mlsanityData to 14 Oct 2026

Papers

New on arXiv

Fri 19 Sep 2025

376 papers

  1. Evaluating Hallucinations in Audio-Visual Multimodal LLMs with Spoken Queries under Diverse Acoustic ConditionsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  2. Self-Rewarding Rubric-Based Reinforcement Learning for Open-Ended ReasoningLLM reasoning → Reinforcement learning for reasoning +1
  3. Sequential Token Merging: Revisiting Hidden StatesState-space sequence models (S4, Mamba) → Vision Mamba backbones +1
  4. Robust Object Detection for Autonomous Driving via Curriculum-Guided Group Relative Policy OptimizationLLM reasoning → Multimodal reasoning +2
  5. Random Direct Preference Optimization for Radiography Report GenerationLLM alignment / RLHF / preference optimisation → Medical LLM alignment
  6. SLM-Based Agentic AI with P-C-G: Optimized for Korean Tool UseLLM agents and tool use → Tool learning and function calling
  7. Pipeline Parallelism is All You Need for Optimized Early-Exit Based Self-Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  8. MMCD: Multi-Modal Collaborative Decision-Making for Connected Autonomy with Knowledge DistillationKnowledge distillation → Multimodal distillation
  9. Qianfan-VL: Domain-Enhanced Universal Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  10. Let's Unlearn Stereotypes Before Decision-Making: Assessing the Impact of Intrinsic Bias Mitigation on Downstream Fairness in LLMsLLM safety and security → Safety alignment, refusal and guardrails
  11. Implicit Behavioral Alignment of Language Agents in High-Stakes Crowd SimulationsLLM agents and tool use → Social simulation and multi-agent debate
  12. GPO: Learning from Critical Steps to Improve LLM ReasoningLLM reasoning → Test-time compute and efficient thinking
  13. KRAST: Knowledge-Augmented Robotic Action Recognition with Structured Text for Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  14. Local Mechanisms of Compositional Generalization in Conditional DiffusionDiffusion models → Diffusion foundations and sampling
  15. VORTEX: Aligning Task Utility and Human Preferences through LLM-Guided Reward ShapingLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  16. Dynamic Objects Relocalization in Changing Environments with Flow MatchingDiffusion models → Diffusion and flow policies for robotics
  17. GRID: Graph-based Reasoning for Intervention and Discovery in Built EnvironmentsLLM reasoning → Causal reasoning in LLMs
  18. Evaluating Behavioral Alignment in Conflict Dialogue: A Multi-Dimensional Comparison of LLM Agents and HumansLLM agents and tool use → Social simulation and multi-agent debate
  19. CoUn: Empowering Machine Unlearning via Contrastive LearningLLM safety and security → Machine unlearning
  20. Evaluation of Causal Reasoning for Large Language Models in Contextualized Clinical Scenarios of Laboratory Test InterpretationLLM reasoning → Clinical and biomedical applications
  21. Enhancing Financial RAG with Agentic AI and Multi-HyDE: A Novel Approach to Knowledge Retrieval and Hallucination ReductionLLM agents and tool use → Financial trading and forecasting agents
  22. RephQA: Evaluating Readability of Large Language Models in Public Health Question AnsweringLLM reasoning → Clinical and biomedical applications
  23. Visual Reasoning Agent: Robust Vision Systems in Remote Sensing via Inference-Time ScalingLLM reasoning → Spatial and embodied reasoning +1
  24. Similarity-Guided Diffusion for Long-Gap Music InpaintingDiffusion models → Audio, speech and music
  25. Generalizability of Large Language Model-Based Agents: A Comprehensive SurveyLLM agents and tool use → General LLM agent frameworks and benchmarks
  26. Overhearing LLM Agents: A Survey, Taxonomy, and RoadmapLLM agents and tool use → General LLM agent frameworks and benchmarks
  27. Test-Time Learning and Inference-Time Deliberation for Efficiency-First Offline Reinforcement Learning in Care Coordination and Population Health ManagementOffline RL and imitation learning from data → Safe offline RL
  28. Inverting Trojans in LLMsLLM safety and security → Backdoor and data poisoning attacks
  29. MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision TokenizerMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  30. Agentic Aerial Cinematography: From Dialogue Cues to Cinematic TrajectoriesLLM agents and tool use → Multimodal and embodied agents
  31. Robust Vision-Language Models via Tensor Decomposition: A Defense Against Adversarial AttacksMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  32. Automated Cyber Defense with Generalizable Graph-based Reinforcement Learning AgentsDeep reinforcement learning methods → Adversarial robustness and RL in finance
  33. Pointing to a Llama and Call it a Camel: On the Sycophancy of Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  34. Reward Evolution with Graph-of-Thoughts: A Bi-Level Language Model Framework for Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning
