mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sun 3 Aug 2025

207 papers

  1. The Art of Breaking Words: Rethinking Multilingual Tokenizer DesignLLM reasoning → Reasoning benchmarks and evaluation
  2. What Makes "Good" Distractors for Object Hallucination Evaluation in Large Vision-Language Models?Multimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  3. A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and ChallengesLLM agents and tool use → Web, search, and research agents
  4. DMSC: Dynamic Multi-Scale Coordination Framework for Time Series ForecastingMixture-of-experts → MoE for time series and graphs
  5. SmallKV: Small Model Assisted Compensation of KV Cache Compression for Efficient LLM InferenceEfficient LLM inference and serving → KV cache optimization
  6. SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story ComprehensionRetrieval-augmented generation → Generation and context integration
  7. ROVER: Recursive Reasoning Over Videos with Vision-Language Models for Embodied TasksLLM reasoning → Spatial and embodied reasoning +1
  8. Word Overuse and Alignment in Large Language Models: The Influence of Learning from Human FeedbackLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  9. Beyond Simulation: Benchmarking World Models for Planning and Causality in Autonomous DrivingWorld models → World models for autonomous driving +1
  10. InspectVLM: Unified in Theory, Unreliable in PracticeMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  11. Decomposing Representation Space into Interpretable Subspaces with Unsupervised LearningMechanistic interpretability → Circuits and mechanistic analysis
  12. Proactive Constrained Policy Optimization with Preemptive PenaltyDeep reinforcement learning methods → Safe and constrained RL
  13. StreamAgent: Towards Anticipatory Agents for Streaming Video UnderstandingEfficient LLM inference and serving → Visual token pruning in multimodal models
  14. Web-CogReasoner: Towards Multimodal Knowledge-Induced Cognitive Reasoning for Web AgentsLLM agents and tool use → Web, search, and research agents
  15. MLP Memory: A Retriever-Pretrained Memory for Large Language ModelsRetrieval-augmented generation → Generation and context integration
  16. RouteMark: A Fingerprint for Intellectual Property Attribution in Routing-based Model MergingMixture-of-experts → Expert routing strategies
  17. LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?LLM agents and tool use → Tool learning and function calling
  18. DiffSemanticFusion: Semantic Raster BEV Fusion for Autonomous Driving via Online HD Map DiffusionEnd-to-end autonomous driving → End-to-end system architecture
  19. Uncertainty-Based Methods for Automated Process Reward Data Construction and Output Aggregation in Mathematical ReasoningLLM reasoning → Reinforcement learning for reasoning +1
  20. Semantically-Guided Inference for Conditional Diffusion Models: Enhancing Covariate Consistency in Time Series ForecastingDiffusion models → Flow matching, time series and science
  21. Bayes-Entropy Collaborative Driven Agents for Research Hypotheses Generation and OptimizationLLM agents and tool use → Web, search, and research agents
  22. Simulated Ensemble Attack: Transferring Jailbreaks Across Fine-tuned Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  23. Granular Concept Circuits: Toward a Fine-Grained Circuit Discovery for Concept RepresentationsMechanistic interpretability → Circuits and mechanistic analysis
  24. OccamVTS: Distilling Vision Models to 1% Parameters for Time Series ForecastingKnowledge distillation → General knowledge distillation methods
  25. Imbalance-Robust and Sampling-Efficient Continuous Conditional GANs via Adaptive Vicinal Learning and Auxiliary RegularizationDiffusion models → Diffusion foundations and sampling
