mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sun 26 Oct 2025

209 papers

  1. Feature-Guided SAE Steering for Refusal-Rate Control using Contrasting PromptsMechanistic interpretability → Steering and probing for LLM safety
  2. Sparsity and Superposition in Mixture of ExpertsMixture-of-experts → MoE large language models
  3. Agentsway -- Software Development Methodology for AI Agents-based TeamsLLM agents and tool use → Software engineering coding agents
  4. Aligning Diffusion Language Models via Unpaired Preference OptimizationDiffusion models → Diffusion and flow policies for robotics +1
  5. Correctness Forensics for Batch Speculative Decoding: Diagnosing the Ragged Tensor ProblemEfficient LLM inference and serving → Speculative decoding
  6. Seeing the Unseen: Towards Training-Free Inspection for Wind Turbine Blades Using Knowledge-Augmented Vision Language ModelsMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  7. Far from the Shallow: Brain-Predictive Reasoning Embedding through Residual DisentanglementLLM reasoning → Reasoning benchmarks and evaluation
  8. Guardian: Decoupling Exploration from Safety in Reinforcement LearningDeep reinforcement learning methods → Safe and constrained RL
  9. Encoder-Decoder Diffusion Language Models for Efficient Training and InferenceDiffusion models → Discrete and text diffusion
  10. Semantic Surgery: Zero-Shot Concept Erasure in Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
  11. Once Upon an Input: Reasoning via Per-Instance Program SynthesisLLM reasoning → Test-time compute and efficient thinking
  12. Lyapunov Function-guided Reinforcement Learning for Flight ControlDeep reinforcement learning methods → RL for robot navigation and UAV control
  13. Semantic-Preserving Cross-Style Visual Reasoning for Robust Multi-Modal Understanding in Large Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
  14. Rethinking the Text-Vision Reasoning Imbalance in MLLMs through the Lens of Training RecipesLLM reasoning → Multimodal reasoning +1
  15. Toward Agents That Reason About Their ComputationDeep reinforcement learning methods → RL training of language and agent models
  16. HRM-Agent: Training a recurrent reasoning model in dynamic environments using reinforcement learningLLM reasoning → Reasoning for agents, planning and code
  17. VEHME: A Vision-Language Model For Evaluating Handwritten Mathematics ExpressionsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  18. Collaborative LLM Agents for C4 Software Architecture Design AutomationLLM agents and tool use → Software engineering coding agents
  19. Self-Calibrated Consistency can Fight Back for Adversarial Robustness in Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  20. Agentic Meta-Orchestrator for Multi-task CopilotsLLM agents and tool use → General LLM agent frameworks and benchmarks
  21. Free Denoising Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  22. Scalable Supervision for Software Agents via Patch ReasoningLLM reasoning → Reasoning for agents, planning and code +1
  23. Seeing is Believing? Evaluating Vision-Language Model Susceptibility in Agent-to-Agent Multimodal PersuasionMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning +1
  24. Jarvis: Towards Personalized AI Assistant via Personal KV-Cache RetrievalLLM reasoning → Multimodal reasoning +2
  25. Policies over Poses: Reinforcement Learning based Distributed Pose-Graph Optimization for Multi-Robot SLAMDeep reinforcement learning methods → RL for robot navigation and UAV control
  26. WebATLAS: An LLM Agent with Experience-Driven Memory and Action SimulationLLM agents and tool use → Web, search, and research agents
  27. S-Chain: Structured Visual Chain-of-Thought For MedicineLLM reasoning → Clinical and biomedical applications +1
  28. Scalable Neural Decoders for Practical Real-Time Quantum Error CorrectionState-space sequence models (S4, Mamba) → Core SSM architectures for language
  29. RaCoT: Plug-and-Play Contrastive Example Generation Mechanism for Enhanced LLM Reasoning ReliabilityLLM reasoning → Knowledge- and tool-augmented reasoning +1
  30. RL-AVIST: Reinforcement Learning for Autonomous Visual Inspection of Space TargetsDeep reinforcement learning methods → RL for robot navigation and UAV control
