mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 22 Oct 2025

393 papers

  1. Policy Optimization Prefers The Path of Least ResistanceLLM reasoning → Test-time compute and efficient thinking
  2. SCoPE VLM: Selective Context Processing for Efficient Document Navigation in Vision-Language ModelsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG +1
  3. TowerVision: Understanding and Improving Multilinguality in Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  4. SynCast: Synergizing Contradictions in Precipitation Nowcasting via Diffusion Sequential Preference OptimizationLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  5. Training data membership inference via Gaussian process meta-modeling: a post-hoc analysis approachLLM safety and security → Membership inference attacks
  6. GAPO: Robust Advantage Estimation for Real-World Code LLMsLLM reasoning → Reinforcement learning for reasoning
  7. Structured and Abstractive Reasoning on Multi-modal Relational Knowledge ImagesLLM reasoning → Multimodal reasoning +1
  8. Not-a-Bandit: Provably No-Regret Drafter Selection in Speculative Decoding for LLMsEfficient LLM inference and serving → Speculative decoding
  9. Ask What Your Country Can Do For You: Towards a Public Red Teaming ModelLLM safety and security → Prompt injection and agent security
  10. Enhancing Reasoning Skills in Small Persian Medical Language Models Can Outperform Large-Scale Data TrainingLLM reasoning → Clinical and biomedical applications +1
  11. Learning Personalized Ad Impact via Contextual Reinforcement Learning under Delayed RewardsDeep reinforcement learning methods → RL theory and sample complexity
  12. ToolScope: Enhancing LLM Agent Tool Use through Tool Merging and Context-Aware FilteringLLM agents and tool use → Tool learning and function calling
  13. SALT: Step-level Advantage Assignment for Long-horizon Agents via Trajectory GraphLLM agents and tool use → Reinforcement learning for LLM agents
  14. Communication to Completion: Modeling Collaborative Workflows with Intelligent Multi-Agent CommunicationLLM agents and tool use → General LLM agent frameworks and benchmarks
  15. Rethinking Reasoning with MDLMs: Early Exits, Post-hoc Reasoning, and BeyondLLM reasoning → Diffusion reasoning and test-time scaling +1
  16. Automating Iconclass: LLMs and RAG for Large-Scale Classification of Religious WoodcutsRetrieval-augmented generation → Multimodal RAG
  17. A Tutorial on Cognitive Biases in Agentic AI-Driven 6G Autonomous NetworksLLM agents and tool use → Agentic AI for wireless networks
  18. Guiding diffusion models to reconstruct flow fields from sparse dataDiffusion models → Flow matching, time series and science
  19. LyriCAR: A Difficulty-Aware Curriculum Reinforcement Learning Framework For Controllable Lyric TranslationDeep reinforcement learning methods → RL training of language and agent models
  20. Robust Reinforcement Learning in Finance: Modeling Market Impact with Elliptic Uncertainty SetsDeep reinforcement learning methods → Adversarial robustness and RL in finance
  21. Surfer 2: The Next Generation of Cross-Platform Computer Use AgentsLLM agents and tool use → GUI and mobile agents
  22. Learning from Supervision with Semantic and Episodic Memory: A Reflective Approach to Agent AdaptationLLM agents and tool use → Agent memory systems
  23. Can They Dixit? Yes they Can! Dixit as a Playground for Multimodal Language Model CapabilitiesMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  24. Compressing Biology: Evaluating the Stable Diffusion VAE for Phenotypic Drug DiscoveryDiffusion models → Flow matching, time series and science
  25. Stream: Scaling up Mechanistic Interpretability to Long Context in LLMs via Sparse AttentionMechanistic interpretability → Knowledge and representations inside LLMs
  26. From Large to Small: Transferring CUDA Optimization Expertise via Reasoning GraphLLM reasoning → Reasoning for agents, planning and code +1
  27. An Integrated Approach to Neural Architecture Search for Deep Q-NetworksDeep reinforcement learning methods → Deep RL algorithms and representations
  28. From Denoising to Refining: A Corrective Framework for Vision-Language Diffusion ModelDiffusion models → Discrete and text diffusion
  29. Knowledge-Guided Multi-Agent Framework for Application-Level Software Code GenerationLLM agents and tool use → Software engineering coding agents
  30. Semantic World ModelsWorld models → Embodied and robot world models +1
  31. Hubble: a Model Suite to Advance the Study of LLM MemorizationLLM safety and security → Machine unlearning
  32. Scaf-GRPO: Scaffolded Group Relative Policy Optimization for Enhancing LLM ReasoningLLM reasoning → Reinforcement learning for reasoning
  33. The Art of Asking: Multilingual Prompt Optimization for Synthetic DataSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  34. Class-Aware Prototype Learning with Negative Contrast for Test-Time Adaptation of Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  35. Blackbox Model Provenance via Palimpsestic Membership InferenceLLM safety and security → Machine unlearning
  36. ToolDreamer: Instilling LLM Reasoning Into Tool RetrieversLLM reasoning → Knowledge- and tool-augmented reasoning +1
  37. OmniMotion-X: Versatile Multimodal Whole-Body Motion GenerationDiffusion models → Video generation
  38. Benchmarking World-Model Learning with Environment-Level QueriesWorld models → World models for language agents
  39. AdaSPEC: Selective Knowledge Distillation for Efficient Speculative DecodersEfficient LLM inference and serving → Speculative decoding +1
  40. Estimating Model-Level Membership Inference Vulnerability Without Reference ModelsLLM safety and security → Membership inference attacks
  41. Beyond Reactivity: Measuring Proactive Problem Solving in LLM AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  42. SmartSwitch: Advancing LLM Reasoning by Overcoming Underthinking via Promoting Deeper Thought ExplorationLLM reasoning → Test-time compute and efficient thinking
  43. SEA: Semantic Map Prediction for Active Exploration of Uncertain AreasDeep reinforcement learning methods → RL for robot navigation and UAV control
  44. A Survey on Cache Methods in Diffusion Models: Toward Efficient Multi-Modal GenerationDiffusion models → Diffusion foundations and sampling
  45. Learning Affordances at Inference-Time for Vision-Language-Action ModelsVision-language-action models → Reasoning and chain-of-thought in VLA
  46. Memo: Training Memory-Efficient Embodied Agents with Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  47. Fast Inference via Hierarchical Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  48. Toward Agentic Software Engineering Beyond Code: Framing Vision, Values, and VocabularyLLM agents and tool use → Software engineering coding agents
