel Framework for Efficient Knowledge Acquisition through Iterative Reflection and Viewpoint DistillationKnowledge distillation → On-policy and self-distillation for LLMs
  85. Direct Reasoning Optimization: Token-Level Reasoning Reflectivity Meets Rubric Gates for Unverifiable TasksLLM reasoning → Reinforcement learning for reasoning
  86. Learning to Explore in Diverse Reward Settings via Temporal-Difference-Error MaximizationDeep reinforcement learning methods → Deep RL algorithms and representations
  87. LapDDPM: A Conditional Graph Diffusion Model for scRNA-seq Generation with Spectral Adversarial PerturbationsDiffusion models → Flow matching, time series and science
  88. Mixture of Cognitive Reasoners: Modular Reasoning with Brain-Like SpecializationLLM reasoning → Reasoning benchmarks and evaluation
  89. EAQuant: Enhancing Post-Training Quantization for MoE Models via Expert-Aware OptimizationMixture-of-experts → MoE large language models
  90. Towards Pervasive Distributed Agentic Generative AI -- A State of The ArtLLM agents and tool use → General LLM agent frameworks and benchmarks
  91. Quantitative Comparison of Fine-Tuning Techniques for Pretrained Latent Diffusion Models in the Generation of Unseen SAR ImagesDiffusion models → Inverse problems and image restoration
  92. AttentionDrag: Exploiting Latent Correlation Knowledge in Pre-trained Diffusion Models for Image EditingDiffusion models → Image generation, text-to-image and editing
  93. Seewo's Submission to MLC-SLM: Lessons learned from Speech Reasoning Language ModelsLLM reasoning → Audio-language model reasoning
  94. Fair Generation without Unfair Distortions: Debiasing Text-to-Image Generation with Entanglement-Free AttentionDiffusion models → Image generation, text-to-image and editing
  95. DualEdit: Mitigating Safety Fallback in LLM Backdoor Editing via Affirmation-Refusal RegulationLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  96. AceReason-Nemotron 1.1: Advancing Math and Code Reasoning through SFT and RL SynergyLLM reasoning → Reinforcement learning for reasoning
  97. COME: Adding Scene-Centric Forecasting Control to Occupancy World ModelWorld models → World models for autonomous driving
  98. Research on Optimal Control Problem Based on Reinforcement Learning under Knightian UncertaintyDeep reinforcement learning methods → RL theory and sample complexity
  99. Thought Crime: Backdoors and Emergent Misalignment in Reasoning ModelsLLM reasoning → Reasoning for agents, planning and code +1
  100. Poison Once, Control Anywhere: Clean-Text Visual Backdoors in VLM-based Mobile AgentsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +2
All 423
  1. Breaking Thought Patterns: A Multi-Dimensional Reasoning Framework for LLMsLLM reasoning → Prompting and chain-of-thought reasoning +1
  2. MT-PCR: Hybrid Mamba-Transformer Network with Spatial Serialization for Point Cloud RegistrationState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  3. Align-then-Unlearn: Embedding Alignment for LLM UnlearningLLM safety and security → Machine unlearning
  4. AI-Facilitated Analysis of Abstracts and Conclusions: Flagging Unsubstantiated Claims and Ambiguous PronounsLLM reasoning → Knowledge- and tool-augmented reasoning
  5. Querying Large Automotive Software Models: Agentic vs. Direct LLM ApproachesLLM agents and tool use → Software engineering coding agents
  6. GreedyPrune: Retenting Critical Visual Token Set for Large Vision Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  7. CertDW: Towards Certified Dataset Ownership Verification via Conformal CalibrationLLM safety and security → Watermarking generated content and models
  8. Dynamic Preference Multi-Objective Reinforcement Learning for Internet Network ManagementDeep reinforcement learning methods → RL for games and combinatorial optimization
  9. STAGE: A Stream-Centric Generative World Model for Long-Horizon Driving-Scene SimulationWorld models → World models for autonomous driving +1
  10. AlphaEvolve: A coding agent for scientific and algorithmic discoveryLLM agents and tool use → Software engineering coding agents
  11. ZINA: Multimodal Fine-grained Hallucination Detection and EditingMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  12. Leveraging Local and Global Knowledge Integration with Time-Frequency Calibrated Distillation for Speech EnhancementKnowledge distillation → Speech and audio distillation
