mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sun 26 Jul 2026

213 papers

  1. Resist, Update, Reject: Preference Optimization Installs a Prior-Dependent Reliability SwitchLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  2. When Does Memory Help? A Cost-Aware Evaluation of Long-Term Memory in Tool-Using LLM AgentsLLM agents and tool use → Agent memory systems
  3. From Blind Edits to Verified Repair: Building Trustworthy User-Side LLM Agents for Web AccessibilityLLM agents and tool use → GUI and mobile agents
  4. Safety Alignment Illusion: The Cross-Lingual Safety Gap in LLMsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  5. MetaSpace: Metamorphic Testing for Spatial Cognition in Embodied AgentsLLM agents and tool use → Multimodal and embodied agents
  6. RAG-TESTER: Automated End-to-End Testing of Retrieval-Augmented Large Language ModelsRetrieval-augmented generation → RAG pipeline design and evaluation
  7. Asymmetric Collapse in Model Merging: When Refusal Over- writes RecognitionLLM safety and security → Safety alignment, refusal and guardrails
  8. Cross-Model Cross-Language AI Coding Agent Performance: Accuracy and Speed of Parallel CLRS AlgorithmsLLM agents and tool use → Software engineering coding agents
  9. HVM-GraphRAG: Holistic-View Multimodal Graph Retrieval-Augmented Generation on Complex DocumentRetrieval-augmented generation → Multimodal RAG
  10. The Mirage of LLM Guardrails: A Case Study in AI-Assisted Medical Note ManipulationLLM safety and security → Safety alignment, refusal and guardrails
  11. A Comparative Study of MCP and A2A for Inter-Agent Coordination in LLM-Based SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  12. OmniCache: Multidimensional Hierarchical Feature Caching For Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  13. TriShieldRAG: 3 Rings, One Blind Spot in Layered Defenses for Retrieval-Augmented GenerationRetrieval-augmented generation → Privacy and security of RAG
  14. SCTA: An Agentic Framework for Stable and Interpretable Target Gene Discovery from Single-Cell RNA SequencingLLM agents and tool use → Medical and scientific domain agents
  15. Kalypso: Relational LLM ServingEfficient LLM inference and serving → Serving systems and request scheduling
  16. Memory Efficient Audio Synthesis with Decoupled Temporal Depth Diffusion TransformersDiffusion models → Audio, speech and music
  17. ACM: Agentic Context Management for Long Horizon TasksLLM agents and tool use → Agent memory systems
  18. From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-ImprovementLLM reasoning → Reinforcement learning for reasoning +2
  19. PathScale-R1: Cross-scale Reasoning for Pathological Image AnalysisLLM reasoning → Clinical and biomedical applications
  20. A Few Words Go a Long Way: Language Guided Robot Policy SynthesisVision-language-action models → Failure recovery and robustness
  21. N0-TWAM: Scaling Tactile-Native World-Action Model for Contact-Rich ManipulationWorld models → Embodied and robot world models
  22. Escaping the Euclidean Void: Manifold-Informed Flow Matching for Sequential RecommendationDiffusion models → Diffusion recommenders
  23. Outcome-Confounded Local Supervision in On-Policy DistillationKnowledge distillation → On-policy and self-distillation for LLMs
  24. Hierarchical Soft Actor-Critic for Sparse-Reward Long-Horizon Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  25. E-Bench: Benchmarking Multi-Step Tool-Use Agents in Real-World Product ScenariosLLM agents and tool use → Tool learning and function calling
  26. LabRobFail: A Benchmark for Robotic Failure Analysis in Chemical Self-driving LaboratoryEnd-to-end autonomous driving → Large language models for driving