  31. Windsock is Dancing: Adaptive Multimodal Retrieval-Augmented GenerationMultimodal LLMs / vision-language models → Document understanding and multimodal RAG +1
  32. Rule-Based Explanations for Retrieval-Augmented LLM SystemsRetrieval-augmented generation → RAG pipeline design and evaluation
  33. FlowCritic: Bridging Value Estimation with Flow Matching in Reinforcement LearningDiffusion models → Diffusion and flow policies for robotics +1
  34. SARVLM: A Vision Language Foundation Model for Semantic Understanding in SAR ImageryMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  35. Self-Attention Decomposition For Training Free Diffusion EditingDiffusion models → Image generation, text-to-image and editing
  36. FastVLM: Self-Speculative Decoding for Fast Vision-Language Model InferenceMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  37. Culturally Grounded Physical Commonsense Reasoning in Italian and English: A Submission to the MRL 2025 Shared TaskLLM reasoning → Reasoning benchmarks and evaluation
  38. Sentra-Guard: A Real-Time Multilingual Defense Against Adversarial LLM PromptsLLM safety and security → Jailbreaking
  39. SwiftSolve: A Self-Iterative, Complexity-Aware Multi-Agent Framework for Competitive ProgrammingLLM agents and tool use → Software engineering coding agents
  40. Breaking Agent Backbones: Evaluating the Security of Backbone LLMs in AI AgentsLLM agents and tool use → Agent threats, guardrails and governance
  41. PerCoR: Evaluating Commonsense Reasoning in Persian via Multiple-Choice Sentence CompletionLLM reasoning → Reasoning benchmarks and evaluation
  42. Everything Counts: The Managed Omnirelevance of Speech in Human-Voice Agent InteractionLLM agents and tool use → General LLM agent frameworks and benchmarks
  43. STATUS Bench: A Rigorous Benchmark for Evaluating Object State Understanding in Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  44. Curriculum-Based Iterative Self-Play for Scalable Multi-Drone RacingDeep reinforcement learning methods → RL for robot navigation and UAV control
  45. A Closed-Loop Personalized Learning Agent Integrating Neural Cognitive Diagnosis, Bounded-Ability Adaptive Testing, and LLM-Driven FeedbackLLM agents and tool use → Educational agents and math problem solving
  46. SABlock: Semantic-Aware KV Cache Eviction with Adaptive Compression Block SizeEfficient LLM inference and serving → KV cache optimization
  47. FAPO: Flawed-Aware Policy Optimization for Efficient and Reliable ReasoningLLM reasoning → Reinforcement learning for reasoning
  48. OFFSIDE: Benchmarking Unlearning Misinformation in Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  49. Ant-inspired Walling Strategies for Scalable Swarm Separation: Reinforcement Learning Approaches Based on Finite State MachinesDeep reinforcement learning methods → RL for robot navigation and UAV control
  50. Open Multimodal Retrieval-Augmented Factual Image GenerationMultimodal LLMs / vision-language models → Document understanding and multimodal RAG +1
  51. Transitive RL: Value Learning via Divide and ConquerDeep reinforcement learning methods → Deep RL algorithms and representations
  52. CANDI: Hybrid Discrete-Continuous Diffusion ModelsDiffusion models → Discrete and text diffusion
  53. Tailoring Reproducing Kernels for Optimal Control via Policy IterationDeep reinforcement learning methods → RL theory and sample complexity
  54. Single-Teacher View Augmentation: Boosting Knowledge Distillation via Angular DiversityKnowledge distillation → General knowledge distillation methods
  55. Learning "Partner-Aware" Collaborators in Multi-Party CollaborationLLM agents and tool use → General LLM agent frameworks and benchmarks
  56. Human-Centred Evaluation of Text-to-Image Generation Models for Self-expression of Mental Distress: A Dataset Based on GPT-4o
  57. Ming-UniAudio: Speech LLM for Joint Understanding, Generation and Editing with Unified Representation
  58. Adaptive Testing for LLM Evaluation: A Psychometric Alternative to Static Benchmarks
  59. Benchmarking ResNet for Short-Term Hypoglycemia Classification with DiaData
  60. EEGReXferNet: A Lightweight Gen-AI Framework for EEG Subspace Reconstruction via Cross-Subject Transfer Learning and Channel-Aware Embedding
