mlsanityData to 7 Oct 2026

Papers

New on arXiv

Sat 21 Feb 2026

167 papers

  1. When Prompt Optimization Becomes Jailbreaking: Adaptive Red-Teaming of Large Language ModelsLLM safety and security → Prompt injection and agent security
  2. GONE: Structural Knowledge Unlearning via Neighborhood-Expanded Distribution ShapingLLM safety and security → Machine unlearning
  3. Advances in GRPO for Generation Models: A SurveyLLM reasoning → Reinforcement learning for reasoning +1
  4. VoxelDiffusionCut: Non-destructive Internal-part Extraction via Iterative Cutting and Structure EstimationDiffusion models → 3D, point cloud and scene generation
  5. AgenticTyper: Automated Typing of Legacy Software Projects Using Agentic AILLM agents and tool use → Software engineering coding agents
  6. When Backdoors Go Beyond Triggers: Semantic Drift in Diffusion Models Under Encoder AttacksDiffusion models → Robustness, privacy and adversarial aspects +1
  7. When Do LLM Preferences Predict Downstream Behavior?LLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  8. Robust and Efficient Tool Orchestration via Layered Execution Structures with Reflective CorrectionLLM agents and tool use → Tool learning and function calling
  9. Global Commander and Local Operative: A Dual-Agent Framework for Scene NavigationLLM agents and tool use → Multimodal and embodied agents
  10. DREAM: Deep Research Evaluation with Agentic MetricsLLM agents and tool use → Web, search, and research agents
  11. LoMime: Query-Efficient Membership Inference using Model Extraction in Label-Only SettingsLLM safety and security → Membership inference attacks
  12. WANSpec: Leveraging Global Compute Capacity for LLM InferenceEfficient LLM inference and serving → Serving systems and request scheduling
  13. Give Users the Wheel: Towards Promptable Recommendation ParadigmMixture-of-experts → MoE for recommender systems
  14. Why Agent Caching Fails and How to Fix It: Structured Intent Canonicalization with Few-Shot LearningLLM agents and tool use → Software engineering coding agents
  15. DeepInnovator: Triggering the Innovative Capabilities of LLMsLLM agents and tool use → Web, search, and research agents
  16. Early Evidence of Vibe-Proving with Consumer LLMs: A Case Study on Spectral Region Characterization with ChatGPT-5.2 (Thinking)LLM reasoning → Mathematical reasoning
  17. Adaptive Collaboration of Arena-Based Argumentative LLMs for Explainable and Contestable Legal ReasoningLLM reasoning → Reasoning for agents, planning and code
  18. From Docs to Descriptions: Smell-Aware Evaluation of MCP Server DescriptionsLLM agents and tool use → Agent threats, guardrails and governance
  19. TRUE: A Trustworthy Unified Explanation Framework for Large Language Model ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  20. Beyond Stationarity: Rethinking Codebook Collapse in Vector QuantizationDiffusion models → Diffusion foundations and sampling
  21. Orchestrating LLM Agents for Scientific Research: A Pilot Study of Multiple Choice Question (MCQ) Generation and EvaluationLLM agents and tool use → Web, search, and research agents
  22. SafeDrive: Fine-Grained Safety Reasoning for End-to-End Driving in a Sparse WorldEnd-to-end autonomous driving → Adversarial scenarios and safety testing
  23. TPRU: Advancing Temporal and Procedural Understanding in Large Multimodal ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  24. DUET-VLM: Dual stage Unified Efficient Token reduction for VLM Training and InferenceLLM reasoning → Multimodal reasoning +2
  25. IDperturb: Enhancing Variation in Synthetic Face Generation via Angular PerturbationDiffusion models → Image generation, text-to-image and editing
  26. HeRO: Hierarchical 3D Semantic Representation for Pose-aware Object ManipulationOffline RL and imitation learning from data → Robot manipulation imitation learning
  27. Habilis-β: A Fast-Motion and Long-Lasting On-Device Vision-Language-Action ModelVision-language-action models → Efficient VLA inference and adaptation
  28. GenPlanner: From Noise to Plans -- Emergent Reasoning in Flow Matching and Diffusion ModelsDiffusion models → Diffusion and flow policies for robotics
  29. Think2: Grounded Metacognitive Reasoning in Large Language ModelsLLM reasoning → Test-time compute and efficient thinking
  30. Rethinking Preference Alignment for Diffusion Models with Classifier-Free GuidanceDiffusion models → Diffusion and flow policies for robotics +1