  35. Dynamic Classifier-Free Diffusion Guidance via Online FeedbackDiffusion models → Diffusion foundations and sampling +1
  36. BaseReward: A Strong Baseline for Multimodal Reward ModelMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  37. DiffusionNFT: Online Diffusion Reinforcement with Forward ProcessDiffusion models → Diffusion and flow policies for robotics
  38. CodeRAG: Finding Relevant and Necessary Knowledge for Retrieval-Augmented Repository-Level Code CompletionRetrieval-augmented generation → RAG for code
  39. PRISM: Probabilistic and Robust Inverse Solver with Measurement-Conditioned Diffusion Prior for Blind Inverse ProblemsDiffusion models → Inverse problems and image restoration
  40. DiEP: Adaptive Mixture-of-Experts Compression through Differentiable Expert PruningMixture-of-experts → MoE large language models
  41. Blind-Spot Guided Diffusion for Self-supervised Real-World DenoisingDiffusion models → Diffusion foundations and sampling
  42. Randomized Smoothing Meets Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  43. See&Trek: Training-Free Spatial Prompting for Multimodal Large Language ModelMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  44. I-FailSense: Towards General Robotic Failure Detection with Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  45. Generating Detailed Character Motion from Blocking PosesDiffusion models → Video generation
  46. Latent Conditioned Loco-Manipulation Using Motion PriorsDeep reinforcement learning methods → RL for robot locomotion and manipulation
  47. SABER: Uncovering Vulnerabilities in Safety Alignment via Cross-Layer Residual ConnectionLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  48. Language-Instructed Reasoning for Group Activity Detection via Multimodal Large Language ModelLLM reasoning → Multimodal reasoning +1
  49. Think, Verbalize, then Speak: Bridging Complex Thoughts and Comprehensible SpeechLLM reasoning → Audio-language model reasoning
  50. DistillMatch: Leveraging Knowledge Distillation from Vision Foundation Model for Multimodal Image MatchingKnowledge distillation → Multimodal distillation
  51. Defining and Monitoring Complex Robot Activities via LLMs and Symbolic ReasoningLLM reasoning → Spatial and embodied reasoning
  52. Scalable Quantum Reinforcement Learning on NISQ Devices with Dynamic-Circuit Qubit Reuse and Grover OptimizationDeep reinforcement learning methods → Quantum reinforcement learning
  53. Uncertainty-Based Smooth Policy Regularisation for Reinforcement Learning with Few DemonstrationsDeep reinforcement learning methods → RL for robot locomotion and manipulation
  54. CoReVLA: A Dual-Stage End-to-End Autonomous Driving Framework for Long-Tail Scenarios via Collect-and-RefineEnd-to-end autonomous driving → Reasoning VLA and VLM driving policies
  55. RLinf: Flexible and Efficient Large-scale Reinforcement Learning via Macro-to-Micro Flow TransformationLLM agents and tool use → Reinforcement learning for LLM agents +1
  56. MoE-CE: Enhancing Generalization for Deep Learning based Channel Estimation via a Mixture-of-Experts FrameworkMixture-of-experts → Expert routing strategies
  57. Compose Yourself: Average-Velocity Flow Matching for One-Step Speech EnhancementDiffusion models → Audio, speech and music
  58. ArchesClimate: Probabilistic Decadal Ensemble Generation With Flow MatchingDiffusion models → Flow matching, time series and science
  59. A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement LearningVision-language-action models → Reinforcement learning and post-training +1
  60. DISPATCH: Distilling Selective Patches for Speech EnhancementKnowledge distillation → Speech and audio distillation
  61. Foundation Models as World Models: A Foundational Study in Text-Based GridWorldsWorld models → World models for language agents
  62. Distribution-Aligned Decoding for Efficient LLM Task AdaptationMechanistic interpretability → Activation steering methods
  63. RACap: Relation-Aware Prompting for Lightweight Retrieval-Augmented Image CaptioningRetrieval-augmented generation → Multimodal RAG
  64. Improving Robotic Manipulation with Efficient Geometry-Aware Vision EncoderLLM reasoning → Spatial and embodied reasoning +1
  65. SAGE: Semantic-Aware Shared Sampling for Efficient DiffusionDiffusion models → Diffusion foundations and sampling
  66. ToFU: Transforming How Federated Learning Systems Forget User DataLLM safety and security → Federated unlearning and poisoning
  67. Efficient Long-Tail Learning in Latent Space by sampling Synthetic DataSynthetic data and self-improvement for LLMs → Model collapse from synthetic data
  68. Multi-Physics: A Comprehensive Benchmark for Multimodal LLMs Reasoning on Chinese Multi-Subject Physics ProblemsLLM reasoning → Spatial and embodied reasoning +1