  27. Offline-Online Curriculum RL for Multimodal ReasoningLLM reasoning → Multimodal reasoning +1
  28. Offline-to-Online Creative Optimization with Generative Models and Adaptive TestingOffline RL and imitation learning from data → Diffusion and flow policies for offline RL
  29. Compute Globally, Materialize Locally: The Memory Contract of Sparse Event-KVEfficient LLM inference and serving → Efficient reasoning and agent inference
  30. Perturbation-Aware Diffusion-Guided Hybrid Segmentation for Robust and Annotation-Efficient Plant Stress PhenotypingDiffusion models → Inverse problems and image restoration
  31. Breaking the Total Variance Barrier: Sharp Sample Complexity for Linear Heteroscedastic Bandits with Fixed Action SetDeep reinforcement learning methods → RL theory and sample complexity
  32. Focus Is All You Need: Adaptive Goal-aware Attention Orchestration for Multi-Agent Graph SystemsLLM reasoning → Reasoning for agents, planning and code +1
  33. Rethinking Logic Optimization Operators: Theory-Derived Operator Compression via Agentic Source AnalysisLLM reasoning → Reasoning for agents, planning and code
  34. Plans Work in Mysterious Ways: Evaluating a Plan Mode for Spreadsheet AgentsLLM agents and tool use → Financial trading and forecasting agents
  35. PathSelect: Sequential Token Selection for Whole Slide PathologyMultimodal LLMs / vision-language models → Medical vision-language models +1
  36. Where Is the Tradeoff in Using Third-Party API Routers for Agentic Software Development?LLM agents and tool use → Agent threats, guardrails and governance
  37. Optimal Reward Shaping: Autonomous Car Parking Case StudyDeep reinforcement learning methods → RL for autonomous driving and traffic
  38. Restoration Flow Matching-Based Channel Refinement and Equalization Correction for MIMO Semantic CommunicationsDiffusion models → Diffusion for compression and wireless
  39. Hybrid Advantage Estimation with Unified Critic for VLM Agentic Reinforcement LearningMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  40. Action from Adjacent Set in Physical Space Outperforms the Best Prediction in World ModelsWorld models → Embodied and robot world models
  41. Anticipatory Risk-Guided Reinforcement Learning for Safe Flight Through Dynamic ClutterDeep reinforcement learning methods → RL for robot navigation and UAV control
  42. ObsDriveBench: Benchmarking Multimodal Understanding under Adverse Weather with Observability AwarenessMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
  43. Real-Time Human-Centric World Modeling for Upper-Body Human-Object InteractionWorld models → Embodied and robot world models
  44. Novel Claim or D'ej`a Vu? Rethinking "Contamination-Free'' Dynamic Evaluation for Multimodal Automated Fact-CheckingLLM reasoning → Reasoning benchmarks and evaluation
  45. Do Diagrams Help Large Language Models Reason? Evidence from Syllogistic ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  46. MOJITO: Modal Joint Learning for Unified End-to-End Autonomous DrivingEnd-to-end autonomous driving → End-to-end system architecture
  47. Do LLMs Know Their Vulnerable Scenarios?LLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +2
  48. To Erase, or Not to Erase: Robust Training-Free Concept Erasure with Preservation aware Adaptive Ranked Subspace ExpansionDiffusion models → Robustness, privacy and adversarial aspects
  49. Learning Sampling Parameters for Diffusion ModelsDiffusion models → Diffusion and flow policies for robotics
  50. Sparse Gaussian-Mixture-Model Q-Functions via Hadamard Overparametrization for Online Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  51. VIPER: Visual In-Context Physics Reasoning for Physically Plausible Video GenerationLLM reasoning → Spatial and embodied reasoning