  31. MaskDiME: Adaptive Masked Diffusion for Precise and Efficient Visual Counterfactual ExplanationsDiffusion models → Diffusion foundations and sampling
  32. MANATEE: Inference-Time Lightweight Diffusion Based Safety Defense for LLMsLLM safety and security → Jailbreaking
  33. LAMMI-Pathology: A Tool-Centric Bottom-Up LVLM-Agent Framework for Molecularly Informed Medical Intelligence in PathologyLLM agents and tool use → Medical and scientific domain agents
  34. Initialization matters in few-shot adaptation of vision-language models for histopathological image classificationMultimodal LLMs / vision-language models → Medical vision-language models
  35. The Convergence of Schema-Guided Dialogue Systems and the Model Context ProtocolLLM agents and tool use → Tool learning and function calling
  36. TAG: Thinking with Action Unit Grounding for Facial Expression RecognitionLLM reasoning → Audio-language model reasoning
  37. Towards Reliable Negative Sampling for Recommendation with Implicit Feedback via In-Community PopularityLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
  38. Driving Like Yourself: A Benchmark for Closed-Loop Personalized End-to-End Autonomous DrivingEnd-to-end autonomous driving → Imitation-learning end-to-end planners
  39. DualScale: Energy-Efficient Disaggregated LLM Serving via Phase-Aware Placement and DVFSEfficient LLM inference and serving → Serving systems and request scheduling
  40. Federated Reasoning Distillation Framework with Model Learnability-Aware Data AllocationLLM reasoning → Prompting and chain-of-thought reasoning
  41. Bridging Modality Disconnect in Self-Reflection via Closed-Loop Visually Grounded VerificationLLM reasoning → Multimodal reasoning +1
  42. When World Models Dream Wrong: Physical-Conditioned Adversarial Attacks against World ModelsWorld models → World model security and GUI agents
  43. Rethinking Retrieval-Augmented Generation as a Cooperative Decision-Making ProblemRetrieval-augmented generation → Generation and context integration
  44. Beyond Description: A Multimodal Agent Framework for Insightful Chart SummarizationLLM agents and tool use → Multimodal and embodied agents
  45. MiSCHiEF: A Benchmark in Minimal-Pairs of Safety and Culture for Holistic Evaluation of Fine-Grained Image-Caption AlignmentMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  46. HIME: Mitigating Object Hallucinations in LVLMs via Hallucination Insensitivity Model EditingMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  47. Many AI Analysts, One Dataset: Navigating the Agentic Data Science MultiverseLLM agents and tool use → Web, search, and research agents
  48. Think with Grounding: Curriculum Reinforced Reasoning with Video Grounding for Long Video UnderstandingLLM reasoning → Multimodal reasoning
  49. Watermarking LLM Agent TrajectoriesLLM agents and tool use → Agent threats, guardrails and governance +1
  50. Insertion Based Sequence Generation with Learnable Order DynamicsDiffusion models → Flow matching, time series and science
  51. Neural Fields as World ModelsWorld models → World models for navigation
  52. Media Integrity and Authentication: Status, Directions, and FuturesLLM safety and security → Watermarking generated content and models
  53. Assessing Cognitive Biases in LLMs for Judicial Decision Support: Virtuous Victim and Halo Effects
  54. Hebbian-Oscillatory Co-Learning
  55. Memory-Augmented Spiking Networks: Synergistic Integration of Complementary Mechanisms for Neuromorphic Vision
  56. Exploration Space Theory: Formal Foundations for Prerequisite-Aware Location-Based Recommendation
  57. From ARIMA to Attention: Power Load Forecasting Using Temporal Deep Learning
  58. Explainable Regime Aware Investing
  59. PEPA: a Persistently Autonomous Embodied Agent with Personalities
  60. MoBiQuant: Mixture-of-Bits Quantization for Token-Adaptive Any-Precision LLM
  61. AINet: Anchor Instances Learning for Regional Heterogeneity in Whole Slide Image
  62. Conditionally Site-Independent Neural Evolution of Antibody Sequences
  63. How Far Can We Go with Pixels Alone? A Pilot Study on Screen-Only Navigation in Commercial 3D ARPGs
  64. Frame2Freq: Spectral Adapters for Fine-Grained Video Understanding
  65. Whisper: Courtside Edition Enhancing ASR Performance Through LLM-Driven Context Generation
  66. Face Presentation Attack Detection via Content-Adaptive Spatial Operators
  67. Yor-Sarc: A gold-standard dataset for sarcasm detection in a low-resource African language