  69. Coordinated Multi-Drone Last-mile Delivery: Learning Strategies for Energy-aware and Timely OperationsDeep reinforcement learning methods → RL for robot navigation and UAV control
  70. Best-of-L: Cross-Lingual Reward Modeling for Mathematical ReasoningLLM reasoning → Reasoning benchmarks and evaluation +1
  71. ChronoForge-RL: Chronological Forging through Reinforcement Learning for Enhanced Video UnderstandingDeep reinforcement learning methods → RL training of language and agent models
  72. Vision-Language Models as Differentiable Semantic and Spatial Rewards for Text-to-3D GenerationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  73. UniGist: Towards General and Hardware-aligned Sequence-level Long Context CompressionEfficient LLM inference and serving → KV cache optimization
  74. On Optimal Steering to Achieve Exact FairnessMechanistic interpretability → Probing deception, bias and beliefs
  75. Can LLMs Judge Debates? Evaluating Non-Linear Reasoning via Argumentation Theory SemanticsLLM reasoning → Reasoning for agents, planning and code
  76. GUI-ReWalk: Massive Data Generation for GUI Agent via Stochastic Exploration and Intent-Aware ReasoningLLM reasoning → Multimodal reasoning +1
  77. RMT-KD: Random Matrix Theoretic Causal Knowledge DistillationKnowledge distillation → General knowledge distillation methods
  78. Pyramid Token Pruning for High-Resolution Large Vision-Language Models via Region, Token, and Instruction-Guided ImportanceMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  79. ORIC: Benchmarking Object Recognition under Contextual Incongruity in Large Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  80. CCrepairBench: A High-Fidelity Benchmark and Reinforcement Learning Framework for C++ Compilation RepairDeep reinforcement learning methods → RL training of language and agent models
  81. SAM: A Mamba-2 State-Space Audio-Language ModelState-space sequence models (S4, Mamba) → Speech and audio SSMs
  82. Layout Stroke Imitation: A Layout Guided Handwriting Stroke Generation for Style Imitation with Diffusion ModelDiffusion models → Image generation, text-to-image and editing
  83. SightSound-R1: Cross-Modal Reasoning Distillation from Vision to Audio Language ModelsLLM reasoning → Audio-language model reasoning +2
  84. Nonconvex Regularization for Feature Selection in Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  85. pFedSAM: Personalized Federated Learning of Segment Anything Model for Medical Image SegmentationMixture-of-experts → Medical and biomedical MoE +1
  86. MicroRCA-Agent: Microservice Root Cause Analysis Method Based on Large Language Model AgentsLLM agents and tool use → Software engineering coding agents
  87. Sparse-Autoencoder-Guided Internal Representation Unlearning for Large Language ModelsLLM safety and security → Machine unlearning +1
  88. Concept Unlearning in Large Language Models via Self-Constructed Knowledge TripletsLLM safety and security → Machine unlearning
  89. Enhancing WSI-Based Survival Analysis with Report-Auxiliary Self-DistillationKnowledge distillation → Distillation for medical imaging
  90. PRIMT: Preference-based Reinforcement Learning with Multimodal Feedback and Trajectory Synthesis from Foundation ModelsDeep reinforcement learning methods → RL training of language and agent models
  91. TennisTV: Do Multimodal Large Language Models Understand Tennis Rallies?Multimodal LLMs / vision-language models → Embodied and 3D vision-language models
  92. EyePCR: A Comprehensive Benchmark for Fine-Grained Perception, Knowledge Comprehension and Clinical Reasoning in Ophthalmic SurgeryLLM reasoning → Clinical and biomedical applications +1
  93. DivLogicEval: A Framework for Benchmarking Logical Reasoning Evaluation in Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  94. Momentum-constrained Hybrid Heuristic Trajectory Optimization Framework with Residual-enhanced DRL for Visually Impaired ScenariosDeep reinforcement learning methods → RL for robot navigation and UAV control
  95. Relevance to Utility: Process-Supervised Rewrite for RAGRetrieval-augmented generation → RAG robustness and adaptive retrieval
  96. Cuckoo Attack: Stealthy and Persistent Attacks Against AI-IDELLM agents and tool use → Agent threats, guardrails and governance
  97. LiteLong: Resource-Efficient Long-Context Data Synthesis for LLMsSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  98. BTL-UI: Blink-Think-Link Reasoning Model for GUI AgentLLM reasoning → Multimodal reasoning +1
  99. DC-Mamba: Bi-temporal deformable alignment and scale-sparse enhancement for remote sensing change detectionState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  100. Reward Hacking Mitigation using Verifiable Composite RewardsLLM reasoning → Reinforcement learning for reasoning +1
All 376
  1. PolyJuice Makes It Real: Black-Box, Universal Red Teaming for Synthetic Image DetectorsLLM safety and security → Vision-language and text-to-image safety