  26. ModFus-DM: Explore the Representation in Modulated Signal Diffusion Generated ModelsDiffusion models → Diffusion for compression and wireless
  27. CultureGuard: Towards Culturally-Aware Dataset and Guard Model for Multilingual Safety ApplicationsLLM agents and tool use → Agent threats, guardrails and governance
  28. DeepVIS: Bridging Natural Language and Data Visualization Through Step-wise ReasoningLLM reasoning → Multimodal reasoning
  29. TimeExpert: An Expert-Guided Video LLM for Video Temporal GroundingMixture-of-experts → Vision mixture-of-experts
  30. Versatile Transition Generation with Image-to-Video DiffusionDiffusion models → Video generation
  31. CoCoA: Collaborative Chain-of-Agents for Parametric-Retrieved Knowledge SynergyRetrieval-augmented generation → Agentic RAG, agents and memory +1
  32. DisCo3D: Distilling Multi-View Consistency for 3D Scene EditingDiffusion models → 3D, point cloud and scene generation
  33. The Bidirectional Process Reward ModelLLM reasoning → Reinforcement learning for reasoning +1
  34. T-GRAG: A Dynamic GraphRAG Framework for Resolving Temporal Conflicts and Redundancy in Knowledge RetrievalRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  35. Cure or Poison? Embedding Instructions Visually Alters Hallucination in Vision-Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  36. Shape Distribution Matters: Shape-specific Mixture-of-Experts for Amodal Segmentation under Diverse OcclusionsMixture-of-experts → Vision mixture-of-experts
  37. MAP: Mitigating Hallucinations in Large Vision-Language Models with Map-Level Attention ProcessingMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  38. Diffusion Models are Open-World Affordance Learners: Leveraging Generative Priors for 3D Affordance LearningDiffusion models → Video generation
  39. DUP: Detection-guided Unlearning for Backdoor Purification in Language ModelsLLM safety and security → Backdoor and data poisoning attacks
  40. ChEmbed: Enhancing Chemical Literature Search Through Domain-Specific Text EmbeddingsRetrieval-augmented generation → Medical and biomedical RAG
  41. EAC-MoE: Expert-Selection Aware Compressor for Mixture-of-Experts Large Language ModelsMixture-of-experts → MoE large language models
  42. A Multi-Agent Pokemon Tournament for Evaluating Strategic Reasoning of Large Language ModelsLLM reasoning → Reasoning for agents, planning and code +1
  43. VFP: Variational Flow-Matching Policy for Multi-Modal Robot ManipulationDiffusion models → Diffusion and flow policies for robotics +1
  44. IMU: Influence-guided Machine UnlearningLLM safety and security → Machine unlearning
  45. LLaDA-MedV: Exploring Large Language Diffusion Models for Biomedical Image UnderstandingMultimodal LLMs / vision-language models → Medical vision-language models +1
  46. Augmented Reinforcement Learning Framework For Enhancing Decision-Making In Machine Learning Models Using External AgentsDeep reinforcement learning methods → Deep RL algorithms and representations
  47. Practical, Generalizable and Robust Backdoor Attacks on Text-to-Image Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
  48. Enhancing Math Reasoning in Small-sized LLMs via Preview Difficulty-Aware InterventionLLM reasoning → Reinforcement learning for reasoning
  49. Drift-aware Collaborative Assistance Mixture of Experts for Heterogeneous Multistream LearningMixture-of-experts → Mixture of LoRA experts
  50. Self-Navigated Residual Mamba for Universal Industrial Anomaly DetectionState-space sequence models (S4, Mamba) → Time series forecasting with SSMs
  51. Censored Sampling for Topology Design: Guiding Diffusion with Human PreferencesDiffusion models → Flow matching, time series and science
  52. Diffusion Models for Future Networks and Communications: A Comprehensive SurveyDiffusion models → Diffusion for compression and wireless