  68. NeuroWise: A Multi-Agent LLM "Glass-Box" System for Practicing Double-Empathy Communication with Autistic Partners
  69. Depth-Enhanced YOLO-SAM2 Detection for Reliable Ballast Insufficiency Identification
  70. Modularity is the Bedrock of Natural and Artificial Intelligence
  71. YOLOv10-Based Multi-Task Framework for Hand Localization and Laterality Classification in Surgical Videos
  72. Optimal and Structure-Adaptive CATE Estimation with Kernel Ridge Regression
  73. INDUCTION: Finite-Structure Concept Synthesis in First-Order Logic
  74. Incremental Transformer Neural Processes
  75. Toward Manifest Relationality in Transformers via Symmetry Reduction
  76. (Perlin) Noise as AI coordinator
  77. Exponential Convergence of (Stochastic) Gradient Descent for Separable Logistic Regression
  78. High Dimensional Procedural Content Generation
  79. CRAFT-LoRA: Content-Style Personalization via Rank-Constrained Adaptation and Training-Free Fusion
  80. AAVGen: Precision Engineering of Adeno-associated Viral Capsids for Renal Selective Targeting
  81. From Human-Level AI Tales to AI Leveling Human Scales
  82. SLDP: Semi-Local Differential Privacy for Density-Adaptive Analytics
  83. DeepInterestGR: Mining Deep Multi-Interest Using Multi-Modal LLMs for Generative Recommendation
  84. Marginalized Bundle Adjustment: Multi-View Camera Pose from Monocular Depth Estimates
  85. PCA-VAE: Differentiable Subspace Quantization without Codebook Collapse
  86. SCHEMA for Gemini 3 Pro Image: A Structured Methodology for Controlled AI Image Generation on Google's Native Multimodal Model
  87. PrivacyBench: Privacy Isn't Free in Hybrid Privacy-Preserving Vision Systems
  88. [b] = [d] - [t] + [p]: Self-supervised Speech Models Discover Phonological Vector Arithmetic
  89. HEHRGNN: A Unified Embedding Model for Knowledge Graphs with Hyperedges and Hyper-Relational Edges
  90. Could Large Language Models work as Post-hoc Explainability Tools in Credit Risk Models?
  91. PhysConvex: Physics-Informed 3D Dynamic Convex Radiance Fields for Reconstruction and Simulation
  92. Characterization of Residual Morphological Substructure Using Supervised and Unsupervised Deep Learning
  93. SceneTok: A Compressed, Diffusable Token Space for 3D Scenes
  94. FOCA: Frequency-Oriented Cross-Domain Forgery Detection, Localization and Explanation via Multi-Modal Large Language Model
  95. Structure-Level Disentangled Diffusion for Few-Shot Chinese Font Generation
  96. BiMotion: B-spline Motion for Text-guided Dynamic 3D Character Generation
  97. Federated Measurement of Demographic Disparities from Quantile Sketches
  98. Enhancing 3D LiDAR Segmentation by Shaping Dense and Accurate 2D Semantic Predictions
  99. Limits of Convergence-Rate Control for Open-Weight Safety
  100. Similarity-as-Evidence: Calibrating Overconfident VLMs for Interpretable and Label-Efficient Medical Active Learning
All 167
  1. (α,β)-Stability for Boosting Vector-Valued Prediction
  2. TIACam: Text-Anchored Invariant Feature Learning with Auto-Augmentation for Camera-Robust Zero-Watermarking
  3. Joint Post-Training Quantization of Vision Transformers with Learned Prompt-Guided Data Generation
  4. Hyperbolic Busemann Neural Networks
  5. VariBASed: Variational Bayes-Adaptive Sequential Monte-Carlo Planning for Deep Reinforcement Learning
  6. Issues with Measuring Task Complexity via Random Policies in Robotic Tasks
  7. Open-Vocabulary Domain Generalization in Urban-Scene Segmentation
  8. Rank-Aware Spectral Bounds on Attention Logits for Stable Low-Precision Training
  9. When the Inference Meets the Explicitness or Why Multimodality Can Make Us Forget About the Perfect Predictor
  10. Exact Attention Sensitivity and the Geometry of Transformer Stability
  11. Echoes of ownership: Adversarial-guided dual injection for copyright protection in MLLMs
  12. When Agda met Vampire
  13. ABD: Default Exception Abduction in Finite First Order Worlds
  14. Detecting AI-Generated Forgeries via Iterative Manifold Deviation Amplification
  15. L2G-Net: Local to Global Spectral Graph Neural Networks via Cauchy Factorizations
  16. CLAP Convolutional Lightweight Autoencoder for Plant Disease Classification
  17. OpenClaw AI Agents as Informal Learners at Moltbook: Characterizing an Emergent Learning Community at Scale
  18. Spatial-Temporal State Propagation Autoregressive Model for 4D Object Generation
  19. Bayesian Lottery Ticket Hypothesis
  20. UniRank: A Multi-Agent Calibration Pipeline for Estimating University Rankings from Anonymized Bibliometric Signals