  49. I Spy With My Model's Eye: Visual Search as a Behavioural Test for MLLMsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  50. CoSense-LLM: Semantics at the Edge with Cost- and Uncertainty-Aware Cloud-Edge CooperationEfficient LLM inference and serving → Early exit and edge inference
  51. DiffAdapt: Difficulty-Adaptive Reasoning for Token-Efficient LLM InferenceLLM reasoning → Test-time compute and efficient thinking +1
  52. From Forecasting to Planning: Policy World Model for Collaborative State-Action PredictionWorld models → Embodied and robot world models +1
  53. CoRoVA: Compressed Representations for Vector-Augmented Code CompletionRetrieval-augmented generation → RAG for code
  54. HSCodeComp: A Realistic and Expert-level Benchmark for Deep Search Agents in Hierarchical Rule ApplicationLLM agents and tool use → Social simulation and multi-agent debate
  55. MedReason-R1: Learning to Reason for CT Diagnosis with Reinforcement Learning and Local ZoomLLM reasoning → Clinical and biomedical applications +2
  56. FidelityGPT: Correcting Decompilation Distortions with Retrieval Augmented GenerationRetrieval-augmented generation → RAG for code
  57. XBench: A Comprehensive Benchmark for Visual-Language Explanations in Chest RadiographyMultimodal LLMs / vision-language models → Medical vision-language models
  58. CBDiff:Conditional Bernoulli Diffusion Models for Image Forgery LocalizationDiffusion models → Image generation, text-to-image and editing
  59. Decomposed Attention Fusion in MLLMs for Training-Free Video Reasoning SegmentationLLM reasoning → Multimodal reasoning +1
  60. VGD: Visual Geometry Gaussian Splatting for Feed-Forward Surround-view Driving ReconstructionEnd-to-end autonomous driving → Generative simulation for driving
  61. DAIL: Beyond Task Ambiguity for Language-Conditioned Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  62. A Matter of Time: Revealing the Structure of Time in Vision-Language ModelsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  63. [De|Re]constructing VLMs' Reasoning in CountingLLM reasoning → Multimodal reasoning +1
  64. The Confusing Instance Principle for Online Linear Quadratic ControlDeep reinforcement learning methods → RL for games and combinatorial optimization
  65. Optimizing the Unknown: Black Box Bayesian Optimization with Energy-Based Model and Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  66. Learning Upper Lower Value Envelopes to Shape Online RL: A Principled ApproachDeep reinforcement learning methods → RL theory and sample complexity
  67. Modeling realistic human behavior using generative agents in a multimodal transport system: Software architecture and Application to ToulouseLLM agents and tool use → Multimodal and embodied agents
  68. CARES: Context-Aware Resolution Selector for VLMsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  69. Using Non-Expert Data to Robustify Imitation Learning via Offline Reinforcement LearningOffline RL and imitation learning from data → Imitation learning methods
  70. Machine Text Detectors are Membership Inference AttacksLLM safety and security → Membership inference attacks
  71. VideoAgentTrek: Computer Use Pretraining from Unlabeled VideosLLM agents and tool use → GUI and mobile agents
  72. Graph Unlearning Meets Influence-aware Negative Preference OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods +1
  73. A Concrete Roadmap towards Safety Cases based on Chain-of-Thought MonitoringLLM reasoning → Prompting and chain-of-thought reasoning
  74. g-DPO: Scalable Preference Optimization for Protein Language ModelsLLM alignment / RLHF / preference optimisation → Preference optimization for molecular design
  75. HybridEP: Scaling Expert Parallelism to Cross-Datacenter Scenario via Hybrid Expert/Data TransmissionMixture-of-experts → Efficient MoE training and inference systems
  76. AegisMCP: Online Graph Intrusion Detection for Tool-Augmented LLMs on Edge DevicesLLM agents and tool use → Agent threats, guardrails and governance
  77. MINED: Probing and Updating with Multimodal Time-Sensitive Knowledge for Large Multimodal ModelsMultimodal LLMs / vision-language models → Image editing and quality assessment
  78. Reasoning Like Experts: Leveraging Multimodal Large Language Models for Drawing-based PsychoanalysisLLM reasoning → Multimodal reasoning +1
  79. AutoMT: A Multi-Agent LLM Framework for Automated Metamorphic Testing of Autonomous Driving SystemsLLM agents and tool use → Multimodal and embodied agents
  80. GigaBrain-0: A World Model-Powered Vision-Language-Action ModelWorld models → Embodied and robot world models +1
  81. NeSyPr: Neurosymbolic Proceduralization For Efficient Embodied ReasoningLLM reasoning → Spatial and embodied reasoning
  82. ETOM: A Five-Level Benchmark for Evaluating Tool Orchestration within the MCP EcosystemLLM agents and tool use → Tool learning and function calling
  83. LLM Unlearning with LLM BeliefsLLM safety and security → Machine unlearning
  84. Securing Multi-Agent Systems Against Corruptions via Node Contribution BackpropagationLLM agents and tool use → Agent threats, guardrails and governance
  85. Seeing Across Views: Benchmarking Spatial Reasoning of Vision-Language Models in Robotic ScenesLLM reasoning → Spatial and embodied reasoning +1
  86. ColorAgent: Building A Robust, Personalized, and Interactive OS AgentLLM agents and tool use → GUI and mobile agents
  87. Optimization Benchmark for Diffusion Models on Dynamical SystemsDiffusion models → Diffusion foundations and sampling
  88. On the Hardness of Reinforcement Learning with Transition Look-AheadDeep reinforcement learning methods → RL theory and sample complexity
  89. MoE-Prism: Disentangling Monolithic Experts for Elastic MoE Services via Model-System Co-DesignsMixture-of-experts → Efficient MoE training and inference systems
  90. ProTerrain: Probabilistic Physics-Informed Rough Terrain World ModelingWorld models → World models for navigation
  91. LoongRL: Reinforcement Learning for Advanced Reasoning over Long ContextsLLM reasoning → Test-time compute and efficient thinking
  92. AgenticMath: Enhancing LLM Reasoning via Agentic-based Math Data GenerationLLM reasoning → Mathematical reasoning +1
  93. M3-SLU: Evaluating Speaker-Attributed Reasoning in Multimodal Large Language ModelsLLM reasoning → Audio-language model reasoning +1
  94. Imitation Learning Policy based on Multi-Step Consistent Integration Shortcut ModelDiffusion models → Diffusion and flow policies for robotics +1