  61. Mutual Information guided Visual Contrastive Learning
  62. Position Paper: If Innovation in AI Systematically Violates Fundamental Rights, Is It Innovation at All?
  63. On the Structure of Floating-Point Noise in Batch-Invariant GPU Matrix Multiplication
  64. Chitchat with AI: Understand the supply chain carbon disclosure of companies worldwide through Large Language Model
  65. Towards Piece-by-Piece Explanations for Chess Positions with SHAP
  66. Pulsar Detection with Deep Learning
  67. Sub-microsecond Transformers for Jet Tagging on FPGAs
  68. AI & Data Competencies: Scaffolding holistic AI literacy in Higher Education
  69. What Work is AI Actually Doing? Uncovering the Drivers of Generative AI Adoption
  70. Traffic flow forecasting, STL decomposition, Hybrid model, LSTM, ARIMA, XGBoost, Intelligent transportation systems
  71. Optimize Any Topology: A Foundation Model for Shape- and Resolution-Free Structural Topology Optimization
  72. Beyond Normality: Reliable A/B Testing with Non-Gaussian Data
  73. Transformers from Compressed Representations
  74. AI-Driven Carbon Monitoring: Transformer-Based Reconstruction of Atmospheric CO2 in Canadian Poultry Regions
  75. JiuTian Chuanliu: A Large Spatiotemporal Model for General-purpose Dynamic Urban Sensing
  76. Quanvolutional Neural Networks for Pneumonia Detection: An Efficient Quantum-Assisted Feature Extraction Paradigm
  77. Quantum Machine Learning for Image Classification: A Hybrid Model of Residual Network with Quantum Support Vector Machine
  78. A machine learning framework integrating seed traits and plasma parameters for predicting germination uplift in crops
  79. A Comprehensive Dataset for Human vs. AI Generated Text Detection
  80. Interpreting and Mitigating Unwanted Uncertainty in LLMs
  81. Long-Term PM2.5 Forecasting Using a DTW-Enhanced CNN-GRU Model
  82. A Review of Neural Networks in Precipitation Prediction
  83. Self-induced stochastic resonance: A physics-informed machine learning approach
  84. Leveraging Large Language Models to Identify Conversation Threads in Collaborative Learning
  85. FastJAM: a Fast Joint Alignment Model for Images
  86. Clustering by Denoising: Latent plug-and-play diffusion for single-cell data
  87. Exploration of Summarization by Generative Language Models for Automated Scoring of Long Essays
  88. LLM-based Fusion of Multi-modal Features for Commercial Memorability Prediction
  89. Efficiently Learning Synthetic Control Models for High-dimensional Disaggregated Data
  90. FairJudge: Abstention-Aware Multimodal Judges for Fairness and Alignment Evaluation in Text-to-Image Models
  91. Logical GANs: Adversarial Learning through Ehrenfeucht Fraisse Games
  92. Cross-Lingual Stability and Bias in Instruction-Tuned Language Models for Humanitarian NLP
  93. Last-Iterate Analyses of FTRL with the 1/2-Tsallis Entropy in Stochastic Bandits
  94. Air Quality Prediction Using LOESS-ARIMA and Multi-Scale CNN-BiLSTM with Residual-Gated Attention
  95. Will Humanity Be Rendered Obsolete by AI?
  96. Distributed Multi-Agent Bandits Over ErdHos-R'enyi Random Networks
  97. MAGIC-Talk: Motion-aware Audio-Driven Talking Face Generation with Customizable Identity Control
  98. A Theory of the Mechanics of Information: Generalization Through Measurement of Uncertainty (Learning is Measuring)
  99. MedXplain-VQA: Multi-Component Explainable Medical Visual Question Answering
  100. Inductive Transfer Learning for Graph-Based Recommenders
All 209
  1. SAO-Instruct: Free-form Audio Editing using Natural Language Instructions
  2. PIP-LLM: Integrating PDDL-Integer Programming with LLMs for Coordinating Multi-Robot Teams Using Natural Language
  3. How Do AI Agents Do Human Work? Comparing AI and Human Workflows Across Diverse Occupations
  4. SeeDNorm: Self-Rescaled Dynamic Normalization