  53. Polymorphic Combinatorial Frameworks (PCF): Guiding the Design of Mathematically-Grounded, Adaptive AI AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  54. LetheViT: Selective Machine Unlearning for Vision Transformers via Attention-Guided Contrastive LearningLLM safety and security → Machine unlearning
  55. One Subgoal at a Time: Zero-Shot Generalization to Arbitrary Linear Temporal Logic Requirements in Multi-Task Reinforcement LearningDeep reinforcement learning methods → Interpretable and logic-guided RL
  56. EvoVLMA: Evolutionary Vision-Language Model AdaptationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  57. RepoForge: Training a SOTA Fast-thinking SWE Agent with an End-to-End Data Curation Pipeline Synergizing SFT and RL at ScaleLLM reasoning → Reasoning for agents, planning and code +1
  58. A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  59. E-VRAG: Enhancing Long Video Understanding with Resource-Efficient Retrieval Augmented GenerationLLM reasoning → Multimodal reasoning +2
  60. Refine-n-Judge: Curating High-Quality Preference Chains for LLM-Fine-TuningLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  61. MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum LearningMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  62. ReasonAct: Progressive Training for Fine-Grained Video Reasoning in Small ModelsLLM reasoning → Multimodal reasoning
  63. Revisiting Gossip Protocols: A Vision for Emergent Coordination in Agentic Multi-Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  64. Towards High-Precision Depth Sensing via Monocular-Aided iToF and RGB Integration
  65. Harmonious Color Pairings: Insights from Human Preference and Natural Hue Statistics
  66. Human-AI collaboration or obedient and often clueless AI in instruct, serve, repeat dynamics?
  67. GlaBoost: A Multimodal Structured Framework for Glaucoma Risk Stratification
  68. Closed-Circuit Television Data as an Emergent Data Source for Urban Rail Platform Crowding Estimation
  69. Context-Adaptive Multi-Prompt Embedding with Large Language Models for Vision-Language Alignment
  70. Towards a Manifesto for Cyber Humanities: Paradigms, Ethics, and Prospects
  71. Hedging with memory: shallow and deep learning with signatures
  72. CTBench: Cryptocurrency Time Series Generation Benchmark
  73. Beyond the Wavefunction: Qualia Abstraction Language Mechanics and the Grammar of Awareness
  74. Pulse Shape Discrimination Algorithms: Survey and Benchmark
  75. Non-Verbal Vocalisations and their Challenges: Emotion, Privacy, Sparseness, and Real Life
  76. Stochastic Encodings for Active Feature Acquisition
  77. Scaling Clinician-Grade Feature Generation from Clinical Notes with Multi-Agent Language Models
  78. Flow-Aware GNN for Transmission Network Reconfiguration via Substation Breaker Optimization
  79. Inferring Reward Machines and Transition Machines from Partially Observable Markov Decision Processes
  80. Less is More: AMBER-AFNO -- a New Benchmark for Lightweight 3D Medical Image Segmentation
  81. CVD-SfM: A Cross-View Deep Front-end Structure-from-Motion System for Sparse Localization in Multi-Altitude Scenes
  82. Proactive Disentangled Modeling of Trigger-Object Pairings for Backdoor Defense
  83. IAUNet: Instance-Aware U-Net
  84. From Binary to Continuous: Stochastic Re-Weighting for Robust Graph Explanation
  85. Quantum-RAG and PunGPT2: Advancing Low-Resource Language Generation and Retrieval for the Punjabi Language
  86. L3M+P: Lifelong Planning with Large Language Models
  87. EgoTrigger: Toward Audio-Driven Image Capture for Human Memory Enhancement in All-Day Energy-Efficient Smart Glasses
  88. A Decentralized Framework for Ethical Authorship Validation in Academic Publishing: Leveraging Self-Sovereign Identity and Blockchain Technology