  95. DaMo: Data Mixing Optimizer in Fine-tuning Multimodal LLMs for Mobile Phone AgentsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  96. A Training-Free Framework for Open-Vocabulary Image Segmentation and Recognition with EfficientNet and CLIPMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  97. Slot Filling as a Reasoning Task for SpeechLLMsLLM reasoning → Reasoning benchmarks and evaluation
  98. Balancing Rewards in Text Summarization: Multi-Objective Reinforcement Learning via HyperVolume OptimizationDeep reinforcement learning methods → RL training of language and agent models
  99. KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented ControlsMultimodal LLMs / vision-language models → Image editing and quality assessment
  100. Continual Knowledge Adaptation for Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
All 393
  1. Unified Reinforcement and Imitation Learning for Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  2. Loopholing Discrete Diffusion: Deterministic Bypass of the Sampling WallDiffusion models → Discrete and text diffusion +1
  3. Collaborative penetration testing suite for emerging generative AI algorithmsLLM safety and security → Prompt injection and agent security
  4. Learning to Make Friends: Coaching LLM Agents toward Emergent Social TiesLLM agents and tool use → Social simulation and multi-agent debate
  5. Knowledge Distillation of Uncertainty using Deep Latent Factor ModelKnowledge distillation → General knowledge distillation methods
  6. TheMCPCompany: Creating General-purpose Agents with Task-specific ToolsLLM agents and tool use → Tool learning and function calling
  7. D2D: Detector-to-Differentiable Critic for Improved Numeracy in Text-to-Image GenerationDiffusion models → Image generation, text-to-image and editing
  8. From Specification to Service: Accelerating API-First Development Using Multi-Agent SystemsLLM agents and tool use → Software engineering coding agents
  9. SCEESR: Semantic-Control Edge Enhancement for Diffusion-Based Super-ResolutionDiffusion models → Inverse problems and image restoration
  10. Social World Model-Augmented Mechanism Design Policy LearningWorld models → World models for language agents
  11. Data Efficient Any Transformer-to-Mamba Distillation via Attention BridgeState-space sequence models (S4, Mamba) → Core SSM architectures for language
  12. Difficulty-Controllable Multiple-Choice Question Generation Using Large Language Models and Direct Preference OptimizationLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  13. RailS: Load Balancing for All-to-All Communication in Distributed Mixture-of-Experts TrainingMixture-of-experts → Efficient MoE training and inference systems
  14. SheetBrain: A Neuro-Symbolic Agent for Accurate Reasoning over Complex and Large SpreadsheetsLLM reasoning → Knowledge- and tool-augmented reasoning +1
  15. See, Think, Act: Online Shopper Behavior Simulation with VLM AgentsLLM reasoning → Reasoning for agents, planning and code +1
  16. Interpret Policies in Deep Reinforcement Learning using SILVER with RL-Guided Labeling: A Model-level Approach to High-dimensional and Multi-action EnvironmentsDeep reinforcement learning methods → Interpretable and logic-guided RL
  17. SPOT: Scalable Policy Optimization with Trees for Markov Decision ProcessesDeep reinforcement learning methods → Interpretable and logic-guided RL
  18. Controllable Machine Unlearning via Gradient PivotingLLM safety and security → Machine unlearning
  19. RLBoost: Harvesting Preemptible Resources for Cost-Efficient Reinforcement Learning on LLMsLLM reasoning → Reinforcement learning for reasoning
  20. Enhancing Graph Neural Networks: A Mutual Learning ApproachKnowledge distillation → Graph neural network distillation
  21. MoE-GS: Mixture of Experts for Dynamic Gaussian SplattingMixture-of-experts → Vision mixture-of-experts
  22. Defending Against Prompt Injection with DataFilterLLM safety and security → Prompt injection and agent security
  23. WebGraphEval: Multi-Turn Trajectory Evaluation for Web Agents using Graph RepresentationLLM agents and tool use → Web, search, and research agents
  24. A Communication-Efficient Decentralized Actor-Critic AlgorithmDeep reinforcement learning methods → RL for games and combinatorial optimization
  25. Rethinking Driving World Model as Synthetic Data Generator for Perception TasksWorld models → World models for autonomous driving +1
  26. Video Consistency Distance: Enhancing Temporal Consistency for Image-to-Video Generation via Reward-Based Fine-TuningDiffusion models → Video generation
  27. PruneHal: Reducing Hallucinations in Multi-modal Large Language Models through Adaptive KV Cache PruningMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs +1
  28. Interpretable Question Answering with Knowledge GraphsRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  29. The Zero-Step Thinking: An Empirical Study of Mode Selection as Harder Early Exit in Reasoning ModelsLLM reasoning → Test-time compute and efficient thinking
  30. Think Straight, Stop Smart: Structured Reasoning for Efficient Multi-Hop RAGRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  31. OpenGuardrails: A Configurable, Unified, and Scalable Guardrails Platform for Large Language ModelsLLM safety and security → Safety alignment, refusal and guardrails
  32. Step-Aware Residual-Guided Diffusion for EEG Spatial Super-ResolutionDiffusion models → Medical imaging and segmentation
  33. Preliminary Use of Vision Language Model Driven Extraction of Mouse Behavior Towards Understanding Fear ExpressionMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  34. HAMLOCK: HArdware-Model LOgically Combined attacKLLM safety and security → Backdoor and data poisoning attacks
  35. Policy Gradient Method for LQG Control via Input-Output-History Representation: Convergence to O(ε)-Stationary PointsDeep reinforcement learning methods → RL for games and combinatorial optimization
  36. DyPBP: Dynamic Peer Beneficialness Prediction for Cryptocurrency P2P Networking
  37. Affordable EEG, Actionable Insights: An Open Dataset and Evaluation Framework for Epilepsy Patient Stratification
  38. A Machine Learning-Based Framework to Shorten the Questionnaire for Assessing Autism Intervention
  39. Dingtalk DeepResearch: A Unified Multi Agent Framework for Adaptive Intelligence in Enterprise Environments
  40. Genotype-Phenotype Integration through Machine Learning and Personalized Gene Regulatory Networks for Cancer Metastasis Prediction
  41. SIGN: Schema-Induced Games for Naming
  42. Interpretable Diagnostics and Adaptive Data Assimilation for Neural ODEs via Discrete Empirical Interpolation
  43. Data-Driven Approach to Capitation Reform in Rwanda
  44. KARIPAP: Quantum-Inspired Tensor Network Compression of Large Language Models Using Infinite Projected Entangled Pair States and Tensor Renormalization Group