  2. SAMPO:Scale-wise Autoregression with Motion PrOmpt for generative world modelsWorld models → Video-generation world models and simulators
  3. MEC-Quant: Maximum Entropy Coding for Extremely Low Bit Quantization-Aware TrainingMixture-of-experts → MoE large language models
  4. Bayesian Risk-Sensitive Policy Optimization For MDPs With General Loss FunctionsDeep reinforcement learning methods → RL theory and sample complexity
  5. Mental Accounts for Actions: EWA-Inspired Attention in Decision TransformersOffline RL and imitation learning from data → Decision transformers and sequence modeling +1
  6. An extended reality-based framework for user risk training in urban built environment
  7. Modelling the Interplay of Eye-Tracking Temporal Dynamics and Personality for Emotion Detection in Face-to-Face Settings
  8. GQVis: A Dataset of Genomics Data Questions and Visualizations for Generative AI
  9. Polynomial Contrastive Learning for Privacy-Preserving Representation Learning on Graphs
  10. Spectral Logit Sculpting: Adaptive Low-Rank Logit Transformation for Controlled Text Generation
  11. Generating High-Quality Datasets for Code Editing via Open-Source Language Models
  12. Deep Learning Empowered Super-Resolution: A Comprehensive Survey and Future Prospects
  13. A review of Recent Techniques for Person Re-Identification
  14. Graph-Theoretic Consistency for Robust and Topology-Aware Semi-Supervised Histopathology Segmentation
  15. Improving Autism Detection with Multimodal Behavioral Analysis
  16. CFDLLMBench: A Benchmark Suite for Evaluating Large Language Models in Computational Fluid Dynamics
  17. Speaker Style-Aware Phoneme Anchoring for Improved Cross-Lingual Speech Emotion Recognition
  18. Uncertainty-Aware Calibrated Clinical Text Classification with Large Language Models
  19. Short-Term Regional Electricity Demand Forecasting in Argentina Using LSTM Networks
  20. Representation-based Broad Hallucination Detectors Fail to Generalize Out of Distribution
  21. How to inject knowledge efficiently? Knowledge Infusion Scaling Law for Pre-training Large Language Models
  22. Meow: End-to-End Outline Writing for Automatic Academic Survey
  23. Low-Cost Sensor Fusion Framework for Organic Substance Classification and Quality Control Using Classification Methods
  24. Unsupervised Outlier Detection in Audit Analytics: A Case Study Using USA Spending Data
  25. MNV-17: A High-Quality Performative Mandarin Dataset for Nonverbal Vocalization Recognition in Speech
  26. TinyEcoWeedNet: Edge Efficient Real-Time Aerial Agricultural Weed Detection
  27. HazeFlow: Revisit Haze Physical Model as ODE and Non-Homogeneous Haze Generation for Real-World Dehazing
  28. The Iconicity of the Generated Image
  29. Explainable Gait Abnormality Detection Using Dual-Dataset CNN-LSTM Models
  30. From Coated to Uncoated: Scanning Electron Microscopy Corrections to Estimate True Surface Pore Size in Nanoporous Membranes
  31. Computational Analysis of Conversation Dynamics through Participant Responsivity
  32. Entropic Causal Inference: Graph Identifiability
  33. A Generative AI System for Biomedical Data Discovery with Grammar-Based Visualizations
  34. Overfitting in Adaptive Robust Optimization
  35. PersonaMatrix: A Recipe for Persona-Aware Evaluation of Legal Summarization
  36. Purely Semantic Indexing for LLM-based Generative Recommendation and Retrieval
  37. Domain-Specific Constitutional AI: Enhancing Safety in LLM-Powered Mental Health Chatbots
  38. LightCode: Compiling LLM Inference for Photonic-Electronic Systems
  39. Evaluating the Effectiveness and Scalability of LLM-Based Data Augmentation for Retrieval
  40. AutoArabic: A Three-Stage Framework for Localizing Video-Text Retrieval Benchmarks
  41. SENSE-7: Taxonomy and Dataset for Measuring User Perceptions of Empathy in Sustained Human-AI Conversations
  42. Improved mmFormer for Liver Fibrosis Staging via Missing-Modality Compensation
  43. End-to-end RL Improves Dexterous Grasping Policies
  44. Proactive Statistical Process Control Using AI: A Time Series Forecasting Approach for Semiconductor Manufacturing
  45. TractoTransformer: Diffusion MRI Streamline Tractography using CNN and Transformer Networks
  46. 3D Gaussian Flats: Hybrid 2D/3D Photometric Scene Reconstruction
  47. Evaluating CxG Generalisation in LLMs via Construction-Based NLI Fine Tuning
  48. AHA -- Predicting What Matters Next: Online Highlight Detection Without Looking Ahead
  49. LenslessMic: Audio Encryption and Authentication via Lensless Computational Imaging
  50. StereoAdapter: Adapting Stereo Depth Estimation to Underwater Scenes
  51. Pico: A Modular Framework for Hypothesis-Driven Small Language Model Research
  52. Hierarchical Retrieval: The Geometry and a Pretrain-Finetune Recipe
  53. 'Rich Dad, Poor Lad': How do Large Language Models Contextualize Socioeconomic Factors in College Admission ?
