mlsanityData to 14 Oct 2026

Papers

New on arXiv

Fri 5 Jun 2026

436 papers

  1. CIFQA: A Deterministic Tool-Grounded Multi-Agent LLM Framework for Financial Query AnsweringLLM agents and tool use → Financial trading and forecasting agents
  2. Latent Space Refusal Anchoring for Low-Resource African Languages: Mechanistic Safety Recovery Without RetrainingLLM safety and security → Safety alignment, refusal and guardrails +1
  3. Coarse-to-Fine Multi-Resolution Diffusion Models for Trajectory Generation in Urban SystemsDiffusion models → Diffusion and flow policies for robotics
  4. Position: The Alignment Community is Unintentionally Building a Censor's ToolkitLLM safety and security → Safety alignment, refusal and guardrails
  5. SAE-StatSteer: Statistical Consensus Feature Selection for Optimization-Free Activation Steering of Large Language ModelsMechanistic interpretability → Activation steering methods
  6. GraphContainer: A Unified Platform for Comparing and Debugging Graph RAG MethodsRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  7. From Tools to Teacher-Built Teammates: No-Code Pedagogical Plugin Authoring with LearnAdapt Agentic Studio and PedOS 1.1 LuminaLLM agents and tool use → Educational agents and math problem solving
  8. Sifei at SemEval-2026 Task 8: Hybrid Retrieval and Query Rewriting for Multi-Turn RAGRetrieval-augmented generation → Generation and context integration
  9. Why Memory Components Fail: Eight Years of License and Sustainability Events in Open-Source Data InfrastructureLLM agents and tool use → Software engineering coding agents
  10. SPARC: A Multi-Agent System for Electrical Circuit Question AnsweringLLM reasoning → Reasoning for agents, planning and code +1
  11. Continuous Audio Thinking for Large Audio Language ModelsLLM reasoning → Audio-language model reasoning
  12. Mitigating Anchoring Bias in LLM-Based Agents for Energy-Efficient 6G Autonomous NetworksLLM agents and tool use → Agentic AI for wireless networks
  13. NAVI-Orbital: First In-Orbit Demonstration of a Zero-Shot Vision-Language Model for Autonomous Earth ObservationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  14. Is My Vision-Language Data in Your AI? Membership Inference Test (MINT) Demo 2LLM safety and security → Membership inference attacks
  15. C-MambaPose: A Physics-Informed Complex Mamba Framework for Cross-Environment WiFi Human Pose EstimationState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
  16. On the Controllability-Fidelity Frontier in Diffusion EditingDiffusion models → Image generation, text-to-image and editing
  17. Less Context, More Accuracy: A Bi-Temporal Memory Engine for LLM Agents Where a Lean Retrieved Context Beats the Full HistoryLLM agents and tool use → Agent memory systems
  18. When Attribution Patching Lies: Diagnosis and a Second-Order CorrectionMechanistic interpretability → Knowledge and representations inside LLMs
  19. Contract2Tool: Learning Preconditions and Effects for Reliable Tool-Augmented LLM AgentsLLM agents and tool use → Tool learning and function calling
  20. TBD-VLA: Temporal Block Diffusion Vision Language Action ModelVision-language-action models → Efficient VLA inference and adaptation
  21. Strained Coherence: A Pre-Failure Signal in Coding Agent Execution TrajectoriesLLM agents and tool use → Software engineering coding agents
  22. Still: Amortized KV Cache Compaction in a Single Forward PassEfficient LLM inference and serving → KV cache optimization
  23. VisualFLIP: Do Predictions Depend on Task-Critical Visual Evidence in Multimodal Reasoning?LLM reasoning → Multimodal reasoning +1
  24. The Cold-Start Safety Gap in LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance
  25. The Last Visible Pixel: Probing Fine-Scale Perception in Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  26. Teacher-Free Self-Training Amplifies but Does Not Compound: A Pass@K Crossover on a Free-Verifier DomainSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training
  27. Path Planning Using Deep Deterministic Policy Gradient: A Reinforcement Learning ApproachDeep reinforcement learning methods → RL for robot navigation and UAV control
  28. Cost-Aware Speculative Execution for LLM-Agent Workflows: An Integrated Five-Dimension MethodLLM agents and tool use → Software engineering coding agents
  29. GRPO Does Not Close the Multi-Agent Coordination GapLLM reasoning → Reinforcement learning for reasoning +1