  5. Neural-HAR: A Dimension-Gated CNN Accelerator for Real-Time Radar Human Activity Recognition
  6. TELL-TALE: Task Efficient LLMs with Task Aware Layer Elimination
  7. Iterative Layer Pruning for Efficient Translation Inference
  8. Understanding What Is Not Said:Referring Remote Sensing Image Segmentation with Scarce Expressions
  9. EchoMind: An Interrelated Multi-level Benchmark for Evaluating Empathetic Speech Language Models
  10. Distributionally Robust Optimization via Diffusion Ambiguity Modeling
  11. Beyond Semantics: How Temporal Biases Shape Retrieval in Transformer and State-Space Models
  12. Multi-Modal Fact-Verification Framework for Reducing Hallucinations in Large Language Models
  13. Low-Resource Dialect Adaptation of Large Language Models: A French Dialect Case-Study
  14. OEUVRE: OnlinE Unbiased Variance-Reduced loss Estimation
  15. ConMatFormer: A Multi-attention and Transformer Integrated ConvNext based Deep Learning Model for Enhanced Diabetic Foot Ulcer Classification
  16. REVISION:Reflective Intent Mining and Online Reasoning Auxiliary for E-commerce Visual Search System Optimization
  17. Cross-view Localization and Synthesis -- Datasets, Challenges and Opportunities
  18. Centrum: Model-based Database Auto-tuning with Minimal Distributional Assumptions
  19. E2Rank: Unifying Text Embedding and Listwise Reranking for Effective and Efficient Search
  20. Critical Insights into Leading Conversational AI Models
  21. Edge Collaborative Gaussian Splatting with Integrated Rendering and Communication
  22. LRW-Persian: Lip-reading in the Wild Dataset for Persian Language
  23. Step2Motion: Locomotion Reconstruction from Pressure Sensing Insoles
  24. Identification of Causal Direction under an Arbitrary Number of Latent Confounders
  25. IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction
  26. Atlas Urban Index: A VLM-Based Approach for Spatially and Temporally Calibrated Urban Development Monitoring
  27. WaveMAE: Wavelet decomposition Masked Auto-Encoder for Remote Sensing
  28. VADTree: Explainable Training-Free Video Anomaly Detection via Hierarchical Granularity-Aware Tree
  29. SALSA: Single-pass Autoregressive LLM Structured Classification
  30. TABL-ABM: A Hybrid Framework for Synthetic LOB Generation
  31. RoboSVG: A Unified Framework for Interactive SVG Generation with Multi-modal Guidance
  32. Estimation of Fireproof Structure Class and Construction Year for Disaster Risk Assessment
  33. Uncertainty-Aware Autonomous Vehicles: Predicting the Road Ahead
  34. Do Stop Me Now: Detecting Boilerplate Responses with a Single Iteration
  35. DAMap: Distance-aware MapNet for High Quality HD Map Construction
  36. Alias-Free ViT: Fractional Shift Invariance via Linear Attention
  37. Look and Tell: A Dataset for Multimodal Grounding Across Egocentric and Exocentric Views
  38. LVD-GS: Gaussian Splatting SLAM for Dynamic Scenes via Hierarchical Explicit-Implicit Representation Collaboration Rendering
  39. Block Coordinate Descent for Neural Networks Provably Finds Global Minima
  40. Conjugate Relation Modeling for Few-Shot Knowledge Graph Completion
  41. Learning Without Augmenting: Unsupervised Time Series Representation Learning via Frame Projections
  42. Managing Self-Learning Experts under Per-Round Budget Constraints
  43. If You Want to Be Robust, Be Wary of Initialization
  44. Variational Polya Tree
  45. A Critical Study on Tea Leaf Disease Detection using Deep Learning Techniques
  46. Enhancing Graph Classification Robustness with Singular Pooling
  47. Environment-aware Motion Matching
  48. Robust Atypical Mitosis Classification with DenseNet121: Stain-Aware Augmentation and Hybrid Loss for Domain Generalization
  49. Integrating Linguistics and AI: Morphological Analysis and Corpus development of Endangered Toto Language of West Bengal