  54. Low-Rank Evolutionary Deep Neural Networks via Adaptive Tangent-Space Reduction
  55. Federated Learning for Financial Forecasting
  56. Accurate Thyroid Cancer Classification using a Novel Binary Pattern Driven Local Discrete Cosine Transform Descriptor
  57. EMPEROR: Efficient Moment-Preserving Representation of Distributions
  58. Longitudinal and Multimodal Recording System to Capture Real-World Patient-Clinician Conversations for AI and Encounter Research: Protocol
  59. Whisper-UT: A Unified Translation Framework for Speech and Text
  60. Introducing Resizable Region Packing Problem in Image Generation, with a Heuristic Solution
  61. Guided Sequence-Structure Generative Modeling for Iterative Antibody Optimization
  62. Improving Deep Tabular Learning
  63. Secure Confidential Business Information When Sharing Machine Learning Models
  64. A Unified AI Approach for Continuous Monitoring of Human Health and Diseases from Intensive Care Unit to Home with Physiological Foundation Models (UNIPHY+)
  65. QUINTA: Reflexive Sensibility For Responsible AI Research and Data-Driven Processes
  66. From Canopy to Ground via ForestGen3D: Learning Cross-Domain Generation of 3D Forest Structure from Aerial-to-Terrestrial LiDAR
  67. Estimating Clinical Lab Test Result Trajectories from PPG using Physiological Foundation Model and Patient-Aware State Space Model -- a UNIPHY+ Approach
  68. Highly Imbalanced Regression with Tabular Data in SEP and Other Applications
  69. Learning Centre Partitions from Summaries
  70. Neural Atlas Graphs for Dynamic Scene Decomposition and Editing
  71. Psychometric Personality Shaping Modulates Capabilities and Safety in Language Models
  72. The Role of High-Performance GPU Resources in Large Language Model Based Radiology Imaging Diagnosis
  73. HARE: an entity and relation centric evaluation framework for histopathology reports
  74. Auto-bidding under Return-on-Spend Constraints with Uncertainty Quantification
  75. TF-DWGNet: A Directed Weighted Graph Neural Network with Tensor Fusion for Multi-Omics Cancer Subtype Classification
  76. ROOT: Rethinking Offline Optimization as Distributional Translation via Probabilistic Bridge
  77. On the Non-Uniqueness of Representation of (U,N)-Implications
  78. A global view of diverse construction methods of fuzzy implication functions rooted on F-chains
  79. How Large Language Models are Designed to Hallucinate
  80. Patterns in the Transition From Founder-Leadership to Community Governance of Open Source
  81. Robust LLM Training Infrastructure at ByteDance
  82. Identifying Critical Pathways in Coronary Heart Disease via Fuzzy Subgraph Connectivity
  83. Architectural change in neural networks using fuzzy vertex pooling
  84. RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation
  85. FocalCodec-Stream: Streaming Low-Bitrate Speech Coding via Causal Distillation
  86. Latent learning: episodic memory complements parametric learning by enabling flexible reuse of experiences
  87. CultureScope: A Dimensional Lens for Probing Cultural Understanding in LLMs
  88. MatchFixAgent: Language-Agnostic Autonomous Repository-Level Code Translation Validation and Repair
  89. Quantum Generative Adversarial Autoencoders: Learning latent representations for quantum data generation
  90. Accelerating Atomic Fine Structure Determination with Graph Reinforcement Learning
  91. Query-Efficient Locally Private Hypothesis Selection via the Scheffe Graph
  92. Fast OTSU Thresholding Using Bisection Method
  93. DIVEBATCH: Accelerating Model Training Through Gradient-Diversity Aware Batch Size Adaptation
  94. UniMRSeg: Unified Modality-Relax Segmentation via Hierarchical Self-Supervised Compensation
  95. AcT2I: Evaluating and Improving Action Depiction in Text-to-Image Models
  96. When Bugs Linger: A Study of Anomalous Resolution Time Outliers and Their Themes
  97. Spatio-temporal, multi-field deep learning of shock propagation in meso-structured media
  98. Recovering Parametric Scenes from Very Few Time-of-Flight Pixels
  99. Network-Based Detection of Autism Spectrum Disorder Using Sustainable and Non-invasive Salivary Biomarkers
  100. RadarGaussianDet3D: Gaussian Representation-based Real-time 3D Object Detection with 4D Automotive Radars
  101. It Depends: Resolving Referential Ambiguity in Minimal Contexts with Commonsense Knowledge
  102. Personalized Federated Heat-Kernel Enhanced Multi-View Clustering via Advanced Tensor Decomposition Techniques
  103. SegDINO3D: 3D Instance Segmentation Empowered by Both Image-Level and Object-Level 2D Features
  104. AdaSports-Traj: Role- and Domain-Aware Adaptation for Multi-Agent Trajectory Modeling in Sports
  105. Beyond Pointwise Scores: Decomposed Criteria-Based Evaluation of LLM Responses
  106. An adaptive subsampling method for large-sample feature screening
  107. Exploring Synthesizable Chemical Space with Iterative Pathway Refinements
  108. MTS-DMAE: Dual-Masked Autoencoder for Unsupervised Multivariate Time Series Representation Learning