  13. Overcoming Overfitting in Reinforcement Learning via Gaussian Process Diffusion PolicyDiffusion models → Diffusion and flow policies for robotics +1
  14. Leveraging In-Context Learning for Language Model AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  15. Rethinking Test-Time Scaling for Medical AI: Model and Task-Aware Strategies for LLMs and VLMsLLM reasoning → Clinical and biomedical applications +1
  16. IKDiffuser: a Diffusion-based Generative Inverse Kinematics Solver for Kinematic TreesDiffusion models → Diffusion and flow policies for robotics
  17. CHARM: Considering Human Attributes for Reinforcement ModelingLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  18. Towards the Autonomous Optimization of Urban Logistics: Training Generative AI with Scientific Tools via Agentic Digital Twins and Model Context ProtocolLLM agents and tool use → General LLM agent frameworks and benchmarks
  19. FinLMM-R1: Enhancing Financial Reasoning in LMM through Scalable Data and Reward DesignLLM reasoning → Reasoning for agents, planning and code +1
  20. MotiveBench: How Far Are We From Human-Like Motivational Reasoning in Large Language Models?LLM reasoning → Reasoning benchmarks and evaluation
  21. Fast Convergence for High-Order ODE Solvers in Diffusion Probabilistic ModelsDiffusion models → Diffusion foundations and sampling
  22. Multipole Attention for Efficient Long Context ReasoningLLM reasoning → Test-time compute and efficient thinking
  23. SynBoost: A Synergistic Framework for Fast Sampling of Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  24. Inverse design of the transmission matrix in a random system using Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  25. Metis-RISE: RL Incentivizes and SFT Enhances Multimodal Reasoning Model LearningLLM reasoning → Multimodal reasoning +1
  26. CFBenchmark-MM: Chinese Financial Assistant Benchmark for Multimodal Large Language ModelMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  27. ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow MatchingDiffusion models → Audio, speech and music
  28. The Space Complexity of Learning-Unlearning AlgorithmsLLM safety and security → Machine unlearning
  29. HKD4VLM: A Progressive Hybrid Knowledge Distillation Framework for Robust Multimodal Hallucination and Factuality Detection in VLMsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs +1
  30. MAGIC: Multi-Agent Argumentation and Grammar Integrated CritiquerLLM agents and tool use → General LLM agent frameworks and benchmarks
  31. NaSh: Guardrails for an LLM-Powered Natural Language ShellLLM safety and security → Safety alignment, refusal and guardrails
  32. Rectifying Privacy and Efficacy Measurements in Machine Unlearning: A New Inference Attack PerspectiveLLM safety and security → Machine unlearning
  33. Evaluating LLMs for Visualization Generation and Understanding
  34. Empathy in Explanation
  35. Which symbol grounding problem should we try to solve?
  36. Using Large Language Models to Study Mathematical Practice
  37. Hello Afrika: Speech Commands in Kinyarwanda
  38. GLU Attention Improve Transformer
  39. Variational Autoencoder for Generating Broader-Spectrum prior Proposals in Markov chain Monte Carlo Methods
  40. A Complex UNet Approach for Non-Invasive Fetal ECG Extraction Using Single-Channel Dry Textile Electrodes
  41. Evaluating the Robustness of Dense Retrievers in Interdisciplinary Domains
  42. LLM2Rec: Large Language Models Are Powerful Embedding Models for Sequential Recommendation
  43. HealthQA-BR: A System-Wide Benchmark Reveals Critical Knowledge Gaps in Large Language Models
  44. Language-Aware Prompt Tuning for Parameter-Efficient Seamless Language Expansion in Multilingual ASR
  45. Adapting Whisper for Parameter-efficient Code-Switching Speech Recognition via Soft Prompt Tuning
  46. Signal Use and Emergent Cooperation
  47. Theoretically Unmasking Inference Attacks Against LDP-Protected Clients in Federated Vision Models
  48. Evaluating Generalization and Representation Stability in Small LMs via Prompting, Fine-Tuning and Out-of-Distribution Prompts
  49. ADAM-Dehaze: Adaptive Density-Aware Multi-Stage Dehazing for Improved Object Detection in Foggy Conditions
