mlsanityData to 14 Oct 2026

Papers

New on arXiv

Fri 10 Jul 2026

325 papers

  1. A Full Adam Theorem for Spectral Heavy-Tail OnsetKnowledge distillation → General knowledge distillation methods
  2. Dependency-Aware Chain-of-Thought Compression for Financial ReasoningLLM reasoning → Test-time compute and efficient thinking
  3. Mutual Debiasing via Dual-Seed Comparison for Probabilistic Sampling in Large Language ModelsLLM reasoning → Test-time compute and efficient thinking
  4. Do LLM Agents Negotiate Rationally? A Mechanism-Design Framework for Verifiable Multi-Agent Interaction over A2A/MCPLLM agents and tool use → Social simulation and multi-agent debate
  5. Exploring More to Solve More: Boosting Diversity in Text Diffusion Models via Entropy-Based GuidanceDiffusion models → Image generation, text-to-image and editing
  6. GuidedRAG: Semantic Steering of Retrieval-Augmented GenerationRetrieval-augmented generation → RAG pipeline design and evaluation
  7. SimpleWikiSearch: A Clean Offline Wikipedia Environment for Agentic SearchLLM agents and tool use → Web, search, and research agents
  8. From Atoms to Entropy: Optimal Noise Allocation for Diffusion Training in the Convex RegimeDiffusion models → Diffusion foundations and sampling
  9. Codec-Gauge: Learning Compression-Friendly Gauges for Transformer KV CachesEfficient LLM inference and serving → KV cache optimization
  10. AppWorld-UL: Benchmarking Diverse Agent-User Interactions for Tool-UseLLM agents and tool use → GUI and mobile agents
  11. DynamicMCPBench: A Trace-Grounded, Effect-Scored Benchmark for LLM Agents over Live MCP ServersLLM agents and tool use → Tool learning and function calling
  12. PromptPack: Scaling LLM Annotation Agents for Online RecommendationLLM agents and tool use → Agentic recommender systems
  13. Evaluating and Guarding Citation Faithfulness in Agentic Scientific SynthesisLLM agents and tool use → Web, search, and research agents
  14. GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image ClassificationDiffusion models → Image generation, text-to-image and editing
  15. The Economics of AI Decoding Chips: Rebalancing Compute, Capacity, and Bandwidth for Efficient LLM InferenceMixture-of-experts → Efficient MoE training and inference systems +1
  16. Model Guides You How to Draw: Adaptive Visual Gating for Unified Multimodal ReasoningLLM reasoning → Multimodal reasoning
  17. Silent Failures in Quantized LLM Reasoning: A Taxonomy-Based Analysis of Hollow Convergence and Failure Mode ShiftsLLM reasoning → Test-time compute and efficient thinking
  18. Who&When Pro: Can LLMs Really Attribute Failures in AI Agents?LLM agents and tool use → Software engineering coding agents
  19. An LLM-powered Agentic Recommendation System for Connected TV Content DiscoveryLLM agents and tool use → Agentic recommender systems
  20. TopoExplore: Homology as an Exploration SignalDeep reinforcement learning methods → Deep RL algorithms and representations
  21. RouteRec: Strict Evaluation of Recommender-Agent Selection and AggregationLLM agents and tool use → Agentic recommender systems
  22. Do These Violent Delights Have Violent Ends? Measuring the Post-Merge Fate of Agentic CodeLLM agents and tool use → Software engineering coding agents
  23. Nonparametric Bayesian Inverse Reinforcement Learning with Data-Parallel Gibbs SamplingOffline RL and imitation learning from data → Inverse reinforcement learning +1
  24. Robo-ValueRL: Reliable Value Estimation for Offline-to-Online Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
  25. From Direction to Magnitude: How Multimodal Instruction-Tuning Reorganizes the Geometric Encoding of Identity-Specifying Prompts in Transformer Hidden StatesLLM reasoning → Prompting and chain-of-thought reasoning +1
  26. Exploring Agentic Workflows for Generating High Quality Math Visual AidsLLM agents and tool use → Educational agents and math problem solving
  27. More Structure, Not More Capacity: Object-Centric Representations for Visuomotor Imitation LearningOffline RL and imitation learning from data → Robot manipulation imitation learning
  28. Memory-Conditioned Tool Calling for Camera-First Visual AgentsLLM agents and tool use → Agent memory systems
  29. TS-Mask VLA: 2D Temporal-Spatial Masking for Vision-Language-Action Model with Effective BridgingVision-language-action models → Efficient VLA inference and adaptation
  30. PanoWorld: Real-World Panoramic GenerationWorld models → Video-generation world models and simulators