  45. Modal Aphasia: Can Unified Multimodal Models Describe Images From Memory?
  46. RatioWaveNet: A Learnable RDWT Front-End for Robust and Interpretable EEG Motor-Imagery Classification
  47. Improving the Physics of Video Generation with VJEPA-2 Reward Signal
  48. Evaluating ChatGPT's Performance in Classifying Pneumonia from Chest X-Ray Images
  49. Quantum Autoencoders for Anomaly Detection in Cybersecurity
  50. COLA: Continual Learning via Autoencoder Retrieval of Adapters
  51. A Multimodal, Multitask System for Generating E Commerce Text Listings from Images
  52. Restoring Pruned Large Language Models via Lost Component Compensation
  53. Towards Accurate and Efficient Waste Image Classification: A Hybrid Deep Learning and Machine Learning Approach
  54. A Flow Model with Low-Rank Transformers for Incomplete Multimodal Survival Analysis
  55. Precise classification of low quality G-banded Chromosome Images by reliability metrics and data pruning classifier
  56. Fuzzy numbers revisited: operations on extensional fuzzy numbers
  57. Data-Centric Lessons To Improve Speech-Language Pretraining
  58. Lightweight Classifier for Detecting Intracranial Hemorrhage in Ultrasound Data
  59. Beyond Hearing: Learning Task-Agnostic ExG Representations from Earphones via Physiology-Informed Tokenization
  60. Alternatives to the Laplacian for Scalable Spectral Clustering with Group Fairness Constraints
  61. Data-Adaptive Transformed Bilateral Tensor Low-Rank Representation for Clustering
  62. LLMs can hide text in other text of the same length
  63. Filter-Based Reconstruction of Images from Events
  64. Coupled Transformer Autoencoder for Disentangling Multi-Region Neural Latent Dynamics
  65. A Multi-Layer Machine Learning and Econometric Pipeline for Forecasting Market Risk: Evidence from Cryptoasset Liquidity Spillovers
  66. Endogenous Aggregation of Multiple Data Envelopment Analysis Scores for Large Data Sets
  67. From Facts to Folklore: Evaluating Large Language Models on Bengali Cultural Knowledge
  68. Exposing Blindspots: Cultural Bias Evaluation in Generative Image Models
  69. Approximate Model Predictive Control for Microgrid Energy Management via Imitation Learning
  70. Beyond One-Way Influence: Bidirectional Opinion Dynamics in Multi-Turn Human-LLM Interactions
  71. Throwing Vines at the Wall: Structure Learning via Random Search
  72. Improving Transfer Learning for Sequence Labeling Tasks by Adapting Pre-trained Neural Language Models
  73. Speculative Sampling for Parametric Temporal Point Processes
  74. On Encoding Matrices using Quantum Circuits
  75. BrainPuzzle: Hybrid Physics and Data-Driven Reconstruction for Transcranial Ultrasound Tomography
  76. The Temporal Graph of Bitcoin Transactions
  77. Extreme Views: 3DGS Filter for Novel View Synthesis from Out-of-Distribution Camera Poses
  78. Optimized Distortion in Linear Social Choice
  79. Machine Learning-Based Localization Accuracy of RFID Sensor Networks via RSSI Decision Trees and CAD Modeling for Defense Applications
