mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sat 10 Jan 2026

159 papers

  1. Attribution Techniques for Mitigating Hallucinated Information in RAG Systems: A SurveyRetrieval-augmented generation → Hallucination detection in RAG
  2. Adaptive Orchestration: Scalable Self-Evolving Multi-Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  3. EmbeddingRWKV: State-Centric Retrieval with Reusable StatesRetrieval-augmented generation → Generation and context integration
  4. Diffusion Models with Heavy-Tailed Targets: Score Estimation and Sampling GuaranteesDiffusion models → Diffusion foundations and sampling
  5. Evaluating Accounting Reasoning Capabilities of Large Language ModelsLLM reasoning → Reasoning for agents, planning and code
  6. GRASP LoRA: GRPO Guided Adapter Sparsity Policy for Cross Lingual TransferLLM reasoning → Reasoning benchmarks and evaluation
  7. Plasticity vs. Rigidity: The Impact of Low-Rank Adapters on Reasoning on a Micro-BudgetLLM reasoning → Test-time compute and efficient thinking
  8. IDRBench: Benchmarking the Interactive Capabilities of Deep Research AgentsLLM agents and tool use → Web, search, and research agents
  9. Evaluating Cross-Lingual Unlearning in Multilingual Language ModelsLLM safety and security → Machine unlearning
  10. Reinforcement Learning-Guided Dynamic Multi-Graph Fusion for Evacuation Traffic PredictionDeep reinforcement learning methods → RL for autonomous driving and traffic
  11. SafePro: Evaluating the Safety of Professional-Level AI AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  12. Do Language Models Reason Across Languages?LLM reasoning → Reasoning benchmarks and evaluation
  13. Leveraging Soft Prompts for Privacy Attacks in Federated Prompt TuningLLM safety and security → Federated unlearning and poisoning
  14. Agentic AI Empowered Intent-Based Networking for 6GLLM agents and tool use → Agentic AI for wireless networks
  15. Attack-Resistant Watermarking for AIGC Image Forensics via Diffusion-based Semantic DeflectionLLM safety and security → Watermarking generated content and models
  16. CEDAR: Context Engineering for Agentic Data ScienceLLM agents and tool use → Web, search, and research agents
  17. Sissi: Zero-shot Style-guided Image Synthesis via Semantic-style IntegrationDiffusion models → Image generation, text-to-image and editing
  18. Object-Centric World Models Meet Monte Carlo Tree SearchWorld models → Latent predictive world models +1
  19. N2N-GQA: Noise-to-Narrative for Graph-Based Table-Text Question Answering Using LLMsLLM reasoning → Knowledge- and tool-augmented reasoning +1
  20. Probing Multimodal Large Language Models on Cognitive Biases in Chinese Short-Video MisinformationMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  21. Are LLMs Vulnerable to Preference-Undermining Attacks (PUA)? A Factorial Analysis Methodology for Diagnosing the Trade-off between Preference Alignment and Real-World ValidityLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  22. QMAVIS: Long Video-Audio Understanding using Fusion of Large Multimodal ModelsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  23. Hellinger Multimodal Variational AutoencodersMixture-of-experts → Multimodal MoE models
  24. QCaption: Video Captioning and Q&A through Fusion of Large Multimodal ModelsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  25. L-RAG: Balancing Context and Retrieval with Entropy-Based Lazy LoadingRetrieval-augmented generation → Generation and context integration
  26. Generative Semantic Multi-Object Tracking: A Large-Scale Benchmark and an MLLM-Driven Reasoning FrameworkLLM reasoning → Multimodal reasoning
  27. Self-Organizing Dual-Buffer Adaptive Clustering Experience Replay (SODACER) for Safe Reinforcement Learning in Optimal ControlDeep reinforcement learning methods → Deep RL algorithms and representations
  28. Short-term electricity load forecasting with multi-frequency reconstruction diffusionDiffusion models → Flow matching, time series and science
  29. BabyVision: Visual Reasoning Beyond LanguageLLM reasoning → Multimodal reasoning +1
  30. MedRAGChecker: Claim-Level Verification for Biomedical Retrieval-Augmented GenerationRetrieval-augmented generation → Medical and biomedical RAG
  31. Bridging Robustness and Efficiency: Real-Time Low-Light Enhancement via Attention U-Net GANDiffusion models → Inverse problems and image restoration
  32. Inference-Time Alignment for Diffusion Models via Variationally Stable Doob's MatchingDiffusion models → Diffusion foundations and sampling