  21. EvalSense: A Framework for Domain-Specific LLM (Meta-)Evaluation
  22. Robust Self-Supervised Cross-Modal Super-Resolution against Real-World Misaligned Observations
  23. Learning Multi-Modal Prototypes for Cross-Domain Few-Shot Object Detection
  24. Chat-Based Support Alone May Not Be Enough: Comparing Conversational and Embedded LLM Feedback for Mathematical Proof Learning
  25. SGNO: Spectral Generator Neural Operators for Stable Long Horizon PDE Rollouts
  26. Operational Robustness of LLMs on Code Generation
  27. Carbon-aware decentralized dynamic task offloading in MIMO-MEC networks via multi-agent reinforcement learning
  28. Vectorized Bayesian Inference for Latent Dirichlet-Tree Allocation
  29. From Few-Shot to Zero-Shot: Towards Generalist Graph Anomaly Detection
  30. BURMESE-SAN: Burmese NLP Benchmark for Evaluating Large Language Models
  31. CaliCausalRank: Calibrated Multi-Objective Ad Ranking with Robust Counterfactual Utility Optimization
  32. ArabicNumBench: Evaluating Arabic Number Reading in Large Language Models
  33. GLaDiGAtor: Language-Model-Augmented Multi-Relation Graph Learning for Predicting Disease-Gene Associations
  34. Nazrin: An Atomic Neural Proof Automation Tactic in Lean 4
  35. A high-resolution nationwide urban village mapping product for 342 Chinese cities based on foundation models
  36. Bounds and Identification of Joint Probabilities of Potential Outcomes and Observed Variables under Monotonicity Assumptions
  37. UFO: Unlocking Ultra-Efficient Quantized Private Inference with Protocol and Algorithm Co-Optimization
  38. Optimizing ID Consistency in Multimodal Large Models: Facial Restoration via Alignment, Entanglement, and Disentanglement
  39. Benchmarking Computational Pathology Foundation Models For Semantic Segmentation
  40. Synthesizing Multimodal Geometry Datasets from Scratch and Enabling Visual Alignment via Plotting Code
  41. RadioGen3D: 3D Radio Map Generation via Adversarial Learning on Large-Scale Synthetic Data
  42. RoboCurate: Harnessing Diversity with Action-Verified Neural Trajectory for Robot Learning
  43. Spectral Rendering Without a Spectral Renderer: Learned Spectral Codes for RGB Pipelines
  44. HONEST-CAV: Hierarchical Optimization of Network Signals and Trajectories for Connected and Automated Vehicles with Multi-Agent Reinforcement Learning
  45. LaS-Comp: Zero-shot 3D Completion with Latent-Spatial Consistency
  46. A Prior-Aware Metric for Efficiently Distinguishing Memorization from Generalization in Large Language Models
  47. Phase-Consistent Magnetic Spectral Learning for Multi-View Clustering
  48. WiCompass: Oracle-driven Data Scaling for mmWave Human Pose Estimation
  49. Task-Aware Exploration via a Predictive Bisimulation Metric
  50. ReHear: Iterative Pseudo-Label Refinement for Semi-Supervised Speech Recognition via Audio Large Language Models
  51. Subtle Motion Blur Detection and Segmentation from Static Image Artworks
  52. Stochastic Gradient Variational Inference with Price's Gradient Estimator from Bures-Wasserstein to Parameter Space
  53. NeXt2Former-CD: Efficient Remote Sensing Change Detection with Modern Vision Architectures
  54. Temporal Action Representation Learning for Tactical Resource Control and Subsequent Maneuver Generation
  55. A Data-Driven Method to Map the Functional Organisation of Human Brain White Matter
  56. IRIS-SLAM: Unified Geo-Instance Representations for Robust Semantic Localization and Mapping
  57. EDU-MATRIX: A Society-Centric Generative Cognitive Digital Twin Architecture for Secondary Education
  58. Semantic Substrate Dynamics Theory: An Operator-Theoretic Framework for Geometric Semantic Drift
  59. Deep LoRA-Unfolding Networks for Image Restoration
  60. In-Context Planning with Latent Temporal Abstractions
  61. Contradiction to Consensus: Dual Perspective, Multi Source Retrieval Based Claim Verification with Source Level Disagreement using LLM
  62. From Trial by Fire To Sleep Like a Baby: A Lexicon of Anxiety Associations for 20k English Multiword Expressions
  63. Systematic Analysis of Coupling Effects on Closed-Loop and Open-Loop Performance in Aerial Continuum Manipulators
  64. Transformers for dynamical systems learn transfer operators in-context
  65. Heterogeneity-agnostic AI/ML-assisted beam selection for multi-panel arrays
  66. Theoretical Lower Bounds on the Robustness of Deep ReLU Networks
  67. Spilled Energy in Large Language Models