mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sun 11 Jan 2026

167 papers

  1. Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and FailuresLLM reasoning → Reinforcement learning for reasoning
  2. Explore with Long-term Memory: A Benchmark and Multimodal LLM-based Reinforcement Learning Framework for Embodied ExplorationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  3. Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD ConceptsLLM agents and tool use → Multimodal and embodied agents
  4. R2BD: A Reconstruction-Based Method for Generalizable and Efficient Detection of Fake ImagesDiffusion models → Image generation, text-to-image and editing
  5. Sola-Visibility-ISPM: Benchmarking Agentic AI for Identity Security Posture Management VisibilityLLM agents and tool use → Agent threats, guardrails and governance
  6. Efficient Visual Question Answering Pipeline for Autonomous Driving via Scene Region CompressionEnd-to-end autonomous driving → VLMs for autonomous driving
  7. When Should We Introduce Safety Interventions During Pretraining?LLM safety and security → Safety alignment, refusal and guardrails
  8. How Secure is Secure Code Generation? Adversarial Prompts Put LLM Defenses to the TestLLM safety and security → Jailbreaking
  9. Overcoming the Retrieval Barrier: Indirect Prompt Injection in the Wild for LLM SystemsLLM safety and security → Prompt injection and agent security
  10. PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic ManipulationVision-language-action models → Reasoning and chain-of-thought in VLA
  11. Dr. Zero: Self-Evolving Search Agents without Training DataLLM agents and tool use → Web, search, and research agents +1
  12. Fine-Tuning vs. RAG for Multi-Hop Question Answering with Novel KnowledgeLLM reasoning → Knowledge- and tool-augmented reasoning +1
  13. Mid-Think: Training-Free Intermediate-Budget Reasoning via Token-Level TriggersLLM reasoning → Test-time compute and efficient thinking
  14. Solar Open Technical ReportMixture-of-experts → MoE large language models
  15. Can Textual Reasoning Improve the Performance of MLLMs on Fine-grained Visual Classification?LLM reasoning → Multimodal reasoning +1
  16. MedTutor: A Retrieval-Augmented LLM System for Case-Based Medical EducationRetrieval-augmented generation → Medical and biomedical RAG
  17. UETQuintet at BioCreative IX -- MedHopQA: Enhancing Biomedical QA with Selective Multi-hop Reasoning and Contextual RetrievalLLM reasoning → Clinical and biomedical applications
  18. LLMs Can't Play Hangman: On the Necessity of a Private Working Memory for Language AgentsLLM agents and tool use → Agent memory systems
  19. A Robust Certified Machine Unlearning Method Under Distribution ShiftLLM safety and security → Machine unlearning
  20. Unified Personalized Understanding, Generating and EditingMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  21. SketchJudge: A Diagnostic Benchmark for Grading Hand-drawn Diagrams with Multimodal Large Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  22. Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video ReasoningLLM reasoning → Multimodal reasoning +1
  23. Forgetting Similar Samples: Can Machine Unlearning Do it Better?LLM safety and security → Machine unlearning
  24. mind_call: A Dataset for Mental Health Function Calling with Large Language ModelsLLM agents and tool use → Medical and scientific domain agents
  25. Measuring Social Bias in Vision-Language Models with Face-Only Counterfactuals from Real PhotosMultimodal LLMs / vision-language models → Social bias and fairness in VLMs
  26. RenderFlow: Single-Step Neural Rendering via Flow MatchingDiffusion models → 3D, point cloud and scene generation
  27. TreePS-RAG: Tree-based Process Supervision for Reinforcement Learning in Agentic RAGRetrieval-augmented generation → Agentic RAG, agents and memory +1
  28. PenForge: On-the-Fly Expert Agent Construction for Automated Penetration TestingLLM agents and tool use → Agent threats, guardrails and governance
  29. CLIMP: Contrastive Language-Image Mamba PretrainingState-space sequence models (S4, Mamba) → Vision Mamba backbones
  30. QASA: Quality-Aware Semantic Augmentation for Robust Multimodal Sentiment AnalysisMultimodal LLMs / vision-language models → Multimodal emotion understanding +1
  31. United We Defend: Collaborative Membership Inference Defenses in Federated LearningLLM safety and security → Federated unlearning and poisoning