  52. When Every Simulation Counts: Value-Based Reinforcement Learning for Accelerated Photonics Inverse DesignDeep reinforcement learning methods → Quantum reinforcement learning
  53. Direction-adaptive Mamba: Spatial-Frequency Dual-Domain Collaborative Learning for PolSAR Image ClassificationState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  54. Two Regimes of Chain-of-Thought Unfaithfulness: Metric-Based Detection Fails Where Models Are WrongLLM reasoning → Prompting and chain-of-thought reasoning
  55. Omni-Prune: Query-Aware Unified Token Pruning for Efficient Omnimodal Large Language ModelsLLM reasoning → Multimodal reasoning +1
  56. Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance
  57. Reasoning or Memorization: Can LLMs Understand and Generate Chinese Xiehouyu Riddles?LLM reasoning → Reasoning benchmarks and evaluation
  58. Separating Capability from Permission: A Governance Framework for Agentic AI Autonomy LevelsLLM agents and tool use → Agent threats, guardrails and governance
  59. Two-Timescale Hierarchical Reinforcement Learning for Resilient OperationsDeep reinforcement learning methods → Deep RL algorithms and representations
  60. LA-RL: Label-Aware Self-Reflection for Reinforcement Learning in Information ExtractionDeep reinforcement learning methods → RL training of language and agent models
  61. Beyond Short Segments : Expanding Speaker Embeddings with Vector Archives
  62. What Does 99% Accuracy Measure? A Reproducible Audit of Shortcut Learning in a Widely Used Fake News Corpus
  63. Subdomain-aware representation compression for pretrained image embeddings
  64. SoftTri: Smooth Triangular Membership Functions for Adaptive Fuzzy Inference Systems
  65. Role differentiation as ignition of a collective information engine: Structuration in Agent Populations
  66. Analyzing and Correcting Benevolence Bias in Large Language Models
  67. Interrupting the Chain: Human Perception of AI-Generated Disinformation Through a Kill Chain Lens
  68. Causal Inference under Interference with Learned Exposure Mappings
  69. Interaction valence reveals contrasting social networks in dairy cattle
  70. Average Distance Approximation for Static Large Graphs
  71. Eleven Years of BRACIS: A Meta-Scientific Study of the Brazilian Conference on Intelligent Systems
  72. A Trust-region Framework for Moment Estimation
  73. PULSE: An Executable Contract Language for Spatiotemporal Knowledge Graph Engineering
  74. Multimodal Auto-regressive Transformer Surrogate for Modeling Variable Operations and Quantifying Uncertainty in Geological Carbon Storage
  75. Deep Divide-and-Reduce in Symbolic Regression
  76. Fast Trainable Multilinear Bases for Image Compression
  77. Hybrid-Field Sparse Channel Representation and Recovery for XL-RIS-Assisted mmWave MIMO Systems
  78. LAWFUL: Law-Aligned Witness for Faithful Use of Latents
  79. Ranked by Position: Order Sensitivity as an Exploitable Attack Surface in LLM Listwise Recommenders
  80. Research Report on Noise-Shaped One-Bit Coefficients in Discrete Polynomial Fourier Extension
  81. Tokens are All You Need: Dual-purpose Semantic IDs for Achieving LLM-Level I/O Efficiency in recommendation systems
  82. DisasterTD: Disaster Toponym Disambiguation Using Multimodal LLMs and Cross-View Geolocalization
  83. Cost-Aware Recovery-Pathway Identification and Bayesian Optimization for Autonomous Materials Discovery
  84. Who Gets Named: Citation Type Predicts Individual Naming by Grounded Language Models, and a Roster Instrument Captures 0.5% of It
  85. Visible to the Court: How AI Is (and Isn't) Litigated in U.S. Federal Court Opinions
  86. Harnessing X-ray Absorption Spectroscopy Data through Multimodal Mining of Battery Literature