  33. DRAGON: LLM-Driven Decomposition and Reconstruction Agents for Large-Scale Combinatorial OptimizationLLM agents and tool use → General LLM agent frameworks and benchmarks
  34. Spec-o3: A Tool-Augmented Vision-Language Agent for Rare Celestial Object Candidate Vetting via Automated Spectral InspectionLLM agents and tool use → Web, search, and research agents
  35. Bi-Mem: Bidirectional Construction of Hierarchical Memory for Personalized LLMs via Inductive-Reflective AgentsLLM agents and tool use → Agent memory systems
  36. ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative RankingLLM agents and tool use → Reinforcement learning for LLM agents +1
  37. Deriving Decoder-Free Sparse Autoencoders from First PrinciplesMechanistic interpretability → Sparse autoencoder training and evaluation
  38. SparseOccVLA: Bridging Occupancy and Vision-Language Models via Sparse Queries for Unified 4D Scene Understanding and PlanningLLM reasoning → Chain-of-thought reasoning for driving +1
  39. On the Adversarial Robustness of 3D Large Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  40. VIPER Strike: Defeating Visual Reasoning CAPTCHAs via Structured Vision-Language InferenceLLM reasoning → Multimodal reasoning
  41. Tone Matters: The Impact of Linguistic Tone on Hallucination in VLMsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  42. Architecting AgentOps Needs CHANGELLM agents and tool use → Software engineering coding agents
  43. ConSensus: Multi-Agent Collaboration for Multimodal SensingLLM agents and tool use → Multimodal and embodied agents
  44. Deep Reinforcement Learning based Control Design for Aircraft Recovery from Loss-of-Control ScenarioDeep reinforcement learning methods → RL for robot navigation and UAV control
  45. Certified Unlearning in Decentralized Federated LearningLLM safety and security → Federated unlearning and poisoning
  46. BackPlay: Head-Only Look-Back Self-Correction for Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  47. Can a Unimodal Language Agent Provide Preferences to Tune a Multimodal Vision-Language Model?Multimodal LLMs / vision-language models → MLLM training and visual instruction tuning +2
  48. Does Inference Scaling Improve Reasoning Faithfulness? A Multi-Model Analysis of Self-Consistency TradeoffsLLM reasoning → Test-time compute and efficient thinking
  49. Semantic Enrichment of CAD-Based Industrial Environments via Scene Graphs for Simulation and ReasoningLLM reasoning → Spatial and embodied reasoning
  50. Structured Episodic Event MemoryRetrieval-augmented generation → Agentic RAG, agents and memory
  51. Value of Information: A Framework for Human-Agent CommunicationLLM agents and tool use → General LLM agent frameworks and benchmarks
  52. HiMem: Hierarchical Long-Term Memory for LLM Long-Horizon AgentsLLM agents and tool use → Agent memory systems
  53. DemMA: Dementia Multi-Turn Dialogue Agent with Expert-Guided Reasoning and Action SimulationLLM reasoning → Clinical and biomedical applications +1
  54. A Methodology for Identifying Evaluation Items for Practical Dialogue Systems Based on Business-Dialogue System Alignment Models
  55. Scalable Board Expansion within a General Game System
  56. An Explainable Market Integrity Monitoring System with Multi-Source Attention Signals and Transparent Scoring
  57. Quality or Quantity? Error-Informed Selective Online Learning with Gaussian Processes in Multi-Agent Systems: Extended Version
  58. Divide and Refine: Enhancing Multimodal Representation and Explainability for Emotion Recognition in Conversation
  59. NoiseFormer -- Noise Diffused Symmetric Attention Transformer
  60. Architecture Before the Formula: Training-Dependent Computational Semantics in Transformers
  61. PointSLAM++: Robust Dense Neural Gaussian Point Cloud-based SLAM
  62. Line-based Event Preprocessing: Towards Low-Energy Neuromorphic Computer Vision
  63. Neuro-Symbolic Activation Discovery: Transferring Mathematical Structures from Physics to Ecology for Parameter-Efficient Neural Networks
  64. Informed Consent for AI Consciousness Research: A Talmudic Framework for Graduated Protections
  65. Imaging-anchored multiomics in cardiovascular disease: integrating cardiac imaging, bulk, single-cell, and spatial transcriptomics
  66. HOSC: A Periodic Activation with Saturation Control for High-Fidelity Implicit Neural Representations