  30. RACT: Retrieval Augmented Column-Table Learning and Prediction for Multi-Table Schema MatchingRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  31. Mitigating the Contractivity Trap in Diffusion ODEs via Stein StabilizationDiffusion models → Diffusion foundations and sampling
  32. Beyond Pass/Fail: Using Process Mining to Understand How LLMs Resist (and Fail) Red Team AttacksLLM safety and security → Prompt injection and agent security
  33. Representational Similarity and Model Behavior in Multi-Agent InteractionLLM agents and tool use → Social simulation and multi-agent debate
  34. Where Instruction Hierarchy Breaks: Diagnosing and Repairing Failures in Reasoning Language ModelsLLM reasoning → Reasoning benchmarks and evaluation +1
  35. Beyond Goodhart's Law: A Dynamic Benchmark for Evaluating Compliance in Multi-Agent SystemsLLM agents and tool use → Agent threats, guardrails and governance
  36. Improving Multimodal Reasoning via Worst Dimension OptimizationLLM reasoning → Multimodal reasoning
  37. Byzantine Cheap Talk: Adversarial Resilience and Topology Effects in LLM Coordination GamesLLM agents and tool use → General LLM agent frameworks and benchmarks
  38. Evaluating RAG Reliability under Clean, Misleading, and Mixed RetrievalRetrieval-augmented generation → RAG robustness and adaptive retrieval
  39. Why Limit the Residual Stream to Layers and Not Tokens? Persistent Memory for Continuous Latent ReasoningLLM reasoning → Test-time compute and efficient thinking
  40. A case study of evaluating AI agents on a neuroscience data-to-discovery pipelineLLM agents and tool use → Web, search, and research agents
  41. MatMind: A Structure-Activity Knowledge-Driven Generative Foundation Model for Materials ScienceDiffusion models → Flow matching, time series and science
  42. Rosetta Memory: Adaptive Memory for Cross-LLM AgentsLLM agents and tool use → Agent memory systems
  43. WhiFlash: Accelerating Speculative Decoding with Token-Level Cross-Paradigm RoutingLLM agents and tool use → Software engineering coding agents +1
  44. MLingualFC: Evaluating Jailbreak Vulnerabilities in Multilingual Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  45. SAW: Stage-Aware Dynamic Weighting for Multi-Objective Reinforcement Learning in Large Language ModelsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  46. Adversarial Robustness of Activation Steering in Large Language ModelsMechanistic interpretability → Steering and probing for LLM safety
  47. Struct-Searcher: Agentic Structural Thinking Advances Multimodal Deep Information SeekingLLM reasoning → Knowledge- and tool-augmented reasoning +1
  48. TRACER: Token ReAssignment for Concept ERasure in Generative RecommendationLLM safety and security → Membership inference attacks
  49. What Makes Video World Model Latents Action-Relevant: Prediction over ReconstructionWorld models → Video-generation world models and simulators
  50. How reliable are LLMs when it comes to playing dice?LLM reasoning → Test-time compute and efficient thinking
  51. Agentopia: Long-Term Life Simulation and Learning in Agent SocietiesLLM agents and tool use → Social simulation and multi-agent debate
  52. MemDreamer: Decoupling Perception and Reasoning for Long Video Understanding via Hierarchical Graph Memory and Agentic Retrieval MechanismLLM reasoning → Multimodal reasoning +2
  53. Affordance-Based Hierarchical Reinforcement Learning for Quadruped PedipulationDeep reinforcement learning methods → RL for robot locomotion and manipulation
  54. Unsupervised Continual Clustering via Forward-Backward Knowledge DistillationKnowledge distillation → Distillation for continual learning
  55. Whisper Hallucination Detection and Mitigation via Hidden Representation Steering and Sparse AutoEncodersMechanistic interpretability → Hallucination detection from model internals
  56. Planning-aligned Token Compression for Long-Context Autonomous DrivingEnd-to-end autonomous driving → Reasoning VLA and VLM driving policies +1
  57. Act As a Real Researcher: A Suite of Benchmarks Evaluating Frontier LLMs and Agentic Harnesses in Research LifecycleLLM agents and tool use → Web, search, and research agents
  58. TEVI: Text-Conditioned Editing of Visual Representations via Sparse Autoencoders for Improved Vision-Language AlignmentMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  59. Agentic Very Much! Adoption of Coding Agent in New GitHub ProjectsLLM agents and tool use → Software engineering coding agents