  80. Simultaneously Solving Infinitely Many LQ Mean Field Games In Hilbert Spaces: The Power of Neural Operators
  81. A Unified Detection Pipeline for Robust Object Detection in Fisheye-Based Traffic Surveillance
  82. AI Pose Analysis and Kinematic Profiling of Range-of-Motion Variations in Resistance Training
  83. Improving Predictive Confidence in Medical Imaging via Online Label Smoothing
  84. Forging GEMs: Advancing Greek NLP through Quality-Based Corpus Curation
  85. Beyond MedQA: Towards Real-world Clinical Decision Making in the Era of LLMs
  86. Enhanced Cyclic Coordinate Descent Methods for Elastic Net Penalized Linear Models
  87. A Framework for the Adoption and Integration of Generative AI in Midsize Organizations and Enterprises (FAIGMOE)
  88. A Fundamental Algorithm for Dependency Parsing (With Corrections)
  89. LLM-Augmented Symbolic NLU System for More Reliable Continuous Causal Statement Interpretation
  90. FutrTrack: A Camera-LiDAR Fusion Transformer for 3D Multiple Object Tracking
  91. Abstain Mask Retain Core: Time Series Prediction by Adaptive Masking Loss with Representation Consistency
  92. SecureInfer: Heterogeneous TEE-GPU Architecture for Privacy-Critical Tensors for Large Language Model Deployment
  93. Towards Strong Certified Defense with Universal Asymmetric Randomization
  94. Revisiting Zeroth-Order Optimization: Minimum-Variance Two-Point Estimators and Directionally Aligned Perturbations
  95. AI-Driven Personalized Learning: Predicting Academic Per-formance Through Leadership Personality Traits
  96. A new wave of vehicle insurance fraud fueled by generative AI
  97. Transformed Multi-view 3D Shape Features with Contrastive Learning
  98. RELATE: A Schema-Agnostic Perceiver Encoder for Multimodal Relational Graphs
  99. On the Optimal Construction of Unbiased Gradient Estimators for Zeroth-Order Optimization
  100. Seed3D 1.0: From Images to High-Fidelity Simulation-Ready 3D Assets
  101. Are Greedy Task Orderings Better Than Random in Continual Linear Regression?
  102. Mitigating Privacy-Utility Trade-off in Decentralized Federated Learning via f-Differential Privacy
  103. Beyond the Ideal: Analyzing the Inexact Muon Update
  104. FINDER: Feature Inference on Noisy Datasets using Eigenspace Residuals
  105. BugPilot: Complex Bug Generation for Efficient Learning of SWE Skills
  106. Enhancing Diagnostic Accuracy for Urinary Tract Disease through Explainable SHAP-Guided Feature Selection and Classification
  107. Large Language Model enabled Mathematical Modeling
  108. EQPO: Equitable Group Relative Policy Optimization for Clinical Reasoning
  109. Deep Sequence-to-Sequence Models for GNSS Spoofing Detection
  110. From Optimization to Prediction: Transformer-Based Path-Flow Estimation to the Traffic Assignment Problem
  111. An Expert-grounded benchmark of General Purpose LLMs in LCA
  112. Quantifying Feature Importance for Online Content Moderation
  113. Automated HIV Screening on Dutch Electronic Health Records with Large Language Models
  114. Transforming Multi-Omics Integration with GANs: Applications in Alzheimer's and Cancer
  115. Artificial Intelligence Powered Identification of Potential Antidiabetic Compounds in Ficus religiosa
  116. An Evaluation of the Pedagogical Soundness and Usability of AI-Generated Lesson Plans Across Different Models and Prompt Frameworks in High-School Physics
  117. SODBench: A Large Language Model Approach to Documenting Spreadsheet Operations
  118. Is This Tracker On? A Benchmark Protocol for Dynamic Tracking
  119. olmOCR 2: Unit Test Rewards for Document OCR
  120. Toward A Better Understanding of Monocular Depth Evaluation
  121. Pico-Banana-400K: A Large-Scale Dataset for Text-Guided Image Editing
  122. The Feasibility of Training Sovereign Language Models in the Global South: A Study of Brazil and Mexico
  123. Integrating Transparent Models, LLMs, and Practitioner-in-the-Loop: A Case of Nonprofit Program Evaluation
  124. Transformers are almost optimal metalearners for linear classification
  125. On Controlled Change: Generative AI's Impact on Professional Authority in Journalism
  126. Environment Inference for Learning Generalizable Dynamical System
  127. Adapting Multilingual Models to Code-Mixed Tasks via Model Merging
  128. GaLLoP: Gradient-based Sparse Learning on Low-Magnitude Parameters
  129. Exploring the Effect of DNN Depth on Adversarial Attacks in Network Intrusion Detection Systems
  130. Adaptive Distribution-aware Quantization for Mixed-Precision Neural Networks
  131. CONFEX: Uncertainty-Aware Counterfactual Explanations with Conformal Guarantees