  31. OpenLongTail: Generative Scaling of Long-Tail Driving DataWorld models → World models for autonomous driving +1
  32. Evolution of Accuracy and Visual-Cognitive Errors in a Decade of Vision-Language AI ModelsLLM reasoning → Multimodal reasoning +1
  33. VEXAIoT: Autonomous IoT Vulnerability EXploitation using AI AgentsLLM agents and tool use → Agent threats, guardrails and governance
  34. Semantic Pareto-DQN: A Multi-Objective Reinforcement Learning Framework for Financial Anomaly DetectionDeep reinforcement learning methods → Adversarial robustness and RL in finance
  35. Task-Specific Multimodal Question Answering Agents via Confidence Calibration and Incremental Reasoning for QANTA 2026LLM agents and tool use → Multimodal and embodied agents
  36. LLM for EDA in Front-End Design: Challenges and OpportunitiesLLM agents and tool use → Software engineering coding agents
  37. Mosaic: Runtime-Efficient Multi-Agent Embodied PlanningLLM agents and tool use → Multimodal and embodied agents
  38. Agora: Enhancing LLM Agent Reasoning Via Auction-Based Task AllocationLLM reasoning → Reasoning for agents, planning and code +1
  39. PAC-ACT: Post-training Actor-Critic for Action Chunking TransformersDeep reinforcement learning methods → RL for robot locomotion and manipulation
  40. TrustX Agent Risk Classification Framework (ARC): Risk-Tiering Internally Created Agentic AI SystemsLLM agents and tool use → Agent threats, guardrails and governance
  41. Wan-Dancer: A Hierarchical Framework for Minute-scale Coherent Music-to-Dance GenerationDiffusion models → Audio, speech and music
  42. TCLA: Training-Free Class-wise Logit Adaptation for Medical Vision-Language ModelsMultimodal LLMs / vision-language models → Medical vision-language models
  43. CORL-AUV: CFD Oriented Reinforcement Learning for Autonomous Underwater VehiclesDeep reinforcement learning methods → RL for robot navigation and UAV control
  44. Writing Bug Reports for Software Repair Agents: What Information Matters Most?LLM agents and tool use → Software engineering coding agents
  45. The Count Is There, but Misaligned: Understanding and Correcting Counting Failures in VLMsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  46. FreyaTTS: A Compact Tokenizer-Free Flow-Matching Transformer for Turkish-First Speech SynthesisDiffusion models → Audio, speech and music
  47. SAGEAgent: A Self-Evolving Agent for Cost-Aware Modality Acquisition in Multimodal Survival PredictionLLM agents and tool use → Medical and scientific domain agents +1
  48. Seeing is Free, Speaking is Not: Uncovering the True Energy Bottleneck in Edge VLM InferenceMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  49. One-Shot Multimodal Learning from Demonstration with Force-Constrained Elastic MapsOffline RL and imitation learning from data → Robot manipulation imitation learning
  50. Failure as a Process: An Anatomy of CLI Coding Agent TrajectoriesLLM agents and tool use → Software engineering coding agents
  51. Shared Selective Persistent Memory for Agentic LLM SystemsLLM agents and tool use → Agent memory systems
  52. Multimodal Reward Hacking in Reinforcement LearningMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +2
  53. ProofCouncil: An LLM Agent for Solving Open Mathematical ProblemsLLM agents and tool use → Educational agents and math problem solving
  54. Robustifying Vision-Language Models via Test-Time Prompt AdaptationMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  55. Test-Time Scaling for Small VLMs on Multilingual Visual MCQLLM reasoning → Multimodal reasoning +1
  56. A Sovereign, Open-Source Foundation Model for German and EnglishMixture-of-experts → MoE large language models +1
  57. Fictional Worldbuilding: Multi-Agent LLM Collaboration with Hierarchical Context Compression and Iterative ReviewLLM agents and tool use → Multimodal and embodied agents
  58. Mach-Mind-4-Flash Technical ReportLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  59. Deceptive Grounding: Entity Attribution Failure in Clinical Retrieval-Augmented GenerationRetrieval-augmented generation → Medical and biomedical RAG
  60. Shortcut Trajectory Planning for Efficient Offline Reinforcement LearningOffline RL and imitation learning from data → Diffusion and flow policies for offline RL
  61. Communication-Efficient Digital-Twin Coordination for Heterogeneous LLM Embodied Agents over Computing Power NetworksLLM agents and tool use → General LLM agent frameworks and benchmarks