  60. Skill-3D: Evolving Scene-Aware Skills for Agentic 3D Spatial ReasoningLLM reasoning → Spatial and embodied reasoning +1
  61. Watch, Remember, Reason: Human-View Video Understanding with MLLMsLLM reasoning → Multimodal reasoning +1
  62. Sparsely gated tiny linear expertsMixture-of-experts → MoE large language models
  63. Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent SkillsLLM agents and tool use → Software engineering coding agents +1
  64. A Comprehensive Anatomy of Human and DeepSeek-R1 LLM Mathematical ReasoningLLM reasoning → Mathematical reasoning
  65. Reversible Foundations: Training a 120B Sparse MoE through State-Preserving ScalingMixture-of-experts → MoE large language models
  66. M3Exam: Benchmarking Multimodal Memory for Realistic User-Agent InteractionsLLM agents and tool use → Agent memory systems
  67. Generative Modeling of Discrete Latent Structures via Dynamic Policy GradientsDeep reinforcement learning methods → RL with diffusion and flow models
  68. Simulation-Driven Imitation Learning for Biosignals-Free Shared-Autonomy Prosthetic GraspingOffline RL and imitation learning from data → Robot manipulation imitation learning
  69. RhinoVLA Technical ReportVision-language-action models → Generalist VLA models and benchmarks
  70. Do Coding Agents Deceive Us? Detecting and Preventing Cheating via Capped Evaluation with Randomized TestsLLM agents and tool use → Software engineering coding agents
  71. Self-evolving LLM agents with in-distribution OptimizationLLM agents and tool use → Reinforcement learning for LLM agents +1
  72. Dash2Sim: Closed-Loop Driving Simulation from in-the-wild Dashcam VideosEnd-to-end autonomous driving → Generative simulation for driving
  73. Defending Jailbreak Attacks on Large Language Models via Manifold Trajectory KineticsLLM safety and security → Jailbreaking
  74. AnchorWorld: Embodied Egocentric World Simulation with View-based Evolution CustomizationWorld models → Video-generation world models and simulators
  75. Certifiable Semantic Agreement Among LLM Agents: What the Admissibility Instrument DecidesLLM agents and tool use → Agent threats, guardrails and governance
  76. QBugLM: An Agentic Benchmarking Framework for LLM-based Quantum Software DebuggingLLM agents and tool use → Medical and scientific domain agents
  77. SV-Detect: AI-generated Text Detection with Steering VectorsMechanistic interpretability → Activation steering methods
  78. DuMate-DeepResearch: An Auditable Multi-Agent System with Recursive Search and Rubric-Grounded ReasoningLLM agents and tool use → Web, search, and research agents
  79. SWE-Explore: Benchmarking How Coding Agents Explore RepositoriesLLM agents and tool use → Software engineering coding agents
  80. Where Flow Matching Leaks: Characterising Membership Signals Along the Interpolation PathDiffusion models → Flow matching, time series and science
  81. Clairvoyant: Predictive Shortest-Job-First Admission for Serial LLM InferenceEfficient LLM inference and serving → Serving systems and request scheduling
  82. When Large Language Models Fail in Healthcare: Evaluating Sensitivity to Prompt VariationsLLM safety and security → Safety alignment, refusal and guardrails
  83. FLOWREADER: Min-Cost Flow Optimization for Multi-Modal Long Document Q&ARetrieval-augmented generation → Multimodal RAG
  84. Robotic Policy Adaptation via Weight-Space Meta-LearningVision-language-action models → Reinforcement learning and post-training
  85. Towards Tight Bounds for Streaming AttentionEfficient LLM inference and serving → KV cache optimization
  86. Shield-Loco: Shielding Locomotion Policies with Predictive Safety FilteringDeep reinforcement learning methods → Safe and constrained RL
  87. From Correctness to Utility: Gain-Based Prefix Evaluation for LLM ReasoningLLM reasoning → Reinforcement learning for reasoning +1
  88. Seeing Without Exposing: Adaptive Privacy Control for Open-World, Context-Hungry MLLMsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  89. Textual Supervision Enhances Geospatial Representations in Vision-Language ModelsLLM reasoning → Spatial and embodied reasoning +1
  90. When Recovery Matters: The Blind Spot of Surrogate Privacy in MLLM EditingMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  91. Test-Time Trajectory Optimization for Autonomous DrivingEnd-to-end autonomous driving → Imitation-learning end-to-end planners