  89. Revisiting Replay and Gradient Alignment for Continual Pre-Training of Large Language Models
  90. IMUCoCo: Enabling Flexible On-Body IMU Placement for Human Pose Estimation and Activity Recognition
  91. How Does Controllability Emerge In Language Models During Pretraining?
  92. Medical Image De-Identification Resources: Synthetic DICOM Data and Tools for Validation
  93. Optimizing Day-Ahead Energy Trading with Proximal Policy Optimization and Blockchain
  94. Complete Evasion, Zero Modification: PDF Attacks on AI Text Detection
  95. DiffusionFF: A Diffusion-based Framework for Joint Face Forgery Detection and Fine-Grained Artifact Localization
  96. Multi-turn Natural Language to Graph Query Language Translation
  97. ProKG-Dial: Progressive Multi-Turn Dialogue Construction with Domain Knowledge Graphs
  98. Counterfactual Reciprocal Recommender Systems for User-to-User Matching
  99. Structure Maintained Representation Learning Neural Network for Causal Inference
  100. Fast Gaussian process inference by exact Mat'ern kernel decomposition
All 207
  1. Counterfactual Probing for Hallucination Detection and Mitigation in Large Language Models
  2. ACT-Tensor: Tensor Completion Framework for Financial Dataset Imputation
  3. Implicit Search Intent Recognition using EEG and Eye Tracking: Novel Dataset and Cross-User Prediction
  4. Moment Estimate and Variational Approach for Learning Generalized Diffusion with Non-gradient Structures
  5. Distinguishing Target and Non-Target Fixations with EEG and Eye Tracking in Realistic Visual Scenes
  6. Context Guided Transformer Entropy Modeling for Video Compression
  7. ChairPose: Pressure-based Chair Morphology Grounded Sitting Pose Estimation through Simulation-Assisted Training
  8. Causal Discovery in Multivariate Time Series through Mutual Information Featurization
  9. Test-Time Training for Speech Enhancement
  10. Beyond Vulnerabilities: A Survey of Adversarial Attacks as Both Threats and Defenses in Computer Vision Systems
  11. Towards Generalizable Context-aware Anomaly Detection: A Large-scale Benchmark in Cloud Environments
  12. OmniEvent: Unified Event Representation Learning
  13. A Simple Algebraic Solution for Estimating the Pose of a Camera from Planar Point Features
  14. Diffusion-based 3D Hand Motion Recovery with Intuitive Physics
  15. Efficient optimization of expensive black-box simulators via marginal means, with application to neutrino detector design
  16. Neural Predictive Control to Coordinate Discrete- and Continuous-Time Models for Time-Series Analysis with Control-Theoretical Improvements
  17. Large Kernel MedNeXt for Breast Tumor Segmentation and Self-Normalizing Network for pCR Classification in Magnetic Resonance Images
  18. Deep Learning-Driven Prediction of Microstructure Evolution via Latent Space Interpolation
  19. From Graph Retrieval to Schema Realization: Counterfactual Validation for Text-to-SPARQL over Heterogeneous Knowledge Graphs
  20. HeQ: a Large and Diverse Hebrew Reading Comprehension Benchmark
  21. Mitigating Persistent Client Dropout in Asynchronous Decentralized Federated Learning
  22. SoccerTrack v2: A Full-Pitch Panoramic Video Dataset for Game State Reconstruction and Ball Action Spotting
  23. Contrastive Multi-Task Learning with Solvent-Aware Augmentation for Drug Discovery
  24. CSLRConformer: A Data-Centric Conformer Approach for Continuous Arabic Sign Language Recognition on the Isharah Datase
  25. Sonify Anything: Towards Context-Aware Sonic Interactions in AR
  26. Skip priors and add graph-based anatomical information, for point-based Couinaud segmentation
  27. Joint Lossless Compression and Steganography for Medical Images via Large Language Models
  28. A comprehensive taxonomy of hallucinations in Large Language Models
  29. VAGPO: Vision-augmented Asymmetric Group Preference Optimization for Graph Routing Problems