  62. LongMedBench: Benchmarking Medical Agents for Long-Horizon Clinical Decision-MakingLLM agents and tool use → Medical and scientific domain agents
  63. Autoregressive latent diffusion for 3D molecule generationDiffusion models → Flow matching, time series and science
  64. Forget Narrowly, Retain Broadly: Unlearning as an Asymmetric Generalization ProblemLLM safety and security → Machine unlearning
  65. Glob3R: Global Structure-from-Motion with 3D Foundation ModelsWorld models → Video-generation world models and simulators
  66. OpenProver: Agentic and Interactive Theorem Proving with Lean 4LLM agents and tool use → Educational agents and math problem solving
  67. Toward Auditable AI Scientists: A Hypothesis Evolution Protocol for LLM AgentsLLM agents and tool use → Web, search, and research agents
  68. Causally Debiased Latent Action Model for Embodied Action Conditioned World ModelsWorld models → Embodied and robot world models
  69. Malaika: Understanding Malware through Tri-Grounded Agentic ReasoningLLM reasoning → Reasoning for agents, planning and code +1
  70. Scoped Verification for Reliable Long-Horizon Agentic Context Evolution under Distribution ShiftLLM agents and tool use → General LLM agent frameworks and benchmarks
  71. KV-PRM: Efficient Process Reward Modeling via KV-Cache Transfer for Multi-Agent Test-Time ScalingLLM reasoning → Reinforcement learning for reasoning +3
  72. BeyondSight: Object Permanence for End-to-End Autonomous DrivingEnd-to-end autonomous driving → Reasoning VLA and VLM driving policies
  73. ReGen: Hierarchical Multi-Prompt Representation Generation for Efficient Waveform Diffusion ModelsDiffusion models → Audio, speech and music
  74. 4D Human-Scene Reconstruction from Low-Overlap CapturesDiffusion models → 3D, point cloud and scene generation
  75. ReProAgent: Tool-Augmented Multi-Stage Agentic Generation of Bug Reproduction Tests from Issue ReportsLLM agents and tool use → Software engineering coding agents
  76. Quantum Circuits in Diffusion Models: A Fair-Comparison Study and a Mechanistic Analysis of Angle-Embedding FailuresDiffusion models → Diffusion foundations and sampling
  77. Multi-Agent LLM Collaboration for Unit Test Generation via Human-Testing-Inspired WorkflowsLLM agents and tool use → Software engineering coding agents
  78. L-MAD: A Systematic Evaluation of Multi-Agent Debate Structures in Legal ReasoningLLM agents and tool use → Social simulation and multi-agent debate
  79. AgentKGV: Agentic LLM-RAG Framework with Two-Stage Training for the Fact Verification of Knowledge GraphsRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG +1
  80. GeoTrace: Geometry-Aware Trajectory Token Compression for Video Large Language ModelsEfficient LLM inference and serving → Visual token pruning in multimodal models
  81. Neuro-Agentic Control: A Deep Learning-based LLM-Powered Agentic AI Framework for Controlling Security ControlsLLM agents and tool use → Agent threats, guardrails and governance
  82. Agentic Proof and Property-Based Testing via Property-Templates in Data-Intensive ComputingLLM agents and tool use → Educational agents and math problem solving
  83. Latency-Aware Digital Twin-Assisted Cooperative Perception for Autonomous VehiclesEnd-to-end autonomous driving → Cooperative and V2X driving
  84. Probing Diffusion Denoising Dynamics for Contrastive Representation LearningDiffusion models → Diffusion foundations and sampling
  85. On Locality and Length Generalization in Visual ReasoningLLM reasoning → Multimodal reasoning
  86. Learning More from Less: Reinforcement Learning from HindsightVision-language-action models → Reinforcement learning and post-training
  87. MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  88. SLBench: Evaluating How LLM Agents Follow Logical Relations in SkillsLLM agents and tool use → Agent skill learning and evolution
  89. Secret Scanner Agent: Extracting Secrets and Access Context from Unstructured DocumentsLLM agents and tool use → Agent threats, guardrails and governance
  90. C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced ClassesMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  91. RaMark: Radioactive Watermarking for Generated Tabular DataLLM safety and security → Watermarking generated content and models
  92. Faking Good and Faking Bad in LLMs: Response Distortion Across Dark Triad Personality Traits
  93. Dimension-Corrected Hitting Times for Heavy-Tailed Spectral Emergence in Neural Optimizer Dynamics
  94. The Battery Price of edge AI: A study of the Environmental Impact of LLM Inference on Mobile Devices