  92. Think Fast: Estimating No-CoT Task-Completion Time Horizons of Frontier AI ModelsLLM reasoning → Prompting and chain-of-thought reasoning
  93. Consistent-Inversion: Reverse Consistency Guidance for Structure-Preserving Visual EditingDiffusion models → Image generation, text-to-image and editing
  94. REMEDI: A Benchmark for Retention and Unlearning Evaluation in Multi-label Clinical Disease InferenceLLM safety and security → Machine unlearning
  95. MalSkillBench: A Runtime-Verified Benchmark of Malicious Agent SkillsLLM agents and tool use → Agent threats, guardrails and governance
  96. Learning Explicit Behavioral Models with Adaptive Questions and World-Model ProbesWorld models → World models for language agents
  97. The Three-Ring Architecture: Governing Agents in the Era of On-Platform OrganisationsLLM agents and tool use → Agent threats, guardrails and governance
  98. DyCon: Dynamic Reasoning Control via Evolving Difficulty ModelingLLM reasoning → Test-time compute and efficient thinking
  99. Coarse-to-Control: Action-Token Planning for Vision-Language-Action ModelsVision-language-action models → Reasoning and chain-of-thought in VLA
  100. LARA: Latent Action Representation Alignment for Vision-Language-Action ModelsVision-language-action models → Human-video and latent-action pretraining
All 436
  1. Dreaming when Necessary: Advancing World Action Models with Adaptive Multi-Modal ReasoningWorld models → Embodied and robot world models +1
  2. Predictive Style Matching: Natural and Robust Humanoid LocomotionDeep reinforcement learning methods → RL for robot locomotion and manipulation
  3. On the Geometry of On-Policy DistillationLLM reasoning → Prompting and chain-of-thought reasoning +1
  4. dots.tts Technical ReportDiffusion models → Audio, speech and music
  5. AsyncPatch Diffusion: spatially-flexible image generationDiffusion models → Diffusion foundations and sampling
  6. SlimSearcher: Training Efficiency-Aware Web Agents via Adaptive Reward GatingLLM agents and tool use → Web, search, and research agents
  7. mmPISA-bench: Do LLMs Reason Equally Well Across 43 Languages?LLM reasoning → Reasoning benchmarks and evaluation
  8. TRACE: Trajectory Reasoning through Adaptive Cross-Step Evidence Aggregation for LLM AgentsLLM reasoning → Reasoning for agents, planning and code +1
  9. TrioPose: Native Triple-Stream Diffusion Transformers for Pose-Guided Text-to-Image GenerationDiffusion models → Image generation, text-to-image and editing
  10. Beyond Rubrics: Exploration-Guided Evaluation Skills for Reward ModelingLLM alignment / RLHF / preference optimisation → Reward hacking and misspecification
  11. STREAM: Stochastic Riemannian Flow Matching with Anisotropic Decoder for Digital Histopathology Image GenerationDiffusion models → Medical imaging and segmentation
  12. StainFlow: Entity-Stain Tracking and Evidence Linking for Process Rewards in GUI AgentsLLM agents and tool use → GUI and mobile agents +2
  13. MADE: Beyond Scoring via a Multilingual Agentic Diagnosing Engine for Fine-Grained Evaluation InsightsLLM agents and tool use → Medical and scientific domain agents
  14. The Sim-to-Real Gap of Foundation Model Agents: A Unified MDP PerspectiveLLM agents and tool use → General LLM agent frameworks and benchmarks
  15. Task Editing for Generalizable 3D Visuomotor Policy LearningLLM reasoning → Spatial and embodied reasoning
  16. A Geometric View for Understanding Concept Learning and Neuron Interpretation in Sparse AutoencodersMechanistic interpretability → Sparse autoencoder training and evaluation
  17. RASFT: Rollout-Adaptive Supervised Fine-Tuning for ReasoningLLM reasoning → Reinforcement learning for reasoning
  18. DataEvolver: Automatic Data Preparation for Large Language Models through Multi-Level Self-EvolvingSynthetic data and self-improvement for LLMs → Code and instruction data synthesis
  19. Teaching the Way, Not the Answer: Privileged Tutoring Distillation for Multimodal Policy OptimizationLLM reasoning → Multimodal reasoning +1
  20. Exploring Agentic Tool-Calling Decisions via Uncertainty-Aligned Reinforcement LearningLLM agents and tool use → Reinforcement learning for LLM agents
  21. Modeling U.S. Attitudes Toward China via an Event-Steered Multi-Agent SimulatorLLM agents and tool use → Social simulation and multi-agent debate