  132. Transformers Provably Learn Algorithmic Solutions for Graph Connectivity, But Only with the Right Data
  133. BATIS: Bayesian Approaches for Targeted Improvement of Species Distribution Models
  134. Misalignment Bounty: Crowdsourcing AI Agent Misbehavior
  135. Statistical Inference for Linear Functionals of Online Least-squares SGD when t gtrsim d1+δ
  136. Zhyper: Factorized Hypernetworks for Conditioned LLM Fine-Tuning
  137. Bridging Earth and Space: A Survey on HAPS for Non-Terrestrial Networks
  138. Enabling Granular Subgroup Level Model Evaluations by Generating Synthetic Medical Time Series
  139. From Answers to Guidance: A Proactive Dialogue System for Legal Documents
  140. LyTimeT: Towards Robust and Interpretable State-Variable Discovery
  141. SEMPO: Lightweight Foundation Models for Time Series Forecasting
  142. RLIE: Rule Generation with Logistic Regression, Iterative Refinement, and Evaluation for Large Language Models
  143. Explainable Face Presentation Attack Detection via Ensemble-CAM
  144. Do Prompts Reshape Representations? An Empirical Study of Prompting Effects on Embeddings
  145. Serverless GPU Architecture for Enterprise HR Analytics: A Production-Scale BDaaS Implementation
  146. Are Large Language Models Sensitive to the Motives Behind Communication?
  147. Directive, Metacognitive or a Blend of Both? A Comparison of AI-Generated Feedback Types on Student Engagement, Confidence, and Outcomes
  148. Curvilinear Structure-preserving Unpaired Cross-domain Medical Image Translation
  149. Study of Training Dynamics for Memory-Constrained Fine-Tuning
  150. Policy Learning with Abstention
  151. Explainable e-sports win prediction through Machine Learning classification in streaming
  152. Unraveling Emotions with Pre-Trained Models
  153. A Graph Engine for Guitar Chord-Tone Soloing Education
  154. Remarks on a recent preprint of Chernikov and Towsner
  155. AgentSense: LLMs Empower Generalizable and Explainable Web-Based Participatory Urban Sensing
  156. Overlap-weighted orthogonal meta-learner for treatment effect estimation over time
  157. Style Attack Disguise: When Fonts Become a Camouflage for Adversarial Intent
  158. Latent Space Factorization in LoRA
  159. Matrix-Free Least Squares Solvers: Values, Gradients, and What to Do With Them
  160. CrossNews-UA: A Cross-lingual News Semantic Similarity Benchmark for Ukrainian, Polish, Russian, and English
  161. Learning and Simulating Building Evacuation Patterns for Enhanced Safety Design Using Generative Models
  162. Augmenting Moment Retrieval: Zero-Dependency Two-Stage Learning
  163. Pragmatic Heterogeneous Collaborative Perception via Generative Communication Mechanism
  164. PBBQ: A Persian Bias Benchmark Dataset Curated with Human-AI Collaboration for Large Language Models
  165. Beyond sparse denoising in frames: minimax estimation with a scattering transform
  166. A Climate-Aware Deep Learning Framework for Generalizable Epidemic Forecasting
  167. Human-Agent Collaborative Paper-to-Page Crafting
  168. A Goal-Driven Survey on Root Cause Analysis
  169. Comparing Uniform Price and Discriminatory Multi-Unit Auctions through Regret Minimization
  170. Digitizing Paper ECGs at Scale: An Open-Source Algorithm for Clinical Research
  171. Uncertainty evaluation of segmentation models for Earth observation
  172. Detecting Latin in Historical Books with Large Language Models: A Multimodal Benchmark
  173. Addressing the Depth-of-Field Constraint: A New Paradigm for High Resolution Multi-Focus Image Fusion
  174. Multi-modal Co-learning for Earth Observation: Enhancing single-modality models via modality collaboration
  175. Can You Trust What You See? Alpha Channel No-Box Attacks on Video Object Detection
  176. HAD: Hierarchical Asymmetric Distillation to Bridge Spatio-Temporal Gaps in Event-Based Object Tracking
  177. The Intricate Dance of Prompt Complexity, Quality, Diversity, and Consistency in T2I Models
  178. Conditions for Catastrophic Forgetting in Multilingual Translation
  179. Demonstrating Real Advantage of Machine-Learning-Enhanced Monte Carlo for Combinatorial Optimization
  180. Insights into the Unknown: Federated Data Diversity Analysis on Molecular Data
  181. PoseCrafter: Extreme Pose Estimation with Hybrid Video Synthesis
  182. Bi-Level Decision-Focused Causal Learning for Large-Scale Marketing Optimization: Bridging Observational and Experimental Data
  183. From Prototypes to Sparse ECG Explanations: SHAP-Driven Counterfactuals for Multivariate Time-Series Multi-class Classification