  95. Sledgehammer or Scalpel? A Fine-grained Adaptive Framework for Implicit Hate Speech
  96. From Sound to Symptom: Real-Time Respiratory Signal Understanding for Conversational Healthcare Agents
  97. A Safety-Gated Multimodal AI Backend for Mental-Health Support: Hierarchical State Representation, Conservative Risk Fusion, and Controlled Generation in Anian
  98. Effective Personalized AI Tutors via LLM-Guided Reinforcement Learning
  99. ComNetX: Local Hierarchical Adaptation for Dynamic Community Detection
  100. The politics of postmortem privacy
All 325
  1. Large Language Models and their Awareness of Mechanics and Spatial Geometry
  2. DumpsterCluster: From Dumpster Diving to Serving LLaMA-70B on 60 GPUs
  3. FluctlightDB: A Memory Model of Data for AI Agents
  4. EEG Emotion Recognition From AI-Generated Biodigital Architecture Images
  5. A Path Integral Model of Cognition
  6. SetGo: Metadata Readiness for Scientific AI Datasets
  7. How LLM Task-Adaptation Reshapes Alignment: A Multi-dimensional Study of Behavioral and Representational Drift
  8. Text-based Tactile Graphics Generation for the Visually Impaired
  9. Improving Access to Essential Medicines via Decision-Aware Machine Learning
  10. HypNO: A Graph-Based Neural Operator with Physics-Informed Message Passing for Hyperbolic Conservation Laws
  11. Leveraging Biokinetic Knowledge Priors for Data-Scarce Bioprocess Modeling
  12. ReliableTableQA:How Much Supervision Does Reliability Annotation Need?
  13. A Graph Neural Network approach to zero-shot Digital Twins
  14. Grounding Investor Views: Neural Predicates in the Black-Litterman Model
  15. Position: Stop Reactively Patching Your Model Every Time and Start Proactive Test-Driven AI Development
  16. CLOE: Christoffel Loss Autoencoder for Anomaly Detection
  17. Uncertainty-Aware Trust Estimation for Multi-LLM Systems via Structured Expert Judgement
  18. ConfidenceBench: Evaluating Confidence Calibration in Large Language Models
  19. MAC 2026: Advancing Micro-Action Analysis Towards Fine-Grained Understanding
  20. Volition Elicitation: Operational Semantics for People and Their Machines
  21. Untrusted Authors, Trusted Answers: A Calculus of Fidelity-Graded Translations
  22. Repairing Shape-Prior Shortcuts in Long-Range Single-Shot Fringe Projection Profilometry
  23. FlashTrie: A GPU-Accelerated Constrained Beam Search for Generative Retrieval
  24. Are We Ready for AI-Driven Discovery? AI Verification Before the Next Fundamental Physics Breakthrough
  25. Geometric mean-based pairwise comparison method with the reference values -- statistical approach
  26. MLPs are Hebbians: Constructing Efficient Fact-Storing MLPs for Transformers
  27. Robustly Invertible Nonlinear Dynamics and the BiLipREN: From Inversion-Based Control to Generative Trajectory Modelling
  28. Local Multimodal Music Alignment from Global Supervision
  29. A Symbolic Neural CPU for Quantization-Simulated Writeback and Interpretable Program Execution
  30. FindMyText: Robust, Scalable Detection of Text Containment in Large Web-Crawled Corpora
  31. Tokenizing Numerical and Embedding Features for LLM RecSys
  32. Runtime Safety Filtering for Learned Small UAS Separation Policies under GNSS Degradation
  33. Manifold Constrained Conformal Prediction for Spatial Events
  34. Vilya-1: An all-atom foundation model for macrocycle structure prediction and design
  35. Beyond Bayesian Nash: Learning Minimax-Regret Equilibria for Adversarial Team Games under Asymmetric Information
  36. UniPose9D: Universal Category-Agnostic Object Pose Estimation
  37. Multimodal Routing for Interpretable, Robust, and Auditable Clinical Prediction
  38. Inverse-IMPRESSION: A Graph-based Platform for Molecular Structure Elucidation from Experimental NMR Spectroscopic Properties
  39. A Production-Oriented Framework for Evaluation of SFX Generation
  40. Learning in Curved Weight Space:Exponential-Linear Weight Reparameterization for Improved Optimization
  41. Workload-Driven Optimization for On-Device Real-Time Subtitle Translation
  42. Optimizing ARDL Models for Retail Sales Forecasting and Fair Pricing
  43. A Foundation Model for Multimodal Event Sequences in Financial Applications
  44. A Knowledge-Based Multi-Agent Framework for Security Control Recommendation
  45. Artificial Intelligence Across the Cardiac Amyloidosis Diagnostic and Management Pathway: From Single-Modality Detection to Multimodal Clinical Integration