  32. ET-Agent: Incentivizing Effective Tool-Integrated Reasoning Agent via Behavior CalibrationLLM reasoning → Reasoning for agents, planning and code +1
  33. MoE-DisCo:Low Economy Cost Training Mixture-of-Experts ModelsMixture-of-experts → Efficient MoE training and inference systems
  34. DAGGER: Distractor-Aware Graph Generation for Executable Reasoning in Math ProblemsLLM reasoning → Mathematical reasoning
  35. MedGround: Bridging the Evidence Gap in Medical Vision-Language Models with Verified Grounding DataMultimodal LLMs / vision-language models → Medical vision-language models
  36. Speak While Watching: Unleashing TRUE Real-Time Video Understanding Capability of Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  37. Seeing through the Conflict: Transparent Knowledge Conflict Handling in Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
  38. CHASE: LLM Agents for Dissecting Malicious PyPI PackagesLLM agents and tool use → Agent threats, guardrails and governance
  39. MoEScore: Mixture-of-Experts-Based Text-Audio Relevance Score Prediction for Text-to-Audio System EvaluationMixture-of-experts → Multimodal MoE models
  40. AgentHallu: Benchmarking Automated Hallucination Attribution of LLM-based AgentsLLM agents and tool use → Medical and scientific domain agents
  41. WFR-FM: Simulation-Free Dynamic Unbalanced Optimal TransportDiffusion models → Flow matching, time series and science
  42. Forest Before Trees: Latent Superposition for Efficient Visual ReasoningLLM reasoning → Multimodal reasoning +1
  43. Thinking with Deltas: Incentivizing Reinforcement Learning via Differential Visual Reasoning PolicyLLM reasoning → Multimodal reasoning
  44. CIRAG: Construction-Integration Retrieval and Adaptive Generation for Multi-hop Question AnsweringRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  45. GDEPO: Group Dual-dynamic and Equal-right Advantage Policy Optimization with Enhanced Training Data Utilization for Sample-Constrained Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning +1
  46. No More Stale Feedback: Co-Evolving Critics for Open-World Agent LearningLLM agents and tool use → Reinforcement learning for LLM agents
  47. SecMoE: Communication-Efficient Secure MoE Inference via Select-Then-ComputeMixture-of-experts → Expert routing strategies
  48. EpiCaR: Knowing What You Don't Know Matters for Better Reasoning in LLMsLLM reasoning → Test-time compute and efficient thinking +1
  49. CyberLLM-FINDS 2025: Instruction-Tuned Fine-tuning of Domain-Specific LLMs with Retrieval-Augmented Generation and Graph Integration for MITRE EvaluationRetrieval-augmented generation → Privacy and security of RAG
  50. From Text to Simulation: A Multi-Agent LLM Workflow for Automated Chemical Process DesignLLM agents and tool use → Medical and scientific domain agents
  51. GanitLLM: Difficulty-Aware Bengali Mathematical Reasoning through Curriculum-GRPOLLM reasoning → Mathematical reasoning
  52. MTMCS-Bench: Evaluating Contextual Safety of Multimodal Large Language Models in Multi-Turn DialoguesMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  53. Benchmarking Egocentric Clinical Intent Understanding Capability for Medical Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Medical vision-language models
  54. On-the-Fly VLA Adaptation via Test-Time Reinforcement LearningVision-language-action models → Reinforcement learning and post-training
  55. Vextra: A Unified Middleware Abstraction for Heterogeneous Vector Database SystemsRetrieval-augmented generation → RAG pipeline design and evaluation
  56. Assessing LLM Response Quality in the Context of Technology-Facilitated Abuse
  57. AI Hallucination from Students' Perspective: A Thematic Analysis
  58. SDUs DAISY: A Benchmark for Danish Culture
  59. Stingy Context: 18:1 Hierarchical Code Compression for LLM Auto-Coding
  60. Which Quantization Should I Use? A Unified Evaluation of llama.cpp Quantization on Llama-3.1-8B-Instruct
  61. Dynamical Systems Analysis Reveals Functional Regimes in Large Language Models
  62. A Mind Cannot Be Smeared Across Time
  63. UBiGTLoc: A Unified BiLSTM-Graph Transformer Localization Framework for IoT Sensor Networks
  64. Enhancing Formal Software Specification with Artificial Intelligence
  65. First African Digital Humanism Summer School 2025