  22. GenPO++: Generative Policy Optimization with Jacobian-free Likelihood RatiosDeep reinforcement learning methods → RL with diffusion and flow models
  23. FinEvolveBench: A Benchmark for Self-Evolving Agents on Low-Repetition Tasks with Implicit RewardsLLM agents and tool use → Financial trading and forecasting agents
  24. Auditing Training Data in Domain-adapted LLMs: LoRA-MINTLLM safety and security → Membership inference attacks
  25. SS-TPT: Stability and Suitability-Guided Test-Time Prompt Tuning for Adversarially Robust Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  26. Quantum-Inspired Trace-Augmented Evidence Selection for Reasoning over Structured Hypothesis SpacesLLM reasoning → Prompting and chain-of-thought reasoning
  27. When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial RobustnessMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  28. Personality Anchoring for Social Simulation: Linking Personality, Social Behavior, and Interaction Success with LLM AgentsLLM agents and tool use → Social simulation and multi-agent debate
  29. From Sampled Outcomes to Capability Distributions: Rethinking Supervision for LLM RoutingLLM reasoning → Test-time compute and efficient thinking
  30. Declarative Skills for AI Agents in Knowledge-Grounded Tool-Use WorkflowsLLM agents and tool use → General LLM agent frameworks and benchmarks
  31. The Fine-Tuning Trap: Evaluating Negative Transfer and the Role of PEFT in Sub-1B Mathematical ReasoningLLM reasoning → Mathematical reasoning
  32. ThinkBooster: A Unified Framework for Seamless Test-Time Scaling of LLM ReasoningLLM reasoning → Test-time compute and efficient thinking
  33. ActionMap: Robot Policy Learning via Voxel Action HeatmapVision-language-action models → Efficient VLA inference and adaptation
  34. Workflow-to-Skill: Skill Creation via Routing-Workflow-Semantics-Attachments DecompositionLLM agents and tool use → Agent skill learning and evolution
  35. Stream3D-VLM: Online 3D Spatial Understanding with Incremental Geometry PriorsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  36. Diagnosing Visual Ignorance in Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  37. ARAPDiffusion: ARAP Regularization for Diffusion-Based Deformable Shape Space LearningDiffusion models → 3D, point cloud and scene generation
  38. FreeAnimate: Training-Free Human Image Animation with Preview-Guided DenoisingDiffusion models → Video generation
  39. Towards Retrieving Interaction Spaces for Agentic SearchLLM agents and tool use → Web, search, and research agents
  40. Unified Safe In-context Image Generation in Multimodal Diffusion Transformers via Restricting Unsafe Information FlowsDiffusion models → Robustness, privacy and adversarial aspects
  41. EgoPressDiff: Multimodal Video Diffusion for Egocentric UV-Domain Hand-Pressure EstimationDiffusion models → Diffusion and flow policies for robotics
  42. Evidence-Based Intelligent Diagnostic and Therapeutic Visualization System with Large Language Models: Multi-Turn Interaction and Multimodal Treatment Plan GenerationLLM reasoning → Clinical and biomedical applications
  43. LRMIL: Efficient Low-Resolution Multiple Instance Learning via High-Resolution Knowledge Distillation for Whole Slide Image ClassificationKnowledge distillation → Distillation for medical imaging
  44. Interpreting Brain Responses to Language with Sparse Features from Language ModelsMechanistic interpretability → SAE features and their applications
  45. MotionEnhancer: Leveraging Video Diffusion for Motion-Enhanced Vision-Language ModelsMultimodal LLMs / vision-language models → Video understanding with MLLMs +1
  46. CRAFT: A Unified Counterfactual Reasoning Framework for Tabular Question Answering and Fact VerificationLLM reasoning → Knowledge- and tool-augmented reasoning
  47. Characterize Then Distill: Mechanistic Reasoning in Large Output SpacesLLM reasoning → Prompting and chain-of-thought reasoning
  48. LLM Agent-Assisted Reverse Engineering with Quantitative Readability MetricsLLM agents and tool use → Software engineering coding agents
  49. SEAM: Shortcut-Aware Real-Time Detection of Scripted vs. Spontaneous Speech for Interview GuardrailsLLM safety and security → Safety alignment, refusal and guardrails
  50. Think Like a Pilot: Fine-Grained Long-Horizon UAV NavigationLLM reasoning → Spatial and embodied reasoning
  51. Translate-R1: Cost-Aware Translation Tool Use via Reinforcement LearningLLM agents and tool use → General LLM agent frameworks and benchmarks