  46. SMETA-ZSL:Semantic Meta-Alignment for Zero-Shot Threat Classification
  47. Faithful by Design: Evaluating and Improving LLM-Generated Clinical Trial Summaries for Multi-Stakeholder Audiences
  48. Banshee: Target Switch Attacks on Gimbal-Stabilized Visual Tracking Systems via Acoustic Injection
  49. Global Merger-Arbitrage Forecasting with Language Models
  50. Learning Partition Trees for Nearest Neighbor Search
  51. Depth-Efficient Quantum Topological Data Analysis for Regime-Specific Detection of Financial Stress
  52. When Classical Baselines Are Tuned as Carefully as the Quantum Model, Does Quantum Reservoir Computing Still Win?
  53. An End-to-End Hybrid Quantum-Classical Sampling Workflow for Discrete Markov Random Fields: A Reproducible Case Study
  54. Next-Dense-Stride Prediction for Multimodal Autoregressive Visual Modeling
  55. What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection
  56. Do Transformer Temporal Heads and Post-Pooling Motion Gates Help CorrNet-based CSLR? An Empirical Study
  57. Remembering Distinct Items, Not Tokens: A Learnable Dirichlet-Process Cache Between State-Space Models and Attention
  58. Bridging the Catalog-to-Real Gap: Scalable Product Recognition via Multi-Stage Contrastive Learning
  59. Index SLM Technical Report
  60. ShapKO: Shapley-Adaptive Modality Knockout for Robust Multimodal Learning
  61. A Dual-Stream Challenge-Response Protocol for Ocular Liveness Verification
  62. CLIR-Bench: Benchmarking Multimodal Question Answering over Irregular Clinical Time Series
  63. Serving the Long Tail: Training-Free LLM Candidate Generation for Vacation Rental Marketplaces
  64. Prompting-MammAlps: Fine-Grained Text-to-Video Retrieval for Camera-Trap Data
  65. Nonlinear Axiomatic Attribution for Cooperative Games
  66. Neural Posterior Estimation for Inferring Weak Lensing Shear
  67. Reliability-Aware Ensemble Classification Under Class Imbalance: A Calibration Study on Liquid-Based Cervical Cytology
  68. Does YOLO26 Truly Offer Advantages Over Its Predecessors for Edge Deployment? A Benchmark Study in Aquaculture
  69. Generative Testing of Automated Speech Recognition Systems
  70. A Strong Balanced-Softmax Classifier-Retraining Baseline for Long-Tailed Recognition
  71. Slide-Level Active Learning Reduces Annotation Burden in H&E images
  72. Tracking Intermittent Particles with Self-Learned Visual Features
  73. Robustness and Stability Analysis of Differentiable Shift-Variant FBP for Cone-Beam CT under Challenging Acquisition Settings
  74. TDSal: Task-Based Top-Down Saliency Prediction Model
  75. Towards Objective Dysgraphia Detection: A Multi-Branch Deep Learning Approach for Online Handwriting Analysis
  76. Performance Benchmarking and Optimisation of Clustering Algorithms for Local and Non-Local Similarity Measure in Medical Image Analysis
  77. Learning Predictive Ambiguity Sets for Decision-Focused Distributionally Robust Optimization
  78. Estimation, Prediction, and Assortment Optimization for Markov Chain Choice Models with Panel Data
  79. RUBRIC: Realism--Utility Balanced Ranking for Imbalanced Classification
  80. RASR: Range-Aware Scale Recovery for Metric UAV Navigation
  81. CHM-Net: Center Heatmap-driven Macro-Micro Modeling Network for MRI-based Microbial Density Stratification
  82. Detangled: A Framework for Creating, Editing, and Inferencing Feature Rich Hair Strands
  83. PHINN-EEG: Topological Time-Series Analysis of Dream-State EEG -- Dynamic Betti Curves for Dream Content Classification and Topology-Conditioned Neural Signal Synthesis
  84. Scalable Visual Pretraining for Language Intelligence
  85. Revisiting Euler-Angle Regression with Kolmogorov-Arnold Networks
  86. ConceptSMILE: Auditing the Trustworthiness of Concept-Based Explainable AI
  87. Deep Gaussian Processes on Directed Acyclic Graphs
  88. Lean-QIT: Towards a Formal Infrastructure for Quantum Information Theory
  89. The Effects of Synthetic Data and Label Distribution on Canola Branch Counting
  90. 4DR360: State Reasoning for Joint 3D Detection and Occupancy Prediction in 4D Radar-Camera Full-Scene Perception