  87. Long-Tailed Medical Image Classification
  88. ADVERSARIAL: And-Inverter Graph-Assisted Hardware Trojan Detection At Scale
  89. Physics-Informed Neural Networks for Predicting Nitrous Oxide Flux
  90. Flash-CNNCap: Capacitance Extraction via Image Mapping
  91. MulRobBench: A Decision-Level Benchmark for Safe and Security-Policy-Compliant Multimodal UAV Agents
  92. A Coulomb Particle Model for Learning Kernel Attention in Transformers
  93. XMix: Combating Extremely Noisy Labels via Local Smoothness in Self-Supervised Feature Space
  94. Head Avatars with Dynamic Explicit Hair
  95. Controllable Diversity in Normalization-Based Implicit Ensembles via Softmax-Temperature Modulation
  96. Covariance Last-Layer Ensembles: Function-Space Diversity for Efficient Uncertainty Quantification
  97. OmniVAE: An Audio-Video VAE with Cross-Modal Alignment for Joint Generation
  98. Understanding Human-like Solutions in Combinatorial Optimization via Learning and Search
  99. Do Visual Features Improve Other-Initiated Repair Detection? A Dyadic Multimodal Approach
  100. Limbomorphs
All 213
  1. STEER: Steerable Dyadic Head Avatars
  2. Latent-LoRA: Compact Latent-Space Adapters with Gradient-Free Routing for Continual Learning
  3. Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations
  4. DriveDNA: A Large-Scale Multimodal Naturalistic Driving Dataset and Benchmark for Driving Style Identification
  5. Earnings25: A Comprehensive 500-Hour Speech Benchmark for Finance
  6. Indic DiarBench: A Multilingual Joint Diarization and ASR Benchmark for Indian Languages
  7. A Frozen 12B Beats Frontier Models on Verified Work: 100% Accuracy, 0 Tokens, Bit-Exact, Forever
  8. How Context Attribution Handles What the Model Already Knows
  9. Beyond Appearance: A Multi-cue Framework and Large-scale Benchmark for Pedestrian Association and Tracking on Mobile Aerial-Ground Platforms
  10. GNN-based Multi-Agent Control of Traffic Shockwaves in Sparse Vehicular Ad-hoc Networks
  11. Maximum Satisfiability of Simple Temporal Problems
  12. Scale Weight Decay and Train Better
  13. Outcome-Fair Restless Multi-Armed Bandits for Stochastic Deadline Scheduling
  14. Training Language Models to Cooperate with Inference-Time Controllers
  15. A Comparison of Data Augmentation Methods for Training Deep Neural Networks on Synthetic Aperture Sonar
  16. WISERouter: LLM Routing with Workload Budget Constraint
  17. RoadVGGT: Road-Structure-Aware Feed-Forward Road Surface Reconstruction
  18. DAP-Pose: Deep Temporal Alignment and Physics-aware Cross-modal Sensor Fusion for Robust Pose Estimation
  19. On the post-hoc Evaluation of PDE Discovery: A Multifaceted Challenge of Scientific Advancement
  20. Soft-Constrained Optimization of Latent Space in Variational Autoencoders
  21. ZenGen: Social Mind for LLMs
  22. Source-Free Controlled Adaptation of Teachers for Continual Test-Time Adaptation
  23. TRUAV: Distributed Multi-Agent Reinforcement Learning for Trajectory Planning and Routing Enhancement in UAV-Aided IoT-Enabled VANETs
  24. AI Strategy: How to Choose What AI Product to Implement
  25. An Exact Counterexample to Carlson's Associated-Prime Depth Conjecture from a Group of Order 128
  26. Recovery of latent inner products from an anisotropic Gaussian random geometric graph
  27. Distributional Split Criteria for Random Forests: Extensions, Shrinkage, and the Robustness of Mean Splitting
  28. Formally Verified Synthesizable Floating-Point Data Types in ARCH HDL
  29. The Intruder Threshold: A Spectral Law for LoRA Fine-Tuning
  30. The Illusion of Secure LLM Code: Closing the Security Gap via Iterative Reprompting
  31. Parameter-Efficient Adaptation of SAM3 for Prompt-Driven Surgical Concept Segmentation