  50. MoNetV2: Enhanced Motion Network for Freehand 3D Ultrasound Reconstruction
  51. Finding Optimal Kernel Size and Dimension in Convolutional Neural Networks An Architecture Optimization Approach
  52. Improving Prostate Gland Segmentation Using Transformer based Architectures
  53. CACTUS as a Reliable Tool for Early Classification of Age-related Macular Degeneration
  54. PictSure: Pretraining Embeddings Matters for In-Context Learning Image Classifiers
  55. Online Conformal Abstention Under Adversarial Bandit Feedback
  56. Automatic Extraction of Clausal Embedding Based on Large-Scale English Text Data
  57. Scientifically-Interpretable Reasoning Network (ScIReN): Discovering Hidden Relationships in the Carbon Cycle and Beyond
  58. Estimation of Treatment Effects in Extreme and Unobserved Data
  59. Ace-CEFR -- A Dataset for Automated Evaluation of the Linguistic Difficulty of Conversational Texts for LLM Applications
  60. Asymptotically Smaller Encodings for Graph Problems and Scheduling
  61. Robust Physics-Informed Neural Network Approach for Estimating Heterogeneous Elastic Properties from Noisy Displacement Data
  62. SimpleDoc: Multi-Modal Document Understanding with Dual-Cue Page Retrieval and Iterative Refinement
  63. Sketched Sum-Product Networks for Joins
  64. MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application
  65. AI-informed model-analogs for understanding subseasonal-to-seasonal jet stream and North American temperature predictability
  66. Causal Mediation Analysis with Multiple Mediators: A Simulation Approach
  67. Lost in the Mix: Evaluating LLM Understanding of Code-Switched Text
  68. FindMeIfYouCan: Bringing Open Set metrics to textitnear , textitfar and textitfarther Out-of-Distribution Object Detection
  69. Evolutionary chemical learning in dimerization networks
  70. Arctic Long Sequence Training: Scalable And Efficient Training For Multi-Million Token Sequences
  71. Mapping Farmed Landscapes from Remote Sensing
  72. Quantum-Informed Contrastive Learning with Dynamic Mixup Augmentation for Class-Imbalanced Expert Systems
  73. ProfiLLM: An LLM-Based Framework for Implicit Profiling of Chatbot Users
  74. Constant Stepsize Local GD for Logistic Regression: Acceleration by Instability
  75. Are manual annotations necessary for statutory interpretations retrieval?
  76. Projecting U.S. coastal storm surge risks and impacts with deep learning
  77. Safe Domains of Attraction for Discrete-Time Nonlinear Systems: Characterization and Verifiable Neural Network Estimation
  78. ASMR: Augmenting Life Scenario using Large Generative Models for Robotic Action Reflection
  79. Bridging Unsupervised and Semi-Supervised Anomaly Detection: A Theoretically-Grounded and Practical Framework with Synthetic Anomalies
  80. Invariant Manifolds of Discrete-time Dynamical Systems with Nonlinear Exosystems via Hybrid Physics-Informed Neural Networks
  81. Meta Optimality for Demographic Parity Constrained Regression via Post-Processing
  82. Rademacher learning rates for iterated random functions
  83. Integrating Knowledge Graphs and Bayesian Networks: A Hybrid Approach for Explainable Disease Risk Prediction
  84. Evaluating Explainability: A Framework for Systematic Assessment and Reporting of Explainable AI Features
  85. Branching Stein Variational Gradient Descent for sampling multimodal distributions
  86. Density-aware Walks for Coordinated Campaign Detection
  87. Logical Expressiveness of Graph Neural Networks with Hierarchical Node Individualization
  88. Intelligent Image Sensing for Crime Analysis: A ML Approach towards Enhanced Violence Detection and Investigation
  89. Few-Shot Learning for Industrial Time Series: A Comparative Analysis Using the Example of Screw-Fastening Process Monitoring
  90. GITO: Graph-Informed Transformer Operator for Learning Complex Partial Differential Equations
  91. A Systematic Review of User-Centred Evaluation of Explainable AI in Healthcare
  92. Enhancing interpretability of rule-based classifiers through feature graphs
  93. OPTIMUS: Observing Persistent Transformations in Multi-temporal Unlabeled Satellite-data
  94. Beyond Shapley Values: Cooperative Games for the Interpretation of Machine Learning Models
  95. DeSPITE: Exploring Contrastive Deep Skeleton-Pointcloud-IMU-Text Embeddings for Advanced Point Cloud Human Activity Understanding