  91. Dynamic Frechet Regression with Feature Selection for Distributional Data
  92. Toward Real-Time Sentence-Level Sign Language Translation
  93. Tokenizer Transplantation: Mitigating Autoregressive Collapse in Edge-Efficient Bengali ASR
  94. Characterization of the Basin of Convexity for Multi-Snapshot Spike Deconvolution via Variable Projection
  95. Promptable Concept Segmentation from Above: Evaluating SAM 3's Zero-Shot and One-Shot Capabilities in Remote Sensing
  96. Entropy-Constrained Machine Learning with Residual Data Augmentation for Modeling Chemical Kinetics
  97. Knowledge Graphs and Explainable AI as Complementary Resources for Urban Mining
  98. SurvFM enables tabular foundation models for right-censored survival prediction
  99. Conceptual Networks for Cross-Linguistic Idiomatic Expressions: A Feature-Based Graph Approach
  100. Large-Scale Portfolio Optimization Problem Under Cardinality Constraint With Enhanced Multi-Objective Evolutionary Algorithms
  101. Beyond Fixed Representations: The Vocabulary and Verifier Gaps in Open-Ended AI
  102. High-Dimensional Interpolators Can Be Fragile: Heavy Tails and High-Dimensional Large Deviations
  103. Graph-Regularized Low-Rank Matrix Completion by Variable Projection
  104. CoCoT-EEG: Contrastive-Pretrained Multiscale Convolutional Transformer for EEG Decoding
  105. GatedLinear: Adaptive Routing of Complementary Linear Bases for Time Series Forecasting
  106. Statistically Undetectable Backdoors in Deep Neural Networks
  107. TSAI-MetaFraud: A Benchmark Dataset for Financial Fraud Transaction and Behavioral Risk Detection in Metaverse Ecosystems
  108. ALICE: Learning a General-Purpose Pathology Foundation Model from Vision, Vision-Language, and Slide-Level Experts
  109. DGSfM: Depth-Guided Scale-Aware Global Structure-from-Motion
  110. What VGGT Knows About Overlap: Probing Geometric Foundation Models for Co-Visibility
  111. All Explanations are Wrong, But Many Are Useful: Exploring the Rashomon Explanation Set with Large Language Models
  112. Normalisation-Based Likelihood Ratio Estimation for Forensic Authorship Verification
  113. Terminal Dimension Reduction for Time Series with Applications
  114. Ceci n'est pas une pipe: AI systems as semantic abstractions
  115. SigLIP-HD by Fine-to-Coarse Supervision
  116. Neural Collapse Is Forbidden: Information Floors in Language Models
  117. Decoupling Language Guidance from Backbones for Text-Guided Medical Segmentation
  118. Foveation-Guided Dynamic Token Selection for Robust and Efficient Vision Transformers
  119. Deep Learning for Dynamic Programming with Recursive Utility Using First-order Conditions
  120. Active rejection enables reliable generalization of universal machine-learning interatomic potentials
  121. Hydra++: Real-Time Hierarchical 3D Scene Graph Construction With Object-Level Shape Estimation
  122. Practical Source Code Recovery from Binary Functions Using Anchor-Based Retrieval and LLM Reasoning
  123. How Does Bayesian Causal Discovery Fail? Characterising Structural Consequences in Linear Gaussian Networks under Latent Confounding
  124. Parameter-Efficient Vision-Language Adaptation with Continuous Metadata Conditioning for Animal Re-Identification
  125. Near-optimal node-private community estimation in polynomial-time
  126. comprisk: A scikit-learn-compatible Python toolkit for competing-risks survival analysis
  127. Multimodal Scenario Similarity Search for Autonomous Driving
  128. Action-Factored Multi-Agent Reinforcement Learning for Scalable Quantum Device Tuning
  129. SVF-CR: Synchronized Visual-Facial Cross-Refinement for Multimodal Ambivalence and Hesitancy Recognition
  130. Self-Guided Test-Time Training for Long-Context LLMs
  131. Similarity search generalisation in contrastive learning with InfoNCE loss
  132. SYNRARE: Synthetic Rare Disease EHR Generation for ML Benchmarking
  133. Data-Efficient Deep Learning: Empirical Guidelines for Training Set Size Estimation in Inertial Sensor Classification
  134. On-Device Adaptive Battery Power Prediction for Electric Vehicles
  135. Fully Trainable Deep Differentiable Logic Gate Networks and Lookup Table Networks