  109. Communications to Circulations: Real-Time 3D Wind Field Prediction Using 5G GNSS Signals and Deep Learning
  110. Attention Schema-based Attention Control (ASAC): A Cognitive-Inspired Approach for Attention Management in Transformers
  111. Compose by Focus: Scene Graph-based Atomic Skills
  112. Graph-based Point Cloud Surface Reconstruction using B-Splines
  113. FMD-TransUNet: Abdominal Multi-Organ Segmentation Based on Frequency Domain Multi-Axis Representation Learning and Dual Attention Mechanisms
  114. Automated Constitutive Model Discovery by Pairing Sparse Regression Algorithms with Model Selection Criteria
  115. GLip: A Global-Local Integrated Progressive Framework for Robust Visual Speech Recognition
  116. What is a good matching of probability measures? A counterfactual lens on transport maps
  117. Time-adaptive SympNets for separable Hamiltonian systems
  118. Session-Level Spoken Language Assessment with a Multimodal Foundation Model via Multi-Target Learning
  119. Generalized Deep Multi-view Clustering via Causal Learning with Partially Aligned Cross-view Correspondence
  120. AI Methods for Permutation Circuit Synthesis Across Generic Topologies
  121. SLaM-DiMM: Shared Latent Modeling for Diffusion Based Missing Modality Synthesis in MRI
  122. Predicting the descent into extremism and terrorism
  123. Towards Robust Visual Continual Learning with Multi-Prototype Supervision
  124. Fed-PISA: Federated Voice Cloning via Personalized Identity-Style Adaptation
  125. Inverse Optimization Latent Variable Models for Learning Costs Applied to Route Problems
  126. Quantum Enhanced Anomaly Detection for ADS-B Data using Hybrid Deep Learning
  127. DAFTED: Decoupled Asymmetric Fusion of Tabular and Echocardiographic Data for Cardiac Hypertension Diagnosis
  128. Model-free algorithms for fast node clustering in SBM type graphs and application to social role inference in animals
  129. Towards Sharper Object Boundaries in Self-Supervised Depth Estimation
  130. EmoHeal: An End-to-End System for Personalized Therapeutic Music Retrieval from Fine-grained Emotions
  131. CoPAD : Multi-source Trajectory Fusion and Cooperative Trajectory Prediction with Anchor-oriented Decoder in V2X Scenarios
  132. Shedding Light on Depth: Explainability Assessment in Monocular Depth Estimation
  133. BEFT: Bias-Efficient Fine-Tuning of Language Models in Low-Data Regimes
  134. VoXtream: Full-Stream Text-to-Speech with Extremely Low Latency
  135. A multi-temporal multi-spectral attention-augmented deep convolution neural network with contrastive learning for crop yield prediction
  136. Structured Information for Improving Spatial Relationships in Text-to-Image Generation
  137. Review of Explainable Decision Support and Adaptive Human-Machine Interfaces for Automation Transparency in Maritime Autonomous Surface Ships
  138. Localmax dynamics for attention in transformers and its asymptotic behavior
  139. EHR-MCP: Real-world Evaluation of Clinical Information Retrieval by Large Language Models via Model Context Protocol
  140. Adversarial Graph Fusion for Incomplete Multi-view Semi-supervised Learning with Tensorial Imputation
  141. Targeted Fine-Tuning of DNN-Based Receivers via Influence Functions
  142. The Missing Piece: A Case for Pre-Training in 3D Medical Object Detection
  143. PAN: Pillars-Attention-Based Network for 3D Object Detection
  144. UniTac2Pose: A Unified Approach Learned in Simulation for Category-level Visuotactile In-hand Pose Estimation
  145. Bayesian Physics Informed Neural Networks for Reliable Transformer Prognostics
  146. The Alignment Bottleneck
  147. Improving Monte Carlo Tree Search for Symbolic Regression
  148. Enhancing Generative Auto-bidding with Offline Reward Evaluation and Policy Search
  149. Beyond the Score: Uncertainty-Calibrated LLMs for Automated Essay Assessment
  150. Sparse Multiview Open-Vocabulary 3D Detection
  151. Interpretable Nanoporous Materials Design with Symmetry-Aware Networks
  152. Deep Feedback Models
  153. Re-FRAME the Meeting Summarization SCOPE: Fact-Based Summarization and Personalization via Questions
  154. A Flow-rate-conserving CNN-based Domain Decomposition Method for Blood Flow Simulations
  155. The Psychology of Falsehood: A Human-Centric Survey of Misinformation Detection
  156. From Data to Diagnosis: A Large, Comprehensive Bone Marrow Dataset and AI Methods for Childhood Leukemia Prediction
  157. MoAngelo: Motion-Aware Neural Surface Reconstruction for Dynamic Scenes
  158. Global Regulation and Excitation via Attention Tuning for Stereo Matching
  159. RangeSAM: On the Potential of Visual Foundation Models for Range-View represented LiDAR segmentation
  160. Self-Supervised Cross-Modal Learning for Image-to-Point Cloud Registration
  161. ENSAM: an efficient foundation model for interactive segmentation of 3D medical images
  162. DeepMech: A Machine Learning Framework for Chemical Reaction Mechanism Prediction
  163. Zero-Shot Visual Grounding in 3D Gaussians via View Retrieval