  30. LoRA-based methods on Unet for transfer learning in Subarachnoid Hematoma Segmentation
  31. VPN: Visual Prompt Navigation
  32. A Trainable Optimizer
  33. Reasoning Systems as Structured Processes: Foundations, Failures, and Formal Criteria
  34. AI-Generated Text is Non-Stationary: Detection via Temporal Tomography
  35. Vision transformer-based multi-camera multi-object tracking framework for dairy cow monitoring
  36. Implementing Cumulative Functions with Generalized Cumulative Constraints
  37. Improving Noise Efficiency in Privacy-preserving Dataset Distillation
  38. Energy-Efficient Federated Learning for Edge Real-Time Vision via Joint Data, Computation, and Communication Design
  39. AGFT: An Adaptive GPU Frequency Tuner for Real-Time LLM Inference Optimization
  40. Intention-Guided Cognitive Reasoning for Egocentric Long-Term Action Anticipation
  41. AG2aussian: Anchor-Graph Structured Gaussian Splatting for Instance-Level 3D Scene Understanding and Editing
  42. Enhancing the Preference Extractor in Multi-turn Dialogues: From Annotating Disasters to Accurate Preference Extraction
  43. Topolow: Force-Directed Euclidean Embedding of Dissimilarity Data with Robustness Against Non-Metricity and Sparsity
  44. SpectralX: Parameter-efficient Domain Generalization for Spectral Remote Sensing Foundation Models
  45. Tracking the Unstable: Appearance-Guided Motion Modeling for Robust Multi-Object Tracking in UAV-Captured Videos
  46. ReflecSched: Solving Dynamic Flexible Job-Shop Scheduling via LLM-Powered Hierarchical Reflection
  47. Physics-Informed Policy Iteration for High-Dimensional Hamilton--Jacobi--Bellman Equations: Interior Error Bounds without Boundary Data
  48. Dynamic Robot-Assisted Surgery with Hierarchical Class-Incremental Semantic Segmentation
  49. HateClipSeg: A Segment-Level Annotated Dataset for Fine-Grained Hate Video Detection
  50. GAIS: Frame-Level Gated Audio-Visual Integration with Semantic Variance-Scaled Perturbation for Text-Video Retrieval
  51. Am I Blue or Is My Hobby Counting Teardrops? Expression Leakage in Large Language Models as a Symptom of Irrelevancy Disruption
  52. Density estimation with atoms, and functional estimation for mixed discrete-continuous data
  53. LT-Gaussian: Long-Term Map Update Using 3D Gaussian Splatting for Autonomous Driving
  54. MHARFedLLM: Multimodal Human Activity Recognition Using Federated Large Language Model
  55. Register Anything: Estimating "Corresponding Prompts" for Segment Anything Model
  56. SURE-Med: Systematic Uncertainty Reduction for Enhanced Reliability in Medical Report Generation
  57. Voxlect: A Speech Foundation Model Benchmark for Modeling Dialects and Regional Languages Around the Globe
  58. Explaining Time Series Classifiers with PHAR: Rule Extraction and Fusion from Post-hoc Attributions
  59. Innovative tokenisation of structured data for LLM training
  60. Generalized Kernelized Bandits: A Novel Self-Normalized Bernstein-Like Dimension-Free Inequality and Regret Bounds
  61. Benchmarking Adversarial Patch Selection and Location
  62. Asynchronous Federated Learning with non-convex client objective functions and heterogeneous dataset
  63. CUPID: Evaluating Personalized and Contextualized Alignment of LLMs from Interactions
  64. QCBench: Evaluating Large Language Models on Domain-Specific Quantitative Chemistry
  65. Bridging Generalization Gap of Heterogeneous Federated Clients Using Generative Models
  66. Measuring and Predicting Where and When Pathologists Focus their Visual Attention while Grading Whole Slide Images of Cancer
  67. Rein++: Efficient Generalization and Adaptation for Semantic Segmentation with Vision Foundation Models
  68. Single Point, Full Mask: Velocity-Guided Level Set Evolution for End-to-End Amodal Segmentation