  136. STEEL: Sparsity-Aware Fused Attention for Energy-Efficient Long-Sequence Inference on AMD's XDNA NPU
  137. Learning Physics-Informed Surrogate Model of Linear Elastic Displacement Fields from Geometry
  138. When Routes Run Out: Adversarial Co-Learning and Explainable Robustness in Quantum Repeater Networks
  139. Graph Neural Networks for Scalable and Transferable Node Centrality Approximation
  140. Spectrally Deconfounded Gradient Boosting
  141. Diversifying to Verify: When Task-Equivalent Programs Differ in Verifiability
  142. CtrlVTON: Controllable Virtual Try-On via Visual-Instance-Prompt Segmentation
  143. Simon-SR: Spatially Adaptive Modulation and Visual Prompt Adaptation for Text-Reinforced Super-Resolution
  144. DKCD: Domain Knowledge-Enhanced Causal Discovery from Unstructured Data
  145. Towards Detecting Inconsistencies in End-to-end Generated TODs
  146. Dynamic Inverse Rendering for Enhanced Material-Lighting Decomposition
  147. WildTrace: Benchmarking Natural Evidence Trails in Long-Context Reasoning
  148. Letting the Data Speak: Extracting Keywords from Crowdsourced Collections with AI
  149. Automatic Thematic Indexing of Large Literary Corpora: A Machine Learning Approach to Voltaire's Complete Works
  150. Exposure is not manifestation: measurement target and output resolution jointly determine which behavioural-faithfulness evaluator wins
  151. From Classification to Localization and Clinical Validation: Large-Scale Development of a Deep Learning System for Thoracic Disease Detection on Chest Radiographs in Thailand
  152. TextileNet: Towards Zero-shot Text-style Segmentation of Manuscripts
  153. Risk-Aware General-Utility Markov Decision Processes
  154. Letter Lemmatization: One-to-one and Banded RNNs for Reversing Character-Set Simplification and Abbreviation in Medieval Text
  155. Leveraging Interpretable Tsetlin Machine for PDF Malware Detection
  156. Super-Tuning: From Activation-Aware Pruning to Sparse Fine-Tuning
  157. Rethinking Monocular Depth Embedding for Generalized Stereo Matching
  158. REMIND: RE-Identification with Memory for INDoor Navigation
  159. LionVote: Per-Layer Learning Rate Adaptation for Lion
  160. Semantic Hardness Is Not Visual Hardness: Sign-Aware Hard Negative Mining for Sign Language Retrieval
  161. Geopolitical alignment: Endorsement effects in large language models
  162. AnythingReality: Robust Online Gaussian Splatting SLAM for Open-Vocabulary VR Scene Exploration
  163. Authority-Bound Governance of Heterogeneous AI Security Decisions in Telecom and IoT Networks
  164. LLMs for health: Perceived benefits, risks, intention to use AI chatbots, and willingness to self-disclose across sensitive health topics
  165. Influence Diagnostics in High-dimensional M-estimation: Precise Asymptotics
  166. All you need is SAMPAT
  167. Temporal Knowledge Graph Forecasting under Distribution Shifts: A Synthetic Evaluation
  168. When Does Order Flow Matter? State-Dependent L2 Liquidity-State Transitions in Crypto Futures
  169. Git-Assistant: Planning-Based Support for Updating Git Repositories
  170. TACTIC: Tactile and Vision Conditioned Contact-Centric Control for Whole-Arm Manipulation
  171. Joint-Embedding Predictive Architecture for Solar PV Panel Fault Classification
  172. Complexity-Guided Component-wise Initialization for Language Model Pretraining
  173. Interference and Retention in Continual Learning
  174. Application of machine learning to monster level prediction in tabletop RPG game design
  175. YeTI: You Only Need Two Noisy Images for Real-World sRGB Noise Generation
  176. GenVid2Robot: From Video Generation to Robot Manipulation via Rigid-Geometric Consistency
  177. HiHR: Hierarchical Hyperbolic Representation for Aerial-Ground Person Re-Identification
  178. Generative Communications: Overview, Technologies, and Trends
  179. Attention to Detail: Evaluating Energy, Performance, and Accuracy Trade-offs Across vLLM Configurations
  180. TSR-Ego: Temporally Guided Stereo Refinement Framework for Egocentric 3D Human Pose Estimation