  164. LC-SLab -- An object-based deep learning framework for large-scale land cover classification from satellite imagery and sparse in-situ labels
  165. Optimizing Product Deduplication in E-Commerce with Multimodal Embeddings
  166. EvoBrain: Dynamic Multi-Channel EEG Graph Modeling for Time-Evolving Brain Networks
  167. A Comparative Study of Rule-Based and Data-Driven Approaches in Industrial Monitoring
  168. FedHK-MVFC: Federated Heat Kernel Multi-View Clustering
  169. Tsururu: A Python-based Time Series Forecasting Strategies Library
  170. The Curious Case of Visual Grounding: Different Effects for Speech- and Text-based Language Encoders
  171. HyP-ASO: A Hybrid Policy-based Adaptive Search Optimization Framework for Large-Scale Integer Linear Programs
  172. SolarCrossFormer: Improving day-ahead Solar Irradiance Forecasting by Integrating Satellite Imagery and Ground Sensors
  173. Phase Transition for Stochastic Block Model with more than √n Communities
  174. On the Convergence of Muon and Beyond
  175. GPU Temperature Simulation-Based Testing for In-Vehicle Deep Learning Frameworks
  176. QWD-GAN: Quality-aware Wavelet-driven GAN for Unsupervised Medical Microscopy Images Denoising
  177. Diversity of Structured Domains via k-Kemeny Scores
  178. Instance Generation for Meta-Black-Box Optimization through Latent Space Reverse Engineering
  179. Boosting Active Learning with Knowledge Transfer
  180. CIDER: A Causal Cure for Brand-Obsessed Text-to-Image Models
  181. DPC-QA Net: A No-Reference Dual-Stream Perceptual and Cellular Quality Assessment Network for Histopathology Images
  182. Hierarchical Reinforcement Learning with Low-Level MPC for Multi-Agent Control
  183. Transfer learning under latent space model
  184. Monte Carlo Tree Diffusion with Multiple Experts for Protein Design
  185. TASAM: Terrain-and-Aware Segment Anything Model for Temporal-Scale Remote Sensing Segmentation
  186. RAVE: Retrieval and Scoring Aware Verifiable Claim Detection
  187. Minimal Semantic Sufficiency Meets Unsupervised Domain Generalization
  188. UPRPRC: Unified Pipeline for Reproducing Parallel Resources -- Corpus from the United Nations
  189. FoBa: A Foreground-Background co-Guided Method and New Benchmark for Remote Sensing Semantic Change Detection
  190. Building Data-Driven Occupation Taxonomies: A Bottom-Up Multi-Stage Approach via Semantic Clustering and Multi-Agent Collaboration
  191. CBPNet: A Continual Backpropagation Prompt Network for Alleviating Plasticity Loss on Edge Devices
  192. Ideal Registration? Segmentation is All You Need
  193. Enriched Feature Representation and Motion Prediction Module for MOSEv2 Track of 7th LSVOS Challenge: 3rd Place Solution
  194. Ontology Creation and Management Tools: the Case of Anatomical Connectivity
  195. Generalization and Optimization of SGD with Lookahead
  196. Overview of PlantCLEF 2024: multi-species plant identification in vegetation plot images
  197. Learning to Optimize Capacity Planning in Semiconductor Manufacturing
  198. Uncertainty-Gated Deformable Network for Breast Tumor Segmentation in MR Images
  199. MCOD: The First Challenging Benchmark for Multispectral Camouflaged Object Detection
  200. Simulated Cortical Magnification Supports Self-Supervised Object Learning
  201. FloorSAM: SAM-Guided Floorplan Reconstruction with Semantic-Geometric Fusion
  202. Hybrid Lie semi-group and cascade structures for the generalized Gaussian derivative model for visual receptive fields
  203. TrueMoE: Dual-Routing Mixture of Discriminative Experts for Synthetic Image Detection
  204. Incremental Multistep Forecasting of Battery Degradation Using Pseudo Targets
  205. Aircraft Fuel Flow Modelling with Ageing Effects: From Parametric Corrections to Neural Networks
  206. EigenTrack: Spectral Activation Feature Tracking for Hallucination and Out-of-Distribution Detection in LLMs and VLMs
  207. GP3: A 3D Geometry-Aware Policy with Multi-View Images for Robotic Manipulation
  208. A Nascent Taxonomy of Machine Learning in Intelligent Robotic Process Automation
  209. Training Variational Quantum Circuits Using Particle Swarm Optimization
  210. REFER: Mitigating Bias in Opinion Summarisation via Frequency Framed Prompting
  211. Impact of Single Rotations and Entanglement Topologies in Quantum Neural Networks
  212. Once Upon a Time: Interactive Learning for Storytelling with Small Language Models
  213. Toward Medical Deepfake Detection: A Comprehensive Dataset and Novel Method
  214. SGMAGNet: A Baseline Model for 3D Cloud Phase Structure Reconstruction on a New Passive Active Satellite Benchmark
  215. Triplet Loss Based Quantum Encoding for Class Separability
  216. Fine-Tuning Large Multimodal Models for Automatic Pronunciation Assessment
  217. SCENEFORGE: Enhancing 3D-text alignment with Structured Scene Compositions
  218. Direct Simultaneous Translation Activation for Large Audio-Language Models
  219. Saccadic Vision for Fine-Grained Visual Classification
  220. Camera Splatting for Continuous View Optimization