  32. GNM Head: A Generative aNthropometric Model of the human head
  33. Extreme Volatility Warning under Label Scarcity via Multi-Source Anomaly Fusion
  34. SpecAHD: Localize to Specialize for Automated Heuristic Design in Large-Scale Routing Problems
  35. An empirical investigation into the properties of standard word embeddings
  36. Contrastive Parameter Disentanglement for Multi-modal Remote Sensing Image Generation
  37. RRTrack: Robust and Recoverable Object 6D Pose Tracking for Dynamic Scenes
  38. No Free Lunch in Flow Surrogates under Time-Varying Boundary Conditions: A Two-Regime Study
  39. XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection
  40. GRAPE: Graduated Routing for Articulated Portrait mesh Estimation
  41. DP-IVON-Gradsq: Differentially Private Squared-Gradient Improved Variational Online Newton
  42. EmoTrace: An Emotion Trajectory-Centered Framework for Psychological Support Dialogue Generation
  43. CALMRec: Causally Aligned Language Memory for Long-Horizon Recommendation
  44. Neural Network Learning of One-Bit Protocols for Qubit Measurement Simulation
  45. When Rates Are Geometric: Rate-Certificate Transfer for Contact Splittings in Optimization
  46. Distributed Convolutional Rank Regression over Decentralized Networks
  47. WGDnet: Wishart-guided Geometric-aware Deep Network for PolSAR Image Classification
  48. Extending Desbordante with Probabilistic Functional Dependency Discovery Support
  49. Variational-Ising-Attention:Tailored Attention Matters for Science
  50. A Controlled Visual-Backbone Benchmark for Multimodal Short-Term Solar Irradiance Forecasting
  51. Order in Desbordante: Techniques for Efficient Implementation of Order Dependency Discovery Algorithms
  52. Segmentation Robustness and Predictive Utility in Glioblastoma Radiomics: Evidence for a Trade-off in Survival Modelling
  53. GEMCo: A Validated, Ethically Releasable Proxy for Inaccessible Counselling Data
  54. DualityCert: Verifier-Gated Language-Model Repair of Broken Duality Claims in Quantum Field Theory
  55. Markerless Motion Capture in Routine Clinical Upper Limb Assessments: Validity and Insights Beyond Ordinal Scoring
  56. MS-GPT: Rethinking MS/MS De Novo Structure Elucidation as Spectrum-Induced Posterior Querying of a Molecule-Language Model
  57. ConFusion: Continuous Fusion Space Learning for Fine-Grained Controllable Infrared and Visible Image Fusion
  58. HiTMS: A High-Throughput Multi-Stream Linguistic Steganography Framework
  59. Weakly Supervised Instance-Level Gleason Pattern Estimation Using Primary and Secondary Labels
  60. JarvisHub: An Open Harness for Canvas-Native Multimodal Creative Agents
  61. Are You Still the Agent I Authorized? Earned Authority under a Fixed Ceiling for Evolving Agents
  62. Verification-Notebook Learning for Source-Aware Multimodal Misinformation Detection
  63. SketchMamba: A Lightweight State-Space Model for Joint Progressive Sketch Classification and Stroke Auto-Completion
  64. Neuromorphic Object Detection: An In-Depth Study and Future Directions
  65. D3O: Dynamic Distribution Distillation for Ordinal Regression
  66. Random Forest-Based Prediction of Bone Volume Fraction and Fracture Position from S-Parameters
  67. An Unofficial FastLAS Tutorial: A Programmer's Guide
  68. GTIN: A Unified Framework for Joint Event and Time Prediction in Temporal Graphs
  69. Neonatal Hypoxic-ischaemic Encephalopathy Classification from the EEG and HRV Signals Using a Conformer based Masked Autoencoder
  70. Language Shapes Instruction Hierarchy Compliance in Multilingual LLMs
  71. GaitFace: A Multimodal Dataset for Long-Range Person Identification
  72. Guiding Language Models to Be More Empathetic: Culturally Sensitive Mental Health Advice Generation Through Human-LLM Collaboration