  96. EmoNews: A Spoken Dialogue System for Expressive News Conversations
  97. VL-GenRM: Enhancing Vision-Language Verification via Vision Experts and Iterative Training
  98. Connecting phases of matter to the flatness of the loss landscape in analog variational quantum algorithms
  99. Students' Reliance on AI in Higher Education: Identifying Contributing Factors
  100. SatHealth: A Multimodal Public Health Dataset with Satellite-based Environmental Factors
  101. Sustainable Machine Learning Retraining: Optimizing Energy Efficiency Without Compromising Accuracy
  102. A Silent Speech Decoding System from EEG and EMG with Heterogenous Electrode Configurations
  103. Evolvable Conditional Diffusion
  104. FrontendBench: A Benchmark for Evaluating LLMs on Front-End Development via Automatic Evaluation
  105. Quantifying Structure in CLIP Embeddings: A Statistical Framework for Concept Interpretation
  106. LHM++: An Efficient Large Human Reconstruction Model for Pose-free Images to 3D
  107. AI reconstruction of European weather from the Euro-Atlantic regimes
  108. UltraZoom: Generating Gigapixel Images from Regular Photos
  109. MARCO: Hardware-Aware Neural Architecture Search for Edge Devices with Multi-Agent Reinforcement Learning and Conformal Prediction Filtering
  110. Test3R: Learning to Reconstruct 3D at Test Time
  111. LTRR: Learning To Rank Retrievers for LLMs
  112. Instruction Following by Principled Boosting Attention of Large Language Models
  113. BanditWare: A Contextual Bandit-based Framework for Hardware Prediction
  114. SOTA: Self-adaptive Optimal Transport for Zero-Shot Classification with Multiple Foundation Models
  115. How Real is CARLAs Dynamic Vision Sensor? A Study on the Sim-to-Real Gap in Traffic Object Detection
  116. Contrastive Self-Supervised Learning As Neural Manifold Packing
  117. Understanding Learning Invariance in Deep Linear Networks
  118. Understanding Lookahead Dynamics Through Laplace Transform
  119. Gradient-Normalized Smoothness for Optimization with Approximate Hessians
  120. Vid-CamEdit: Video Camera Trajectory Editing with Generative Rendering from Estimated Geometry
  121. Balancing Knowledge Delivery and Emotional Comfort in Healthcare Conversational Systems
  122. UltraVideo: High-Quality UHD Video Dataset with Comprehensive Captions
  123. What Happens During the Loss Plateau? Understanding Abrupt Learning in Transformers
  124. Enforcing tail calibration when training probabilistic forecast models
  125. The Sample Complexity of Distributed Simple Binary Hypothesis Testing under Information Constraints
  126. Gradient Boosting for Spatial Regression Models with Autoregressive Disturbances
  127. Min-p, Max Exaggeration: A Critical Analysis of Min-p Sampling in Language Models
  128. Hybrid Meta-learners for Estimating Heterogeneous Treatment Effects
  129. A Gravity-informed Spatiotemporal Transformer for Human Activity Intensity Prediction
  130. PrefixMemory-Tuning: Modernizing Prefix-Tuning by Decoupling the Prefix from Attention
  131. Adversarial Disentanglement by Backpropagation with Physics-Informed Variational Autoencoder
  132. Lecture Video Visual Objects (LVVO) Dataset: A Benchmark for Visual Object Detection in Educational Videos
  133. PeakWeather: MeteoSwiss Weather Station Measurements for Spatiotemporal Deep Learning
  134. xbench: Tracking Agents Productivity Scaling with Profession-Aligned Real-World Evaluations
  135. EUNIS Habitat Maps: Enhancing Thematic and Spatial Resolution for Europe through Machine Learning
  136. Computational lower bounds in latent models: clustering, sparse-clustering, biclustering
  137. EvolvTrip: Enhancing Literary Character Understanding with Temporal Theory-of-Mind Graphs
  138. An Empirical Study of LLM-as-a-Judge: How Design Choices Impact Evaluation Reliability
  139. Global Convergence of Adjoint-Optimized Neural PDEs
  140. FreeQ-Graph: Free-form Querying with Semantic Consistent Scene Graph for 3D Scene Understanding
  141. Graph-Convolutional-Beta-VAE for Synthetic Abdominal Aorta Aneurysm Generation
  142. Variational Inference with Mixtures of Isotropic Gaussians
  143. EBS-CFL: Efficient and Byzantine-robust Secure Clustered Federated Learning
  144. A Hybrid Artificial Intelligence Method for Estimating Flicker in Power Systems