  66. AI Deployment Authorisation: A Global Standard for Machine-Readable Governance of High-Risk Artificial Intelligence
  67. Residual Cross-Modal Fusion Networks for Audio-Visual Navigation
  68. Tackling Heterogeneity in Quantum Federated Learning: An Integrated Sporadic-Personalized Approach
  69. Sliced-Wasserstein Distribution Alignment Loss Improves the Ultra-Low-Bit Quantization of Large Language Models
  70. E^2-LLM: Bridging Neural Signals and Interpretable Affective Analysis
  71. NOVAK: Unified adaptive optimizer for deep neural networks
  72. Multiplicative Orthogonal Sequential Editing for Language Models
  73. Robust Bayesian Optimization via Tempered Posteriors
  74. 3D Wavelet-Based Structural Priors for Controlled Diffusion in Whole-Body Low-Dose PET Denoising
  75. XBTorch: A Unified Framework for Modeling and Co-Design of Crossbar-Based Deep Learning Accelerators
  76. The AI Cognitive Trojan Horse: How Large Language Models May Bypass Human Epistemic Vigilance
  77. Robust Mean Estimation under Quantization
  78. Billboard in Focus: Estimating Driver Gaze Duration from a Single Image
  79. Automated Domain Question Mapping (DQM) with Educational Learning Materials
  80. Local EGOP for Continuous Index Learning
  81. Hallucinations Live in Variance
  82. Adversarial Attacks on Medical Hyperspectral Imaging Exploiting Spectral-Spatial Dependencies and Multiscale Features
  83. GPU-Accelerated ANNS: Quantized for Speed, Built for Change
  84. Engineering of Hallucination in Generative AI: It's not a Bug, it's a Feature
  85. When Abundance Conceals Weakness: Knowledge Conflict in Multilingual Models
  86. Task Arithmetic with Support Languages for Low-Resource ASR
  87. Explainable Deep Radiogenomic Molecular Imaging for MGMT Methylation Prediction in Glioblastoma
  88. Codified Foreshadowing-Payoff Text Generation
  89. CloneMem: Benchmarking Long-Term Memory for AI Clones
  90. Tight Analysis of Decentralized SGD: A Markov Chain Perspective
  91. TurkBench: A Benchmark for Evaluating Turkish Large Language Models
  92. Zer0n: An AI-Assisted Vulnerability Discovery and Blockchain-Backed Integrity Framework
  93. Belief in False Information: A Human-Centered Security Risk in Sociotechnical Systems
  94. Conditional Normalizing Flows for Forward and Backward Joint State and Parameter Estimation
  95. Lexicalized Constituency Parsing for Middle Dutch: Low-resource Training and Cross-Domain Generalization
  96. LLM Performance Predictors: Learning When to Escalate in Hybrid Human-AI Moderation Systems
  97. MicLog: Towards Accurate and Efficient LLM-based Log Parsing via Progressive Meta In-Context Learning
  98. MemTrust: A Zero-Trust Architecture for Unified AI Memory System
  99. Unity Forests: Improving Interaction Modelling and Interpretability in Random Forests
  100. Spatial Multi-Task Learning for Breast Cancer Molecular Subtype Prediction from Single-Phase DCE-MRI
All 167
  1. ObjSplat: Geometry-Aware Gaussian Surfels for Active Object Reconstruction
  2. FinCARDS: Card-Based Analyst Reranking for Financial Document Question Answering
  3. Match Made with Matrix Completion: Efficient Learning under Matching Interference
  4. Benchmarking Autonomy in Scientific Experiments: A Hierarchical Taxonomy for Autonomous Large-Scale Facilities
  5. Categorize Early, Integrate Late: Divergent Processing Strategies in Automatic Speech Recognition
  6. Generalization Bounds for Transformer Channel Decoders
  7. RealMem: Benchmarking LLMs in Real-World Memory-Driven Interaction
  8. The Impact of Anisotropic Covariance Structure on the Training Dynamics and Generalization Error of Linear Networks
  9. HAS-VQ: Hessian-Adaptive Sparse Vector Quantization for High-Fidelity LLM Compression
  10. X-Coder: Advancing Competitive Programming with Synthetic Tasks, Solutions, and Tests
  11. Towards Operational Streamflow Forecasting in the Limpopo River Basin using Long Short-Term Memory Networks
  12. VISTA: Knowledge-Driven Vessel Trajectory Imputation with Repair Provenance
  13. Symphonym: Universal Phonetic Embeddings for Cross-Script Toponym Matching
  14. Active Learning Strategies for Efficient Machine-Learned Interatomic Potentials Across Diverse Material Systems
  15. Towards Compositional Generalization in LLMs for Smart Contract Security: A Case Study on Reentrancy Vulnerabilities
  16. Tractable Multinomial Logit Contextual Bandits with Non-Linear Utilities