  67. RewriteNets: End-to-End Trainable String-Rewriting for Generative Sequence Modeling
  68. Bridging the Trust Gap: Clinician-Validated Hybrid Explainable AI for Maternal Health Risk Assessment in Bangladesh
  69. DS-CIM: Digital Stochastic Computing-In-Memory Featuring Accurate OR-Accumulation via Sample Region Remapping for Edge AI Models
  70. Beyond Perfect Scores: Proof-by-Contradiction for Trustworthy Machine Learning
  71. Explainability of Complex AI Models with Correlation Impact Ratio
  72. Characterising Toxicity in Generative Large Language Models
  73. Quantification and Classification of Carbon Nanotubes in Electron Micrographs using Vision Foundation Models
  74. Will it Merge? On The Causes of Model Mergeability
  75. Otimizando A Alocacc~ao De Salas De Aula Com Foco Na Acessibilidade Para Pessoas Com Deficiencia
  76. InFi-Check: Interpretable and Fine-Grained Fact-Checking of LLMs
  77. What makes for an enjoyable protagonist? An analysis of character warmth and competence
  78. Physics-constrained Gaussian Processes for Predicting Shockwave Hugoniot Curves
  79. Revisiting Training Scale: An Empirical Study of Token Count, Power Consumption, and Parameter Efficiency
  80. eSkiTB: A Synthetic Event-based Dataset for Tracking Skiers
  81. A Multimodal Deep Learning Framework for Predicting ICU Deterioration: Integrating ECG Waveforms with Clinical Data and Clinician Benchmarking
  82. Boosting Overlapping Organoid Instance Segmentation Using Pseudo-Label Unmixing and Synthesis-Assisted Learning
  83. Efficient Aspect Term Extraction using Spiking Neural Network
  84. MedEinst: Benchmarking the Einstellung Effect in Medical LLMs through Counterfactual Differential Diagnosis
  85. KASER: Knowledge-Aligned Student Error Simulator for Open-Ended Coding Tasks
  86. Labels have Human Values: Value Calibration of Subjective Tasks
  87. Lower Bounds for the Algorithmic Complexity of Learned Indexes
  88. Burn-After-Use for Preventing Data Leakage through a Secure Multi-Tenant Architecture in Enterprise LLM
  89. Efficient and Reliable Estimation of Named Entity Linking Quality: A Case Study on GutBrainIE
  90. Cross-Border Data Security and Privacy Risks in Large Language Models and IoT Systems
  91. Pragya: An AI-Based Semantic Recommendation System for Sanskrit Subhasitas
  92. UMLoc: Uncertainty-Aware Map-Constrained Inertial Localization with Quantified Bounds
  93. How Context Shapes Truth: Geometric Transformations of Statement-level Truth Representations in LLMs
  94. Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective
  95. Detecting LLM-Generated Text with Performance Guarantees
  96. Softly Induced Functional Simplicity: Implications for Neural Network Generalisation, Robustness, and Distillation
  97. Stylistic Evolution and LLM Neutrality in Singlish Language
  98. Are Emotions Arranged in a Circle? Geometric Analysis of Emotion Representations via Hyperspherical Contrastive Learning
  99. APEX: Learning Adaptive Priorities for Multi-Objective Alignment in Vision-Language Generation
  100. EVM-QuestBench: An Execution-Grounded Benchmark for Natural-Language Transaction Code Generation
All 159
  1. CSR-RAG: An Efficient Retrieval System for Text-to-SQL on the Enterprise Scale
  2. Mosaic: Unlocking Long-Context Inference for Diffusion LLMs via Global Memory Planning and Dynamic Peak Taming
  3. ArrowGEV: Grounding Events in Video via Learning the Arrow of Time
  4. Robust Sparse Signal Recovery with Outliers: A Hard Thresholding Pursuit Approach Based on LAD
  5. Mechanism-Faithful Queueing Simulation Model Translation with Large Language Model Support
  6. Resource-constrained Project Scheduling with Time-of-Use Energy Tariffs and Machine States: A Logic-based Benders Decomposition Approach
  7. Towards Egocentric 3D Hand Pose Estimation in Unseen Domains
  8. Expos'ia: Teaching and Assessment of Academic Writing Skills for Research Project Proposals and Peer Feedback
  9. Improving Day-Ahead Grid Carbon Intensity Forecasting by Joint Modeling of Local-Temporal and Cross-Variable Dependencies Across Different Frequencies
  10. Atomic-SNLI: Fine-Grained Natural Language Inference through Atomic Fact Decomposition
  11. Toward Generalizable Deblurring: Leveraging Massive Blur Priors with Linear Attention for Real-World Scenarios
  12. Pareto-Optimal Model Selection for Low-Cost, Single-Lead EMG Control in Embedded Systems
  13. A novel RF-enabled Non-Destructive Inspection Method through Machine Learning and Programmable Wireless Environments