  145. A Structured Dataset of Disease-Symptom Associations to Improve Diagnostic Accuracy
  146. Avoiding Obfuscation with Prover-Estimator Debate
  147. Assessing the Limits of In-Context Learning beyond Functions using Partially Ordered Relation
  148. The ASP-based Nurse Scheduling System at the University of Yamanashi Hospital
  149. Qwen vs. Gemma Integration with Whisper: A Comparative Study in Multilingual SpeechLLM Systems
  150. Calibrated Predictive Lower Bounds on Time-to-Unsafe-Sampling in LLMs
  151. Agent Capability Negotiation and Binding Protocol (ACNBP)
  152. From Data-Driven to Purpose-Driven Artificial Intelligence: Systems Thinking for Data-Analytic Automation of Patient Care
  153. Machine Learning-Driven Compensation for Non-Ideal Channels in AWG-Based FBG Interrogator
  154. Integrated Pipeline for Monocular 3D Reconstruction and Finite Element Simulation in Industrial Applications
  155. Characterizing Linguistic Shifts in Croatian News via Diachronic Word Embeddings
  156. Perfect Privacy for Discriminator-Based Byzantine-Resilient Federated Learning
  157. Non-Asymptotic Stability and Consistency Guarantees for Physics-Informed Neural Networks via Coercive Operator Analysis
  158. A Comprehensive Survey on Video Scene Parsing:Advances, Challenges, and Prospects
  159. Atomizer: Generalizing to new modalities by breaking satellite images down to a set of scalars
  160. Learning Augmented Graph k-Clustering
  161. The Price of Freedom: Exploring Expressivity and Runtime Tradeoffs in Equivariant Tensor Products
  162. Micro-macro Gaussian Splatting with Enhanced Scalability for Unconstrained Scene Reconstruction
  163. TensorSLM: Energy-efficient Embedding Compression of Sub-billion Parameter Language Models on Low-end Devices
  164. K/DA: Automated Data Generation Pipeline for Detoxifying Implicitly Offensive Language in Korean
  165. A Semantically-Aware Relevance Measure for Content-Based Medical Image Retrieval Evaluation
  166. Multiview Geometric Regularization of Gaussian Splatting for Accurate Radiance Fields
  167. Stimulus Motion Perception Studies Imply Specific Neural Computations in Human Visual Stabilization
  168. UAV Object Detection and Positioning in a Mining Industrial Metaverse with Custom Geo-Referenced Data
  169. FOAM: A General Frequency-Optimized Anti-Overlapping Framework for Overlapping Object Perception
  170. Hierarchical Multi-Positive Contrastive Learning for Patent Image Retrieval
  171. GeoSDF: Plane Geometry Diagram Synthesis via Signed Distance Field
  172. Imaging at the quantum limit with convolutional neural networks
  173. TurBLiMP: A Turkish Benchmark of Linguistic Minimal Pairs
  174. Curriculum Learning for Biological Sequence Prediction: The Case of De Novo Peptide Sequencing
  175. Position: Pause Recycling LoRAs and Prioritize Mechanisms to Uncover Limits and Effectiveness
  176. Multimodal Integration Challenges in Emotionally Expressive Child Avatars for Training Applications
  177. ESRPCB: an Edge guided Super-Resolution model and Ensemble learning for tiny Printed Circuit Board Defect detection
  178. ROSAQ: Rotation-based Saliency-Aware Weight Quantization for Efficiently Compressing Large Language Models
  179. A Two-stage Optimization Method for Wide-range Single-electron Quantum Magnetic Sensing
  180. An Interdisciplinary Approach to Human-Centered Machine Translation
  181. Enhancing Omics Cohort Discovery for Research on Neurodegeneration through Ontology-Augmented Embedding Models
  182. SA-LUT: Spatial Adaptive 4D Look-Up Table for Photorealistic Style Transfer
  183. Unveiling the Learning Mind of Language Models: A Cognitive Framework and Empirical Study
  184. Deep Learning-Based Multi-Object Tracking: A Comprehensive Survey from Foundations to State-of-the-Art
  185. Towards a Formal Specification for Self-organized Shape Formation in Swarm Robotics
  186. In Silico Study for Optimizing Intensity and Focality Electrode Configurations for Directional DBS Under Uncertainty Using Metaheuristic L1L1 Method
  187. A Neural Model for Word Repetition
  188. Overcoming Occlusions in the Wild: A Multi-Task Age Head Approach to Age Estimation
  189. Self-Supervised Enhancement for Depth from a Lightweight ToF Sensor with Monocular Images
  190. PRO: Projection Domain Synthesis for CT Imaging