  221. KITE: Kernelized and Information Theoretic Exemplars for In-Context Learning
  222. A PCA Based Model for Surface Reconstruction from Incomplete Point Clouds
  223. Inference Offloading for Cost-Sensitive Binary Classification at the Edge
  224. VOX-KRIKRI: Unifying Speech and Language through Continuous Fusion
  225. TISDiSS: A Training-Time and Inference-Time Scalable Framework for Discriminative Source Separation
  226. Chunk Knowledge Generation Model for Enhanced Information Retrieval: A Multi-task Learning Approach
  227. Layer-wise Minimal Pair Probing Reveals Contextual Grammatical-Conceptual Hierarchy in Speech Representations
  228. Toward Efficient Influence Function: Dropout as a Compression Tool
  229. FingerSplat: Contactless Fingerprint 3D Reconstruction and Generation based on 3D Gaussian Splatting
  230. GS-Scale: Unlocking Large-Scale 3D Gaussian Splatting Training via Host Offloading
  231. UNIV: Unified Foundation Model for Infrared and Visible Modalities
  232. Information Geometry of Variational Bayes
  233. Multilingual LLM Prompting Strategies for Medical English-Vietnamese Machine Translation
  234. PCSR: Pseudo-label Consistency-Guided Sample Refinement for Noisy Correspondence Learning
  235. SciEvent: Benchmarking Multi-domain Scientific Event Extraction
  236. Efficient Extractive Text Summarization for Online News Articles Using Machine Learning
  237. Interpretable Network-assisted Random Forest+
  238. Prostate Capsule Segmentation from Micro-Ultrasound Images using Adaptive Focal Loss
  239. Beyond the Average: Distributional Causal Inference under Imperfect Compliance
  240. SETrLUSI: Stochastic Ensemble Multi-Source Transfer Learning Using Statistical Invariant
  241. Personalized Prediction By Learning Halfspace Reference Classes Under Well-Behaved Distribution
  242. Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification
  243. CFDA & CLIP at TREC iKAT 2025: Enhancing Personalized Conversational Search via Query Reformulation and Rank Fusion
  244. How many classes do we need to see for novel class discovery?
  245. Chunk Based Speech Pre-training with High Resolution Finite Scalar Quantization
  246. Multimodal Learning for Fake News Detection in Short Videos Using Linguistically Verified Data and Heterogeneous Modality Fusion
  247. Subset Selection for Stratified Sampling in Online Controlled Experiments
  248. Towards Size-invariant Salient Object Detection: A Generic Evaluation and Optimization Approach
  249. Contrastive Learning with Spectrum Information Augmentation in Abnormal Sound Detection
  250. Small LLMs with Expert Blocks Are Good Enough for Hyperparamter Tuning
  251. How important is language for human-like intelligence?
  252. From Development to Deployment of AI-assisted Telehealth and Screening for Vision- and Hearing-threatening diseases in resource-constrained settings: Field Observations, Challenges and Way Forward
  253. Exploring Polyglot Harmony: On Multilingual Data Allocation for Large Language Models Pretraining
  254. Hybrid Deep Learning-Federated Learning Powered Intrusion Detection System for IoT/5G Advanced Edge Computing Network
  255. Diffusion-Based Cross-Modal Feature Extraction for Multi-Label Classification
  256. The Multi-Query Paradox in Zeroth-Order Optimization
  257. DNA-DetectLLM: Unveiling AI-Generated Text via a DNA-Inspired Mutation-Repair Paradigm
  258. M-DaQ: Retrieving Samples with Multilingual Diversity and Quality for Instruction Fine-Tuning Datasets
  259. MS-GS: Multi-Appearance Sparse-View 3D Gaussian Splatting in the Wild
  260. Enhancing Sa2VA for Referent Video Object Segmentation: 2nd Solution for 7th LSVOS RVOS Track
  261. Nonconvex Decentralized Stochastic Bilevel Optimization under Heavy-Tailed Noise
  262. Stress Testing Deliberative Alignment for Anti-Scheming Training
  263. Beyond Words: Enhancing Desire, Emotion, and Sentiment Recognition with Non-Verbal Cues
  264. Geometric Integration for Neural Control Variates
  265. Universal Learning of Stochastic Dynamics for Exact Belief Propagation using Bernstein Normalizing Flows
  266. GUI-ARP: Enhancing Grounding with Adaptive Region Perception for GUI Agents
  267. Fully Decentralized Cooperative Multi-Agent Reinforcement Learning is A Context Modeling Problem
  268. How do Language Models Generate Slang: A Systematic Comparison between Human and Machine-Generated Slang Usages
  269. A Survey and Comparative Evaluation of Intrinsic Dimension Estimators under the Manifold Hypothesis
  270. LLM Cache Bandit Revisited: Addressing Query Heterogeneity for Cost-Effective LLM Inference
  271. KoopCast: Trajectory Forecasting via Koopman Operators
  272. The (Short-Term) Effects of Large Language Models on Unemployment and Earnings
  273. Backdoor Mitigation via Invertible Pruning Masks
  274. Lynx: Towards High-Fidelity Personalized Video Generation
  275. Multi-resolution Enhancement for Full Spectrum Neural Representations
  276. FRAUDGUESS: Spotting and Explaining New Types of Fraud in Million-Scale Financial Data