  52. STRIPS-WM: Learning Grounded Propositional STRIPS-style World Models from ImagesWorld models → Embodied and robot world models
  53. AdaGRPO: A Capability-Aware Adaptive Enhancement for Flow-based GRPOLLM reasoning → Reinforcement learning for reasoning
  54. Progress-SQL: Improving Reinforcement Learning for Text-to-SQL via Progressive RewardsDeep reinforcement learning methods → RL training of language and agent models
  55. PandaAI: A Practical Agent CQ2 for Neuro-symbolic Data Analysis And Integrated Decision-Making in Quantitative FinanceLLM agents and tool use → Financial trading and forecasting agents
  56. SCALE: Scalable Cross-Attention Learning with Extrapolation for Agentic Workflow SchedulingLLM agents and tool use → General LLM agent frameworks and benchmarks
  57. Lane Change Trajectory Planning for Personalized Driving Comfort and Mobility EfficiencyEnd-to-end autonomous driving → Imitation-learning end-to-end planners
  58. Exploring Reinforcement Learning for Fluid Transitions Between Clinical Mental Healthcare and Everyday Wellness SupportDeep reinforcement learning methods → RL for clinical treatment and surgery
  59. Korean Culture into LLM Alignment: Toward Cultural CoherenceLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  60. TA-RAG: Tone-Aware Retrieval-Augmented Generation for Peer-Support Health CommunicationRetrieval-augmented generation → Medical and biomedical RAG
  61. AdMem: Advanced Memory for Task-solving AgentsLLM agents and tool use → Agent memory systems
  62. Trajectools Demo: Towards No-Code Solutions for Movement Data Analytics
  63. RENDER: Controlling Reader-Facing Evidence in LLM Memory Evaluation
  64. Automatic bioinformatic software named entity recognition from literature
  65. Nine Emotion Centroids: A Label-Free Valence Axis That Transfers Across Four Modalities
  66. A Metamorphic Artificial Age Score Decision-Support Prototype for Flight-Log-Based Drone Propeller Health Monitoring
  67. SuTRA : Structurally-Unified Tokenization with Root Awareness
  68. Position: Current Model Cards Are Insufficient for Downstream Governance of Open-Weight Foundation Models
  69. Position: Want Better ML Reviews? Stop Asking Nicely and Start Incentivizing with a Credit System
  70. Multimodal Drivers' Emotion Recognition and Safety-Oriented Intervention for Intelligent Transportation Systems
  71. Measuring and Improving Behavioral Consistency in Large Language Models through Fact-Heuristic-Emotion State Enforcement
  72. Temporal Context Reinstatement Drives Episodic-Like Order Memory in Long-Context Language Models
  73. Too much evidence, too little time: From text to actionable recommendations through multi-objective evidence reasoning
  74. AdaRoPE: Not All Attention Heads Should Rotate and Scale Equally
  75. The Hidden Water Geography of U.S. Hyperscale Data Centers in the AI Era
  76. The Rising Unsustainability of AI Graphics Cards Production
  77. MediEncoder: Nonlinear Representation Learning for High-Dimensional Causal Mediation Analysis
  78. Bridging Multi-Valued Heuristics and Dimensionality Reduction in Multi-Objective Search
  79. A physical adaptive material motor unit neural network: a hygromorph composite material machine
  80. Pixel-TTS: Image based Text Rendering for Robust Text-to-Speech
  81. Automated 3D Kinematic Monitoring for Circadian Activity and Anomaly Detection in Juvenile Fish
  82. MMLongEmbed: Benchmarking Multimodal Embedding Models in Long-Context Scenarios
  83. Position: Hippocampal Explicit Memory Is the Cornerstone for AGI
  84. The Whale That Outswam Evolution: Swarm Intelligence Maximises Memory in Connectome Reservoirs
  85. TRAPS: Treatment-Assignment Prediction via Pathway-informed Stratification
  86. Temporal Coverage over Density: Parsimonious Training-Set Design for ML Climate Downscaling
  87. Pander Score: A Continuous Measure of Sycophancy as Epistemic Deference
  88. Beyond the Thin-Layer Limit: Differentiable Volumetric Training for Visible-Range Diffractive Neural Networks
  89. Beyond Individual Personas: Aligning Synthetic Dialogue to Population-Level Behavior Distributions
  90. C3VD-DEFCOL: A Deformable Colonoscopy Dataset with Time-Resolved 3D Ground Truth and Realistic Appearance
  91. Partially Performative Prediction
  92. The Cross-Architecture Substrate: A Domain-Transcendent, Calibration-Surviving Geometric Invariant of Modern Vision Encoders