  191. Sparse Convolutional Recurrent Learning for Efficient Event-based Neuromorphic Object Detection
  192. Uncertainty-Aware Remaining Lifespan Prediction from Images
  193. JENGA: Object selection and pose estimation for robotic grasping from a stack
  194. Audio-Visual Driven Compression for Low-Bitrate Talking Head Videos
  195. Spiking Neural Networks for Low-Power Vibration-Based Predictive Maintenance
  196. Simple is what you need for efficient and accurate medical image segmentation
  197. Training Neural Networks by Optimizing Neuron Positions
  198. HELENA: High-Efficiency Learning-based channel Estimation using dual Neural Attention
  199. CALM: Consensus-Aware Localized Merging for Multi-Task Learning
  200. RealHiTBench: A Comprehensive Realistic Hierarchical Table Benchmark for Evaluating LLM-Based Table Analysis
  201. Deflating Deflationism: A Critical Perspective on Debunking Arguments Against LLM Mentality
  202. Realtime-Capable Hybrid Spiking Neural Networks for Neural Decoding of Cortical Activity
  203. Bi-directional Context-Enhanced Speech Large Language Models for Multilingual Conversational ASR
  204. Experimental Design for Semiparametric Bandits
  205. TR2M: Transferring Monocular Relative Depth to Metric Depth with Language Descriptions and Dual-Level Scale-Oriented Contrast
  206. Delving Into the Psychology of Machines: Exploring the Structure of Self-Regulated Learning via LLM-Generated Survey Responses
  207. The Structure-Content Trade-off in Knowledge Graph Retrieval
  208. Enhancing Goal-oriented Proactive Dialogue Systems via Consistency Reflection and Correction
  209. Mitigating loss of variance in ensemble data assimilation: machine learning-based and distance-free localization
  210. StoryBench: A Dynamic Benchmark for Evaluating Long-Term Memory with Multi Turns
  211. DicFace: Dirichlet-Constrained Variational Codebook Learning for Temporally Coherent Video Face Restoration
  212. TextureSplat: Per-Primitive Texture Mapping for Reflective Gaussian Splatting
  213. Verifying the Verifiers: Unveiling Pitfalls and Potentials in Fact Verifiers
  214. Probabilistic Modeling of Spiking Neural Networks with Contract-Based Verification
  215. NTU Speechlab LLM-Based Multilingual ASR System for Interspeech MLC-SLM Challenge 2025
  216. Advancing Image-Based Grapevine Variety Classification with a New Benchmark and Evaluation of Masked Autoencoders
  217. Document-Level Tabular Numerical Cross-Checking: A Coarse-to-Fine Approach
  218. Joint Analysis of Optical and SAR Vegetation Indices for Vineyard Monitoring: Assessing Biomass Dynamics and Phenological Stages over Po Valley, Italy
  219. VIS-Shepherd: Constructing Critic for LLM-based Data Visualization Generation
  220. Tady: A Neural Disassembler without Structural Constraint Violations
  221. Active Multimodal Distillation for Few-shot Action Recognition
  222. Action Dubber: Timing Audible Actions via Inflectional Flow
  223. Vine Copulas as Differentiable Computational Graphs
  224. Large Language Models as 'Hidden Persuaders': Fake Product Reviews are Indistinguishable to Humans and Machines
  225. Brain Imaging Foundation Models, Are We There Yet? A Systematic Review of Foundation Models for Brain Imaging and Biomedical Research
  226. Automatic Multi-View X-Ray/CT Registration Using Bone Substructure Contours
  227. The impact of uncertainty on regularized learning in games
  228. Anomaly Object Segmentation with Vision-Language Models for Steel Scrap Recycling
  229. SeqPE: Transformer with Sequential Position Encoding
  230. Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks
  231. AdaLRS: Loss-Guided Adaptive Learning Rate Search for Efficient Foundation Model Pretraining
  232. Energy-Efficient Digital Design: A Comparative Study of Event-Driven and Clock-Driven Spiking Neurons
  233. Open-Set LiDAR Panoptic Segmentation Guided by Uncertainty-Aware Learning
  234. An Explainable and Interpretable Composite Indicator Based on Decision Rules
  235. Distinct Computations Emerge From Compositional Curricula in In-Context Learning
  236. Vector Ontologies as an LLM world view extraction method
  237. Generalized Proof-Number Monte-Carlo Tree Search
  238. On Immutable Memory Systems for Artificial Agents: A Blockchain-Indexed Automata-Theoretic Framework Using ECDH-Keyed Merkle Chains