  181. Understanding Schedule-Free Methods in Nonconvex Optimization: Rate Guarantees and Escaping Saddles
  182. COAST: Context-Aware Differential Learning for Gene Expression Prediction in Spatial Transcriptomics
  183. A Personalized Computational Framework for Assessing the Sufficiency of Partially Observed Data in Healthcare AI models
  184. What Pixels Are Enough? SEAMS: Sufficiency Saliency via MSE-Preservation Soft-Masks
  185. Activation Steering Transfer to Agents: One Gain Ratio Does Not Identify Potency and Efficacy
  186. Weaving Light and Time: Unified Harmonic-Geometric Representation Learning for Dense RGB-Event Parsing
  187. MedRealMM: A Real-World Multimodal Benchmark for Chinese Online Medical Consultation
  188. Control Laguerre Tessellation: Semi-discrete Optimal Transport Over Control Systems
  189. Super-Generalist: Towards Comprehensive and Accurate Medical Image Understanding via Generalist-Specialist Synergy
  190. IB-Flow: Information Bottleneck-Guided CFG Distillation for Few-Step Text-to-Image Generation
  191. VTaMo: Video-Text Alignment Model for Sign Language Translation
  192. Power Flow Feasibility Assessment Using Variational Graph Autoencoders
  193. Augmenting Fundamental Analysis with Large Language Models: A RAG-Based System for Generating Investor Briefs
  194. Event Burst Trigger: An Availability Backdoor Attack on Event-Based SNN Object Detection
  195. Event Stream based Multi-Modal Video Anomaly Detection: A Benchmark Dataset and Algorithms
  196. Quantum-Enhanced Synthetic Data Generation Using Quantum Circuit Born Machines for Imbalanced Tabular Learning
  197. Integrating Large Language Models and Graph Convolutional Networks for Semi-Supervised Image Classification
  198. Equivariant Filter for High Performance Image Tracking using an Event Camera
  199. Beyond Metadata: CAPRA for Hidden Subgroup Analysis under Missing Metadata in Medical Imaging
  200. A Coreset Selection Framework with Ensemble Aggregation for Image Classification
  201. Solving Stochastic Fixed-Point Equations with High Probability
  202. PRecG: Legal Precedent Retrieval with Graph Neural Networks and Rhetorical Role Segmentation
  203. Beyond Time Shifts: Adapting Omni-LLM as a Reference-Free Evaluator for Generative Audio-Visual Models
  204. EXHOLD: Experience-Aware Real-Time Hold Control for Large-Scale Ride-Hailing Matching at DiDi
  205. DETRAM: End-to-end DEtection, Tracking and Recovery of HumAn Meshes
  206. Achieving Almost Exact Recovery in Almost Quadratic Time: Rank-Based Graph Matching via Local Tree Correlation Tests
  207. Subtoken Vision Transformer for Fine-grained Recognition
  208. A Survey on the Green Development of Large Models: From Resource-Efficient Architectures to Hardware-Software Co-Design
  209. REBASE: Reference-Background Subspace Elimination for Training-Free In-Context Segmentation
  210. Adaptive Latent Trajectory Anchoring for Action Segmentation Dataset Condensation
  211. Toward Active Object Detection for UAVs in the Wild: A Large-Scale Dataset, Benchmark and Method
  212. Pitfalls and Remedies for Multi-Task Bayesian Optimization
  213. OmniMapBench: Benchmarking Visual-Centric Reasoning on Diverse Map Documents
  214. Inside the Skill Market: From Software Engineering Activities to Reusable Agent Skills
  215. EvoLP: Self-Evolving Latency Predictor for Model Compression in Real-Time Edge Systems
  216. ARCANA: A Reflective Multi-Agent Program Synthesis Framework for ARC-AGI-2 Reasoning
  217. STEAM: Stable Self-Training with Elastic Matching and Adaptive Purification
  218. An Emergent Mirage: Is Emergent Misalignment and Realignment Indeed a Robust Phenomenon?
  219. COBS: Cumulant Order Block Sparse Attention
  220. Variable-Length Generative Protein Design via Generalized Poisson Flow
  221. Quantum Logic as the Logic of Contexts
  222. Evolutionary Intelligence for Scientific Discovery: From Evolutionary Computation to Cumulative Discovery Systems
  223. Video Generation Models are General-Purpose Vision Learners
  224. Phone Segmentation and Recognition through Phonological Activation Mapping
  225. Correlation-Aware Contextual Bandits with Surrogate Rewards for LLM Routing