  69. Authorship Attribution in Multilingual Machine-Generated Texts
  70. StrandDesigner: Towards Practical Strand Generation with Sketch Guidance
  71. SPARTA: Advancing Sparse Attention in Spiking Neural Networks via Spike-Timing-Based Prioritization
  72. DRKF: Decoupled Representations with Knowledge Fusion for Multimodal Emotion Recognition
  73. Minimal High-Resolution Patches Are Sufficient for Whole Slide Image Representation via Cascaded Dual-Scale Reconstruction
  74. Glass Surface Segmentation with an RGB-D Camera via Weighted Feature Fusion for Service Robots
  75. Semantic Encryption: Secure and Effective Interaction with Cloud-based Large Language Models via Semantic Transformation
  76. Privacy-Preserving Inference for Quantized BERT Models
  77. Reliable Microservice Tail Latency Prediction via Decoupled Dual-Stream Learning and Gradient Modulation
  78. Rate-distortion Optimized Point Cloud Preprocessing for Geometry-based Point Cloud Compression
  79. OpenMed NER: Open-Source, Domain-Adapted State-of-the-Art Transformers for Biomedical NER Across 12 Public Datasets
  80. TCDiff: Triplex Cascaded Diffusion for High-fidelity Multimodal EHRs Generation with Incomplete Clinical Data
  81. From Pixels to Places: A Systematic Benchmark for Evaluating Image Geolocalization Ability in Large Language Models
  82. Towards Generalizable AI-Generated Image Detection via Image-Adaptive Prompt Learning
  83. Enhancing Zero-Shot Brain Tumor Subtype Classification via Fine-Grained Patch-Text Alignment
  84. Heteroscedasticity of Denoising Score Matching with Generalised Smooth Noise
  85. CLIMD: A Curriculum Learning Framework for Imbalanced Multimodal Diagnosis
  86. DMTrack: Spatio-Temporal Multimodal Tracking via Dual-Adapter
  87. A Plug-and-Play Multi-Criteria Guidance for Diverse In-Betweening Human Motion Generation
  88. Beyond Discrete Samples: High Information Density Replay for Efficient Lifelong Person Re-Identification
  89. A Spatio-temporal Continuous Network for Stochastic 3D Human Motion Prediction
  90. Set Pivot Learning: Redefining Generalized Segmentation with Vision Foundation Models
  91. Dynamic Clustering for Personalized Federated Learning on Heterogeneous Edge Devices
  92. Harnessing Textual Semantic Priors for Knowledge Transfer and Refinement in CLIP-Driven Continual Learning
  93. Tractography-Guided Dual-Label Collaborative Learning for Multi-Modal Cranial Nerves Parcellation
  94. KANMixer: a minimal KAN-centered mixer for long-term time series forecasting
  95. TopoImages: Incorporating Local Topology Encoding into Deep Learning Models for Medical Image Classification
  96. Deeply Supervised Multi-Task Autoencoder for Biological Brain Age estimation using three dimensional T1-weighted magnetic resonance imaging
  97. Adaptive LiDAR Scanning: Harnessing Temporal Cues for Efficient 3D Object Detection via Multi-Modal Fusion
  98. Unsupervised Learning for the Elementary Shortest Path Problem
  99. Empowering Tabular Data Preparation with Language Models: Why and How?
  100. MGCR-Net:Multimodal Graph-Conditioned Vision-Language Reconstruction Network for Remote Sensing Change Detection
  101. Are All Prompt Components Value-Neutral? Understanding the Heterogeneous Adversarial Robustness of Dissected Prompt in Large Language Models
  102. Understanding Why ChatGPT Outperforms Humans in Visualization Design Advice
  103. Getting out of the Big-Muddy: Escalation of Commitment in LLMs
  104. Leveraging Machine Learning for Botnet Attack Detection in Edge-Computing Assisted IoT Networks
  105. MOPrompt: Multi-objective Semantic Evolution for Prompt Optimization
  106. FluidFormer: Transformer with Continuous Convolution for Particle-based Fluid Simulation
  107. MiraGe: Multimodal Discriminative Representation Learning for Generalizable AI-Generated Image Detection