  239. A Game-Theoretic Negotiation Framework for Cross-Cultural Consensus in LLMs
  240. No-Regret Learning Under Adversarial Resource Constraints: A Spending Plan Is All You Need!
  241. Lightweight Task-Oriented Semantic Communication Empowered by Large-Scale AI Models
  242. Restarted contractive operators to learn at equilibrium
  243. The Butterfly Effect: Neural Network Training Trajectories Are Highly Sensitive to Initial Conditions
  244. High-Quality Facial Albedo Generation for 3D Face Reconstruction from a Single Image using a Coarse-to-Fine Approach
  245. IGD: Token Decisiveness Modeling via Information Gain in LLMs for Personalized Recommendation
  246. SASep: Saliency-Aware Structured Separation of Geometry and Feature for Open Set Learning on Point Clouds
  247. Towards Explaining Monte-Carlo Tree Search by Using Its Enhancements
  248. NeuroPhysNet: A FitzHugh-Nagumo-Based Physics-Informed Neural Network Framework for Electroencephalograph (EEG) Analysis and Motor Imagery Classification
  249. Polyra Swarms: A Shape-Based Approach to Machine Learning
  250. Capability Salience Vector: Fine-grained Alignment of Loss and Capabilities for Downstream Task Scaling Law
  251. DVP-MVS++: Synergize Depth-Normal-Edge and Harmonized Visibility Prior for Multi-View Stereo
  252. Bayesian Active Learning of (small) Quantile Sets through Expected Estimator Modification
  253. Fatigue-Aware Adaptive Interfaces for Wearable Devices Using Deep Learning
  254. A Comprehensive Survey on Deep Learning Solutions for 3D Flood Mapping
  255. Do Music Preferences Reflect Cultural Values? A Cross-National Analysis Using Music Embedding and World Values Survey
  256. KEPLA: A Knowledge-Enhanced Deep Learning Framework for Accurate Protein-Ligand Binding Affinity Prediction
  257. ViT-NeBLa: A Hybrid Vision Transformer and Neural Beer-Lambert Framework for Single-View 3D Reconstruction of Oral Anatomy from Panoramic Radiographs
  258. SPOT: Bridging Natural Language and Geospatial Search for Investigative Journalists
  259. Dynamic Context-oriented Decomposition for Task-aware Low-rank Adaptation with Less Forgetting and Faster Convergence
  260. From Empirical Evaluation to Context-Aware Enhancement: Repairing Regression Errors with LLMs
  261. Dynamic Acoustic Model Architecture Optimization in Training for ASR
  262. Enhancing Large Language Models with Reliable Knowledge Graphs
  263. Development of the user-friendly decision aid Rule-based Evaluation and Support Tool (REST) for optimizing the resources of an information extraction task
  264. GeoRecon: Graph-Level Representation Learning for 3D Molecules via Reconstruction-Based Pretraining
  265. Efficient Approximate Temporal Triangle Counting in Streaming with Predictions
  266. Real Time Self-Tuning Adaptive Controllers on Temperature Control Loops using Event-based Game Theory
  267. Efficient Algorithms for Logistic Contextual Slate Bandits with Bandit Feedback
  268. Machine Learning as Iterated Belief Change a la Darwiche and Pearl
  269. StgcDiff: Spatial-Temporal Graph Condition Diffusion for Sign Language Transition Generation
  270. Federated ADMM from Bayesian Duality
  271. Adapting LLMs for Minimal-edit Grammatical Error Correction
  272. CMU's IWSLT 2025 Simultaneous Speech Translation System
  273. Random Matrix Theory for Deep Learning: Beyond Eigenvalues of Linear Models
  274. Quantum AGI: Ontological Foundations
  275. EmbodiedPlace: Learning Mixture-of-Features with Embodied Constraints for Visual Place Recognition
  276. Stochastic Multi-Objective Multi-Armed Bandits: Regret Definition and Algorithm
  277. SAGDA: Open-Source Synthetic Agriculture Data for Africa
  278. Accelerating PDE-Constrained Optimization by the Derivative of Neural Operators