  184. Which Evaluation for Which Model? A Taxonomy for Speech Model Assessment
  185. Teaming LLMs to Detect and Mitigate Hallucinations
  186. Lookahead Routing for Large Language Models
  187. Energy-Efficient and Dequantization-Free Q-LLMs: A Spiking Neural Network Approach to Salient Value Mitigation
  188. What is the Best Sequence Length for BABYLM?
  189. Towards Single-Source Domain Generalized Object Detection via Causal Visual Prompts
  190. KnowMol: Advancing Molecular Large Language Models with Multi-Level Chemical Knowledge
  191. ELUTQ: Optimizing Quantization Accuracy under LUT-Based Computation for Edge LLMs
  192. Online Two-Stage Submodular Maximization
  193. Mitigating representation bias caused by missing pixels in methane plume detection
  194. PRGCN: A Graph Memory Network for Cross-Sequence Pattern Reuse in 3D Human Pose Estimation
  195. Predicting before Reconstruction: A generative prior framework for MRI acceleration
  196. Re-evaluating Minimum Bayes Risk Decoding for Automatic Speech Recognition
  197. PCP-GAN: Property-Constrained Pore-scale image reconstruction via conditional Generative Adversarial Networks
  198. Exploring "Many in Few" and "Few in Many" Properties in Long-Tailed, Highly-Imbalanced IC Defect Classification
  199. Automated Morphological Analysis of Neurons in Fluorescence Microscopy Using YOLOv8
  200. A Foundational Theory of Quantitative Abstraction: Adjunctions, Duality, and Logic for Probabilistic Systems
  201. Multi-Camera Worker Tracking in Logistics Warehouse Considering Wide-Angle Distortion
  202. Revisiting the Relation Between Robustness and Universality
  203. Neural Variational Dropout Processes
  204. FairNet: Dynamic Fairness Correction without Performance Loss via Contrastive Conditional LoRA
  205. BLiSS 1.0: Evaluating Bilingual Learner Competence in Second Language Small Language Models
  206. From See to Shield: ML-Assisted Fine-Grained Access Control for Visual Data
  207. EchoFake: A Replay-Aware Dataset for Practical Speech Deepfake Detection
  208. Spatio-temporal Sign Language Representation and Translation
  209. ToMMeR -- Efficient Entity Mention Detection from Large Language Models
  210. Iterative Training of Physics-Informed Neural Networks with Fourier-enhanced Features
  211. SONAR-SLT: Multilingual Sign Language Translation via Language-Agnostic Sentence Embedding Supervision
  212. ARA: Adaptive Rank Allocation for Efficient Large Language Model SVD Compression
  213. Beyond Uniform SVD:Dual-Level Optimization across Columns and Modules for LLM Compression
  214. Learning Noise-Resilient and Transferable Graph-Text Alignment via Dynamic Quality Assessment
  215. LMFD: Latent Monotonic Feature Discovery
  216. A Derandomization Framework for Structure Discovery: Applications in Neural Networks and Beyond
  217. Survival of the fittest Cox model: Pivotal variable selection for time-to-event data
  218. Using Temperature Sampling to Effectively Train Robot Learning Policies on Imbalanced Datasets
  219. AegisRF: Adversarial Perturbations Guided with Sensitivity for Protecting Intellectual Property of Neural Radiance Fields
  220. AMAuT: A Flexible and Efficient Multiview Audio Transformer Framework Trained from Scratch
  221. Sign Language Translation with Sentence Embedding Supervision
  222. The Massive Legal Embedding Benchmark (MLEB)
  223. Autobidding Arena: unified evaluation of the classical and RL-based autobidding algorithms
  224. DARE: A Deformable Adaptive Regularization Estimator for Learning-Based Medical Image Registration
  225. ConvXformer: Differentially Private Hybrid ConvNeXt-Transformer for Inertial Navigation
  226. Learning To Defer To A Population With Limited Demonstrations
  227. Modeling Turn-Taking with Semantically Informed Gestures
  228. Scalable LinUCB: Low-Rank Design Matrix Updates for Recommenders with Large Action Spaces
  229. A Markov Decision Process for Variable Selection in Branch & Bound
  230. A New Type of Adversarial Examples
  231. Local Obfuscation by GLINER for Impartial Context Aware Lineage: Development and evaluation of PII Removal system
  232. Foundation Model Forecasts: Form and Function
  233. To Use or to Refuse? Re-Centering Student Agency with Generative AI in Engineering Design Education
  234. Nonmonotone subgradient methods based on a local descent lemma
  235. Every Attention Matters: An Efficient Hybrid Architecture for Long-Context Reasoning
  236. Metadata Extraction Leveraging Large Language Models
  237. BrainMCLIP: Brain Image Decoding with Multi-Layer feature Fusion of CLIP
  238. Algorithmic Fairness in NLP: Persona-Infused LLMs for Human-Centric Hate Speech Detection
  239. Exploring Scale Shift in Crowd Localization under the Context of Domain Generalization