  17. Distributional Clarity: The Hidden Driver of RL-Friendliness in Large Language Models
  18. UDPNet: Unleashing Depth-based Priors for Robust Image Dehazing
  19. Fine-grained Verbal Attack Detection via a Hierarchical Divide-and-Conquer Framework
  20. V2P: Visual Attention Calibration for GUI Grounding via Background Suppression and Center Peaking
  21. TagSpeech: End-to-End Multi-Speaker ASR and Diarization with Fine-Grained Temporal Grounding
  22. Paraphrasing Adversarial Attack on LLM-as-a-Reviewer
  23. MixRI: Mixing Features of Reference Images for Novel Object Pose Estimation
  24. Unsupervised Domain Adaptation with SAM-RefiSeR for Enhanced Brain Tumor Segmentation
  25. Personality-Aware Reinforcement Learning for Persuasive Dialogue with LLM-Driven Simulation
  26. An Ubuntu-Guided Large Language Model Framework for Cognitive Behavioral Mental Health Dialogue
  27. MVGGT: Multimodal Visual Geometry Grounded Transformer for Multiview 3D Referring Expression Segmentation
  28. Applying Embedding-Based Retrieval to Airbnb Search
  29. U-MASK: User-adaptive Spatio-Temporal Masking for Personalized Mobile AI Applications
  30. Learning QoE from Packet-Level Measurements in Encrypted Video Conferencing Traffic
  31. BiasLab: A Multilingual Dual-Framing Framework for LLM Bias Measurement, Applied to Workplace and HR Contexts
  32. Deep Learning-Based Channel Extrapolation for Dual-Band Massive MIMO Systems
  33. A Brain-like Synergistic Core in LLMs Drives Behaviour and Learning
  34. Explainable Multimodal Aspect-Based Sentiment Analysis with Dependency-guided Large Language Model
  35. Code Evolution for Control: Synthesizing Policies via LLM-Driven Evolutionary Search
  36. Variational decomposition autoencoding improves disentanglement of latent representations
  37. PRISM: Color-Stratified Point Cloud Sampling
  38. OSCAR: Optical-aware Semantic Control for Aleatoric Refinement in Sar-to-Optical Translation
  39. Enhancing Low-resolution Image Representation Through Normalizing Flows
  40. SARA: Scene-Aware Reconstruction Accelerator
  41. Constrained Density Estimation via Optimal Transport
  42. PDR: A Plug-and-Play Positional Decay Framework for LLM Pre-training Data Detection
  43. Analyzing the effect of prediction accuracy on the distributionally-robust competitive ratio
  44. SpatialNav: Leveraging Spatial Scene Graphs for Zero-Shot Vision-and-Language Navigation
  45. Doing More with Less: Data Augmentation for Sudanese Dialect Automatic Speech Recognition
  46. Graph Neural Network with One-side Edge Sampling for Fraud Detection
  47. CliffordNet: All You Need is Geometric Algebra
  48. Cross-Modal Computational Model of Brain-Heart Interactions via HRV and EEG Feature
  49. MemGovern: Enhancing Code Agents through Learning from Governed Human Experiences
  50. Artificial Entanglement in the Fine-Tuning of Large Language Models
  51. Garbage Attention in Large Language Models: BOS Sink Heads and Sink-aware Pruning
  52. Dimension-reduced outcome-weighted learning for estimating individualized treatment regimes in observational studies
  53. AutoTour: Automatic Photo Tour Guide with Smartphones and LLMs
  54. Multi-Stage Evolutionary Model Merging with Meta Data Driven Curriculum Learning for Sentiment-Specialized Large Language Modeling
  55. The Normalized Difference Layer: A Differentiable Spectral Index Formulation for Deep Learning
  56. Structure-preserving learning and prediction in optimal control of collective motion
  57. ALFA: A Safe-by-Design Approach to Mitigate Quishing Attacks Launched via Fancy QR Codes
  58. Comparative Separation: Evaluating Separation on Comparative Judgment Test Data
  59. A Backpropagation-Free Feedback-Hebbian Network for Continual Learning Dynamics
  60. Towards Computational Chinese Paleography
  61. FinForge: Semi-Synthetic Financial Benchmark Generation
  62. Federated Continual Learning for Privacy-Preserving Hospital Imaging Classification
  63. Logic-Driven Semantic Communication for Resilient Multi-Agent Systems
  64. Why are there many equally good models? An Anatomy of the Rashomon Effect
  65. Predicting Student Success with Heterogeneous Graph Deep Learning and Machine Learning Models
  66. USFetal: Tools for Fetal Brain Ultrasound Compounding
  67. When Humans Judge Irises: Pupil Size Normalization as an Aid and Synthetic Irises as a Challenge