  50. DeepfakeBench-MM: A Comprehensive Benchmark for Multimodal Deepfake Detection
  51. CLEANet: Robust and Efficient Anomaly Detection in Contaminated Multivariate Time Series
  52. Cross-Species Transfer Learning in Agricultural AI: Evaluating ZebraPose Adaptation for Dairy Cattle Pose Estimation
  53. Does In-IDE Calibration of Large Language Models work at Scale?
  54. CLIN-LLM: A Safety-Constrained Hybrid Framework for Clinical Diagnosis and Treatment Generation
  55. SWAN: Self-supervised Wavelet Neural Network for Hyperspectral Image Unmixing
  56. Projection Embedded Diffusion Bridge for CT Reconstruction from Incomplete Data
  57. Mitigating Attention Sinks and Massive Activations in Audio-Visual Speech Recognition with LLMs
  58. Personal Care Utility (PCU): Building the Health Infrastructure for Everyday Insight and Guidance
  59. RoGER-SLAM: A Robust Gaussian Splatting SLAM System for Noisy and Low-light Environment Resilience
  60. A roadmap for curvature-based geometric data analysis and learning
  61. A Framework for Quantifying How Pre-Training and Context Benefit In-Context Learning
  62. AutoBench: Automating LLM Evaluation through Reciprocal Peer Assessment
  63. ATOM: AdapTive and OptiMized dynamic temporal knowledge graph construction using LLMs
  64. PSScreen V2: Partially Supervised Multiple Retinal Disease Screening
  65. UltraVoice: Scaling Fine-Grained Style-Controlled Speech Conversations for Spoken Dialogue Models
  66. Prediction-Powered Semi-Supervised Learning with Online Power Tuning
  67. MobileGeo: Exploring Hierarchical Knowledge Distillation for Resource-Efficient Cross-view Drone Geo-Localization
  68. Pedagogy-driven Evaluation of Generative AI-powered Intelligent Tutoring Systems
  69. Optimal Anytime Algorithms for Online Convex Optimization with Adversarial Constraints
  70. From Pixels to Views: Learning Angular-Aware and Physics-Consistent Representations for Light Field Microscopy
  71. MELDAE: A Framework for Micro-Expression Spotting, Detection, and Automatic Evaluation in In-the-Wild Conversational Scenes
  72. Combining Deep Learning and Explainable AI for Toxicity Prediction of Chemical Compounds
  73. SPIRAL: Self-Play Incremental Racing Algorithm for Learning in Multi-Drone Competitions
  74. Semi-Supervised Learning under General Causal Models
  75. Learning Event-guided Exposure-agnostic Video Frame Interpolation via Adaptive Feature Blending
  76. Blockchain Signatures to Ensure Information Integrity and Non-Repudiation in the Digital Era: A comprehensive study
  77. Statistical Analysis of the Sinkhorn Iterations for Two-Sample Schr"odinger Bridge Estimation
  78. Cross-Paradigm Graph Backdoor Attacks with Promptable Subgraph Triggers
  79. DDTR: Diffusion Denoising Trace Recovery
  80. LooGLE v2: Are LLMs Ready for Real World Long Dependency Challenges?
  81. qc-kmeans: A Quantum Compressive K-Means Algorithm for NISQ Devices
  82. Approximate Gradient Coding for Distributed Learning with Heterogeneous Stragglers
  83. Iteratively Refined Early Interaction Alignment for Subgraph Matching based Graph Retrieval
  84. SRSR: Enhancing Semantic Accuracy in Real-World Image Super-Resolution with Spatially Re-Focused Text-Conditioning
  85. Text to Trust: Evaluating Fine-Tuning and LoRA Trade-offs in Language Models for Unfair Terms of Service Detection
  86. Bag-of-Word-Groups (BoWG): A Robust and Efficient Loop Closure Detection Method Under Perceptual Aliasing
  87. AesCrop: Aesthetic-driven Cropping Guided by Composition
  88. Multi-Modal Masked Autoencoders for Learning Image-Spectrum Associations for Galaxy Evolution and Cosmology
  89. Semi-supervised Vertex Hunting, with Applications in Network and Text Analysis
  90. Random Search Neural Networks for Efficient and Expressive Graph Learning
  91. A Scalable Global Optimization Algorithm For Constrained Clustering
  92. Data-driven Sensor Placement for Predictive Applications: A Correlation-Assisted Attribution Framework (CAAF)
  93. Toward Robust Signed Graph Learning through Joint Input-Target Denoising
  94. GateFuseNet: An Adaptive 3D Multimodal Neuroimaging Fusion Network for Parkinson's Disease Diagnosis
  95. LLEMA: Evolutionary Search with LLMs for Multi-Objective Materials Discovery
  96. Towards Scalable Oversight via Partitioned Human Supervision
  97. Multi-Scale Finite Expression Method for PDEs with Oscillatory Solutions on Complex Domains
  98. A Sociophonetic Analysis of Racial Bias in Commercial ASR Systems Using the Pacific Northwest English Corpus
  99. The Limits of Data Scaling: Sub-token Utilization and Acoustic Saturation in Multilingual ASR
  100. LAMP: Data-Efficient Linear Affine Weight-Space Models for Parameter-Controlled 3D Shape Generation and Extrapolation
  101. Frustratingly Easy Task-aware Pruning for Large Language Models
  102. The Tonogenesis Continuum in Tibetan: A Computational Investigation
  103. An Analytic Theory of Quantum Imaginary Time Evolution
  104. Contextual Tokenization for Graph Inverted Indices
  105. Agent-GSPO: Communication-Efficient Multi-Agent Systems via Group Sequence Policy Optimization
  106. CHOIR: Collaborative Harmonization fOr Inference Robustness
  107. DynaPose4D: High-Quality 4D Dynamic Content Generation via Pose Alignment Loss
  108. Learning Local Stackelberg Equilibria from Repeated Interactions with a Learning Agent
  109. Backward-Friendly Optimization: Training Large Language Models with Approximate Gradients under Memory Constraints