  93. Breaking the Bubble: Asynchronous Pipeline Parallel Training with Bounded Weight Inconsistency
  94. Whose Norms? Disentangling Cultural and Personal Alignment in Large Language Models
  95. Safety is Contextual, LLM-Judges Are Not: Navigating the Rigid Priors of Evaluators
  96. Overcoming the Regulatory Bottleneck via Agent-to-Agent Protocols: A Nuclear Case Study
  97. Instrumented data for causal scientific machine learning
  98. Model Multiplicity for Adversarial Detection in Small Language Model Training on Edge Devices
  99. Beyond English benchmarks: clinical llm evaluation in Brazilian Portuguese
  100. Large-scale empirical tuning and comparison of default optimizers for variational inference
  101. Does Persona Make LLMs K-pop Fans? A Pilot Study of LLM-Based Online Concert Audience Agents
  102. Agentic multi-fidelity learning of quasiparticle and excitonic properties
  103. Cherry-pick Override: LLM Judges Under-use the Non-Directional Verdicts Their Contract Authorizes
  104. Jas: AI-Paired Engineering as a Revival of N-Version Programming
  105. The ACUTE Protocol: Operationalizing Language Model Activations for Better Calibration, Utility, and Trust
  106. Joint Structural Pruning and Mixed-Precision Quantization for LLM Compression
  107. MinNav: Minimalist Navigation Using Optical Flow For Active Tiny Aerial Robots
  108. Scaling Participation in Modular AI Systems
  109. SLMJury: Can Small Language Models Judge as Well as Large Ones?
  110. Memetic Capture: A Pluralistic Policy Framework for Governing AI-Driven Cultural Disempowerment
  111. Reconstructing and forecasting disease trajectories of patients with Alzheimer's disease using routine data in resource-constrained settings
  112. MOLOT System Card: Malicious Operational Logic Observation Transformer
  113. Frequency-Scale Saliency for Spectral Descriptor Analysis in 3D Shape Retrieval
  114. A Framework for Evaluating and Benchmarking Concept Drift Detection Methods
  115. Non-Archimedean Polydisc Spaces and Applications to Optimisation
  116. Land cover and flood type govern the detection limits of satellite-based flood mapping across diverse global flood events
  117. Unlocking Latent Value: Taxonomy-Guided Recovery of High-Performing Data from Low-Tier Web Corpora
  118. DALE-CT: Depth-Aware 2D Slice Encoders Learn an Anatomical World Model of Chest CT
  119. Beyond Point Estimates: Benchmarking Uncertainty Quantification Methods on the AION-1 Astronomical Foundation Model
  120. Contrast encodes inductive bias: separating slow noise from dynamics in predictive representation learning
  121. Quantum-Enhanced Similarity Measures for Polarimetric Materials Classification
  122. scCBGM: Interpretable Single-Cell Counterfactual Editing
  123. DroneDAR: Long-Range Drone Distance Estimation Using Monocular Vision and Bounding-Box Features
  124. ReadingMachine: A Computational Methodology for Structured Corpus Reading and Large-Scale Synthesis
  125. Characterizing the Discrete Geometry of ReLU Networks
  126. Benchmarking Quantum Algorithmic Resilience for CVaR Portfolio Optimization: The Expressibility-Coherence Trade-off
  127. Cutting LLM Evaluation Costs with SySRs: A Bandit Algorithm that Provably Exploits Model Similarity
  128. GNSS-FM: A Self-Supervised Foundation Model for Daily GNSS Displacement Time Series
  129. A Geometry-Aware Triplane Field Network for Vehicle Aerodynamic Prediction
  130. Some hypotheses on how chatbots work in problem-solution-driven conversations: Large Language Models as confirmation of the Innovation Illusion
  131. Automatic Extraction of Structured Information from Brain MRI Reports Using an Open-Weight Large Language Model
  132. Multi-planar 2D-U-Net Segmentation of 3D-CT Abdominal Organs augmented by Spatial Occurrence Maps
  133. SHIELD-IDS: Structurally Heterogeneous Ensemble with Integrated Layered Defense for Intrusion Detection Systems
  134. Beyond Accuracy: Interpreting Topic Representation in Suicide Ideation Detection Models
  135. Attention at the Theoretical Minimum: A Mathematics of Arrays Framework for Memory-Optimal Transformer Kernels
  136. Cross-View Urban Traffic Dataset: Drone-Supervised Ground Truth for Monocular Bird's-Eye View Localization
  137. Decoding Naturalistic Emotion Dynamics from the Brain: An LLM-Enhanced Regression Framework
  138. FunctionEvolve: Structure-Guided Symbolic Regression with LLMs
  139. How Much Dense Attention is Necessary? Oracle-Guided Sparse Prefill for Full/GQA Layers in Hybrid Long-Context Models
  140. EvoCSFL: Surrogate-Assisted Evolutionary Client Selection for Efficient and Robust Federated Learning
  141. EssentialGIN: a new approach for gene essentiality prediction based on graph isomorphism neural networks
  142. Pharmacogenomic Knowledge Graph Augmentation for Graph Neural Network-Based Drug-Drug Interaction Prediction
  143. TianJi-Environ: An Autonomous AI Scientist for Atmospheric Environmental Research
  144. DSFNet: Learning Dual-Domain Spectral Operators for Multi-Modality Spatio-Temporal Forecasting in Urban Transportation Systems
  145. Vessel Traffic Flow Prediction on Sparse Data via Spatio-Temporal Graph Neural Networks with a Learnable Tweedie Head