  279. PhenoKG: Knowledge Graph-Driven Gene Discovery and Patient Insights from Phenotypes Alone
  280. Crime Hotspot Prediction Using Deep Graph Convolutional Networks
  281. Dynamic Reinsurance Treaty Bidding via Multi-Agent Reinforcement Learning
  282. GS-2DGS: Geometrically Supervised 2DGS for Reflective Object Reconstruction
  283. Honesty in Causal Forests: When It Helps and When It Hurts
  284. Equitable Electronic Health Record Prediction with FAME: Fairness-Aware Multimodal Embedding
  285. A Novel ViDAR Device With Visual Inertial Encoder Odometry and Reinforcement Learning-Based Active SLAM Method
  286. Dynamic Graph Condensation
  287. Pro-AD: Learning Comprehensive Prototypes with Prototype-based Constraint for Multi-class Unsupervised Anomaly Detection
  288. Learning Event Completeness for Weakly Supervised Video Anomaly Detection
  289. A Memetic Walrus Algorithm with Expert-guided Strategy for Adaptive Curriculum Sequencing
  290. SuperPoint-SLAM3: Augmenting ORB-SLAM3 with Deep Features, Adaptive NMS, and Learning-Based Loop Closure
  291. Fast and Furious Symmetric Learning in Zero-Sum Games: Gradient Descent as Fictitious Play
  292. Uncertainty-Aware Graph Neural Networks: A Multi-Hop Evidence Fusion Approach
  293. Discerning What Matters: A Multi-Dimensional Assessment of Moral Competence in LLMs
  294. SuperPlace: The Renaissance of Classical Feature Aggregation for Visual Place Recognition in the Era of Foundation Models
  295. CHILL at SemEval-2025 Task 2: You Can't Just Throw Entities and Hope -- Make Your LLM to Get Them Right
  296. Video Individual Counting With Implicit One-to-Many Matching
  297. CoIFNet: A Unified Framework for Multivariate Time Series Forecasting with Missing Values
  298. PRISM2: Unlocking Multi-Modal General Pathology AI with Clinical Dialogue
  299. Rethinking Explainability in the Era of Multimodal AI
  300. Stress-Testing Multimodal Foundation Models for Crystallographic Reasoning
  301. NeuVAS: Neural Implicit Surfaces for Variational Shape Modeling
  302. Beyond the First Read: AI-Assisted Perceptual Error Detection in Chest Radiography Accounting for Interobserver Variability
  303. Continual Learning for Generative AI: From LLMs to MLLMs and Beyond
  304. Just Go Parallel: Improving the Multilingual Capabilities of Large Language Models
  305. ViewPCL: a point cloud based active learning method for multi-view segmentation
  306. MAMMA: Markerless & Automatic Multi-Person Motion Action Capture
  307. Evolution of ReID: From Early Methods to LLM Integration
  308. Forecast-Then-Optimize Deep Learning Methods
  309. SpaceTrack-TimeSeries: Time Series Dataset towards Satellite Orbit Analysis
  310. AS400-DET: Detection using Deep Learning Model for IBM i (AS/400)
  311. WildCAT3D: Appearance-Aware Multi-View Diffusion in the Wild
  312. DETRPose: Real-Time End-to-End Multi-Person Pose Estimation via Modified Transformer Decoder and Novel Denoising Keypoints
  313. Knowledge Graph Fusion with Large Language Models for Accurate, Explainable Manufacturing Process Planning
  314. Position: Certified Robustness Does Not (Yet) Imply Model Security
  315. A Practical Guide for Evaluating LLMs and LLM-Reliant Systems
  316. C-TLSAN: Content-Enhanced Time-Aware Long- and Short-Term Attention Network for Personalized Recommendation
  317. Edeflip: Supervised Word Translation between English and Yoruba
  318. Symmetry in Neural Network Parameter Spaces
  319. Geometric Embedding Alignment via Curvature Matching in Transfer Learning
  320. Missing the human touch? A computational stylometry analysis of GPT-4 translations of online Chinese literature
  321. Condition Monitoring with Machine Learning: A Data-Driven Framework for Quantifying Wind Turbine Energy Loss
  322. Antibody Foundational Model : Ab-RoBERTa
  323. Adaptable Symbolic Music Infilling with MIDI-RWKV