  73. Mission-Level Runtime Assurance for LLM-Assisted ISR Swarms over a Verification-Aware Fabric
  74. The JEPA Paradox in Language: The Geometry of Linguistic Alternatives
  75. Geometry Meets Semantics: Fractional Gradient Stabilization for Semantic-Driven Bounding Box Optimization in Visual Detection Tasks
  76. Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis
  77. ATCNet-CIAM for Multi-Session Motor Imagery EEG Signal Classification
  78. Auditing Alignment Controllability in LLMs via Political Axes
  79. Chamaileon: Cross-Context Binder Design with Contextualized Modeling and Mixed Sampling
  80. The Cross-Domain Generalization Cost of Offensive Language Detection
  81. Topological Data Analysis and Graph-Theoretic Approaches for Tennis Match Prediction
  82. Choosing a Text Embedding Model: A Practical Benchmarking and Decision Framework
  83. MemVLN: Episodic and Procedural Memory for Vision-and-Language Navigation
  84. Impute On-Demand: Adaptive Correlated Time Series Imputation for Changing Environments
  85. Learning switched non-linear dynamical systems from a single trajectory
  86. Physics-Informed Neural Networks for Discovering Periodic Orbits in the Gravitational Three-Body Problem
  87. Formalizing Flag Algebras in Lean
  88. Token-Region Guided Cross-Attention Fusion for Multimodal Affect Interpretation
  89. PlanCraft: Sketch, Refine, and Furnish for Architect-Inspired Progressive 3D Residential Scene Generation
  90. An adaptive multi-fuzzy logic model for diagnosing transformer faults using dynamic weight optimization
  91. Charging Phase Health Indicators for Battery State-of-Health Estimation: A Systematic Comparison of CC, CV, and Combined Approaches under Cross-Battery Validation
  92. Mwando: Leveraging AI to Preserve and Teach shiKomori
  93. A Multi-stage Constrained Optimization Framework for Data-driven Problems
  94. ATLAS: Automated Approximation of Transformers for Efficient Homomorphic Inference in One Hour
  95. Robust 6-DoF Object Pose Tracking with Built-In Recovery under Occlusions and Rapid Object Motions
  96. Learning to Optimize: Joint Routing and Flow Allocation on Sparse Non-Euclidean Networks
  97. Extending Fourier Neural Operators for Modeling Parameterized and Coupled PDEs
  98. Generalization bounds and sample complexity for remaining useful life prediction from complete degradation trajectories
  99. Multi-Modal Object Re-Identification with Prompt-S6 and Semantic-Aware Knowledge Guidance
  100. Local Regularization Does Not Characterize Multiclass PAC Learnability
  101. Constraint-Bound Agnostic Bayesian Optimization: One Model for All Thresholds
  102. PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling
  103. Do Small Models Use the Law You Give Them? Context-Injected Fine-Tuning for Legal QA in Bangladesh
  104. Do LLM Debates Repeat Arguments Differently Across Languages?
  105. A Characterization of the Orthocomplement of the Tangent Space of Semiparametric Markov Models
  106. Neural Representation of Minimal Surfaces
  107. Experimentation and Commitment under Reward Shifts
  108. TLA+-Bench: An Execution-Grounded Benchmark and Dataset for Natural-Language to TLA Specification Generation
  109. Harmonized Interpretable ECG Waveform Features for Robust Cross-Dataset Clinical Prediction
  110. NeurGO: Learning to Generate Elite Candidates for Meta-Black-Box Expensive Optimization
  111. Blood Pressure Estimation from PPG: A Comparative Study of Direct and ECG-Mediated Deep Learning Pipelines
  112. Transfer Learning Architectures for Scalable Multi-Fidelity Bayesian Optimization
  113. A Statistical Difference between Single-Layer Learning and Hierarchical Learning in Wide Neural Networks