  14. Precision Meets Art: Autonomous Multi-UAV System for Large Scale Mural Drawing
  15. Neural Nonmyopic Bayesian Optimization in Dynamic Cost Settings
  16. The AI Pyramid A Conceptual Framework for Workforce Capability in the Age of AI
  17. Coding in a Bubble? Evaluating LLMs in Resolving Context Adaptation Bugs During Code Adaptation
  18. 3D CoCa v2: Contrastive Learners with Test-Time Search for Generalizable Spatial Intelligence
  19. Learning Domain Agnostic Latent Embeddings of 3D Faces for Zero-shot Animal Expression Transfer
  20. SRFlow: A Dataset and Regularization Model for High-Resolution Facial Optical Flow via Splatting Rasterization
  21. IndRegBias: A Dataset for Studying Indian Regional Biases in English and Code-Mixed Social Media Comments
  22. VVTRec: Radio Interferometric Reconstruction through Visual and Textual Modality Enrichment
  23. Hybrid LSTM-UKF Framework: Ankle Angle and Ground Reaction Force Estimation
  24. StablePDENet: Enhancing Neural Operator Stability through Physics-Informed Residual-Sensitivity Regularization
  25. PRISP: Privacy-Safe Few-Shot Personalization via Lightweight Adaptation
  26. R3D: Regional-guided Residual Radar Diffusion
  27. Gecko: An Efficient Neural Architecture Inherently Processing Sequences with Arbitrary Lengths
  28. Physics-informed Gaussian Process Regression in Solving Eigenvalue Problem of Linear Operators
  29. PixRec: Leveraging Visual Context for Next-Item Prediction in Sequential Recommendation
  30. CulinaryCut-VLAP: A Vision-Language-Action-Physics Framework for Food Cutting via a Force-Aware Material Point Method
  31. LitVISTA: A Benchmark for Narrative Orchestration in Literary Text
  32. Physics-Informed Tree Search for High-Dimensional Computational Design
  33. How to Build Robust, Scalable Models for GSV-Based Indicators in Neighborhood Research
  34. WHU-PCPR: A cross-platform heterogeneous point cloud dataset for place recognition in complex urban scenes
  35. FlexAct: Why Learn when you can Pick?
  36. Time Travel Engine: A Shared Latent Chronological Manifold Enables Historical Navigation in Large Language Models
  37. On a Gradient Approach to Chebyshev Center Problems with Applications to Function Learning
  38. LsrIF: Enhancing Logic-Structured Instruction Following of Large Language Models
  39. A Unified Shape-Aware Foundation Model for Time Series Classification
  40. NC-Bench: An LLM Benchmark for Evaluating Conversational Competence
  41. HiDVFS: Hierarchical Multi-Agent DVFS for Real-Time OpenMP DAG Workloads
  42. GlobalPaint: Spatiotemporal Coherent Video Outpainting with Global Feature Guidance
  43. Stitch the Fragments: One-Shot Hierarchical Federated Clustering
  44. Steer Model beyond Assistant: Controlling System Prompt Strength via Contrastive Decoding
  45. BizFinBench.v2: Towards Reliable LLMs in Finance via Real-User Data and Offline/Online Bilingual Evaluation
  46. MITRA: A Large-Scale Parallel Corpus and Multilingual Pretrained Language Model for Machine Translation and Semantic Retrieval for P=ali, Sanskrit, Buddhist Chinese, and Tibetan
  47. AfriqueLLM: How Data Mixing and Model Architecture Impact Continued Pre-training for African Languages
  48. Context Matters: Peer-Aware Student Behavioral Engagement Measurement via VLM Action Parsing and LLM Sequence Classification
  49. Continual Quantum Architecture Search with Tensor-Train Encoding: Theory and Applications to Signal Processing
  50. Object-WIPER : Training-Free Object and Associated Effect Removal in Videos
  51. Supervised and Unsupervised Neural Network Solver for First Order Hyperbolic Nonlinear PDEs
  52. Hierarchical Pooling and Explainability in Graph Neural Networks for Tumor and Tissue-of-Origin Classification Using RNA-seq Data
  53. Talking to Extraordinary Objects: Folktales Offer Analogies for Interacting with Technology
  54. From Easy to Hard++: Promoting Differentially Private Image Synthesis Through Spatial-Frequency Curriculum
  55. SafeGPT: Preventing Data Leakage and Unethical Outputs in Enterprise LLM Use
  56. Human-in-the-Loop Interactive Report Generation for Chronic Disease Adherence
  57. Do Implicit Personalization and Explicit Styles Conflict? PsPLUG: A Lightweight Plug-in for Balancing Personalization and Style in Customized LLMs
  58. Average shortest-path length in word-adjacency networks: Chinese versus English
  59. Computational Mapping of Reactive Stroma in Prostate Cancer Yields Interpretable, Prognostic Biomarkers