  240. Seabed-Net: A multi-task network for joint bathymetry estimation and seabed classification from remote sensing imagery in shallow waters
  241. Clustered Calibration: Representation-Aware Probability Calibration via Learned Subpopulations
  242. SORA-ATMAS: Adaptive Trust Management and Multi-LLM Aligned Governance for Future Smart Cities
  243. Enabling Reconfiguration-Communication Overlap for Collective Communication in Optical Networks
  244. Online Handwritten Signature Verification Based on Temporal-Spatial Graph Attention Transformer
  245. HAD: HAllucination Detection Language Models Based on a Comprehensive Hallucination Taxonomy
  246. Transformers are Inherently Succinct
  247. JointCQ: Improving Factual Hallucination Detection with Joint Claim and Query Generation
  248. Topology of Currencies: Persistent Homology for FX Co-movements: A Comparative Clustering Study
  249. FrogDeepSDM: Improving Frog Counting and Occurrence Prediction Using Multimodal Data and Pseudo-Absence Imputation
  250. Knowledge and Common Knowledge of Strategies
  251. QiMeng-SALV: Signal-Aware Learning for Verilog Code Generation
  252. Vision-Based Mistake Analysis in Procedural Activities: A Review of Advances and Challenges
  253. Error Analysis of Triangular Optimal Transport Maps for Filtering
  254. Enhancing Early Alzheimer Disease Detection through Big Data and Ensemble Few-Shot Learning
  255. Magnetic field estimation using Gaussian process regression for interactive wireless power system design
  256. MobiAct: Efficient MAV Action Recognition Using MobileNetV4 with Contrastive Learning and Knowledge Distillation
  257. Hierarchical DLO Routing with Reinforcement Learning and In-Context Vision-language Models
  258. LAPRAD: LLM-Assisted PRotocol Attack Discovery
  259. An Argumentative Explanation Framework for Generalized Reason Model with Inconsistent Precedents
  260. ChatGPT Unveils Its Limits: Principles of Law Deliver Checkmate
  261. FnRGNN: Distribution-aware Fairness in Graph Neural Network
  262. Advances in 4D Representation: Geometry, Motion, and Interaction
  263. Synthesizability Prediction of Crystalline Structures with Structure-Aware Feature Learning and Uncertainty Quantification
  264. Background Fades, Foreground Leads: Curriculum-Guided Background Pruning for Efficient Foreground-Centric Collaborative Perception
  265. Mixing Configurations for Downstream Prediction
  266. Understanding the Implicit Biases of Design Choices for Time Series Foundation Models
  267. Brain-Inspired Perspective on Configurations: Unsupervised Similarity and Early Cognition
  268. Space Object Detection using Multi-frame Temporal Trajectory Completion Method
  269. Modality Matching Matters: Calibrating Language Distances for Cross-Lingual Transfer in URIEL+
  270. SFGFusion: Surface Fitting Guided 3D Object Detection with 4D Radar and Camera Fusion
  271. No Intelligence Without Statistics: The Invisible Backbone of Artificial Intelligence
  272. DiSRouter: Distributed Self-Routing for LLM Selections
  273. Shrinkage to Infinity: Reducing Test Error by Inflating the Minimum Norm Interpolator in Linear Models
  274. Aligning Multilingual News for Stock Return Prediction
  275. An Active Diffusion Neural Network for Graphs
  276. GRASPLAT: Enabling dexterous grasping through novel view synthesis
  277. When Users Are Happy but Agents Are Wrong: Multi-Dimensional Evaluation of Tool-Augmented Dialogue
  278. Malaria Detection from Blood Cell Images Using XceptionNet
  279. Imbalanced Gradients in RL Post-Training of Multi-Task LLMs
  280. News-Aware Direct Reinforcement Trading for Financial Markets
  281. When Facts Change: Probing LLMs on Evolving Knowledge with evolveQA
  282. FootFormer: Estimating Stability from Visual Input
  283. Transfer Learning Beyond the Standard Model
  284. "You Are Rejected!": An Empirical Study of Large Language Models Taking Hiring Evaluations
  285. Natural Gradient VI: Guarantees for Non-Conjugate Models
  286. Extreme Event Aware (η-) Learning
  287. Instance-Dependent Regret Bounds for Nonstochastic Linear Partial Monitoring
  288. VeFA: Vector-Based Feature Space Adaptation for Robust Model Fine-Tuning
  289. Subliminal Corruption: Mechanisms, Thresholds, and Interpretability
  290. X-Ego: Acquiring Team-Level Tactical Situational Awareness via Cross-Egocentric Contrastive Video Representation Learning
  291. Tibetan Language and AI: A Comprehensive Survey of Resources, Methods and Challenges
  292. A Multi-faceted Analysis of Cognitive Abilities: Evaluating Prompt Methods with Large Language Models on the CONSORT Checklist
  293. Learning Granger Causality under Latent Confounding via Intervention-Induced Heterogeneity