  146. Transfer learning for causal forest
  147. BCG-FM: A Foundation Model for Ambient Cardiac Health Sensing
  148. HARP: Efficient Data Selection for Finetuning Large Language Models
  149. Knowledge-Inclusive Adaptive Physics-Informed Neural Network for Microbial Interaction Modelling
  150. Test-Time Adaptive Composition for Machine Learning as a Service (MLaaS) in IoT Environments
  151. Semantic Cache Distillation: Efficient State Transfer via Reuse and Selective Patching
  152. SWE-Marathon: Can Agents Autonomously Complete Ultra-Long-Horizon Software Work?
  153. UniSHARP: Universal Sharp Monocular View Synthesis
  154. Streaming Video Generation with Streaming Force Control
  155. Differences in Detection: Explainability Where it Matters
  156. Your UnEmbedding Matrix is Secretly a Feature Lens for Text Embeddings
  157. Sparse Subspace-to-Expert Sharing for Task-Agnostic Continual Learning
  158. Implicit Data Synthesis for Contrastive Unsupervised Data Augmentation
  159. Accelerated Decentralized Stochastic Gradient Descent for Strongly Convex Optimization
  160. Second-Order Path Kernel Interpolation Formulas in Machine Learning
  161. Bradley-Terry Rankings for Recommender Systems Across Dataset Taxonomies
  162. Twelve quick tips for designing AI-driven HPC workflows
  163. How AI Agents Reshape Knowledge Work: Autonomy, Efficiency, and Scope
  164. CoMetaPNS: Continually Meta-learning Personalized Neural Surrogates for Cardiac Electrophysiology Simulations
  165. Network Recovery from Cascade Data: A Debiased Jacobian-Based Machine Learning Approach
  166. Drifting Models for Surrogate Flow Modeling
  167. Supervision versus Demonstration-Based In-Context Learning for Multiword Expression Classification
  168. Graph Neural Network leveraging Higher-order Class Label Connectivity for Heterophilous Graphs
  169. Amortized Neural Optimization for Pre-Layout Signal Integrity Design Space Exploration using Differentiable Surrogates
  170. Time series Foundation Models based on Physics-Informed Synthetic Histories for Cold-Start Photovoltaic Forecasting
  171. PaperFlow: Profiling, Recommending, and Adapting Across Daily Paper Streams
  172. Sycophantic Praise: Evaluating Excessive Praise in Language Models
  173. Re-imagining ISO 26262 in the Age of Autonomous Vehicles: Enhancing Controllability through Transferability and Predictability
  174. The Lipreading Gap: Do VSR Models Perceive Visual Speech Like Human Lipreaders?
  175. OpenGlass: Ultra-Low-Power On-Device AI Eyewear with Event-based Vision
  176. Discovering Multiscale Deep Formulas in Complex Systems via Neural-Guided Lambda Calculus
  177. The Masked Advantage: Uncovering Local-Language Access to Cultural Knowledge in LLMs
  178. DisPOSE: Projected Polystochastic Diffusion for Self-Supervised Multi-View 3D Human Pose Estimation
  179. Video-Based Prediction of In-Flight Particle Characteristics in Atmospheric Plasma Spraying
  180. The Proxy Benders Decomposition
  181. RealDocBench: A Benchmark for Field-Level QA and Layout Understanding on Real-World Regulated Documents
  182. Are Good Generators Good Decision-Makers? Policy Learning for General Interventions via Retargeted Counterfactual Generation
  183. Mind the Gap: Disentangling Performance Bottlenecks in Video Instance Segmentation
  184. Online Pandora's Box for Contextual LLM Cascading
  185. Making the Most of Limited Data: Score-Aware Training for Text-to-Music Generation
  186. Unified Geometry-Guided ML-FTLE for Tracking Transient Chaos from Scalar Time Series
  187. Covariance Shrinkage via Stochastic Interpolation
  188. Impact of Synthetic Lesional MR Images in Automated Focal Cortical Dysplasia Detection in Low-Data Scenarios
  189. Beyond Backscatter: InSAR coherence from detected SAR images
  190. Mitosis Detection in the Wild: Multi-Tumor and Context-Aware Generalization in the MIDOG 2025 Challenge
  191. A robust PPG foundation model using multimodal physiological supervision
  192. Breaking the Ice: Analyzing Cold Start Latency in vLLM
  193. DirectAudioEdit: Inversion-Free Text-Guided Audio Editing via Diffusion Prediction Contrast
  194. Spatial-Temporal Decoupled Adapter for Micro-gesture Online Recognition
  195. SleepExplain: Explainable Non-Rapid Eye Movement and Rapid Eye Movement Sleep Stage Classification from EEG Signal
  196. TabSwift: An Efficient Tabular Foundation Model with Row-Wise Attention
  197. LLM-Guided Evolution for Medical Decision Pipelines
  198. VeriDrive: Verifiable Counterfactual Supervision for Cost-Efficient Vision-Language Planning
  199. How Far Can Chord-Symbol Time-Series Adaptation Carry Genre Identity? Capabilities and Boundaries in Multi-Genre Chord-Symbol Modeling
  200. Varifold Moment Invariants for Sustainable and Explainable Contour Feature Extraction
  201. A Temporal Spatial Minimax Rate for Smoothly-Varying Distributions in Wasserstein Space
  202. CultureScore: Evaluating Cultural Faithfulness in Video Generation Models
  203. Acoustic Cue Alignment in Audio Language Models for Speech Emotion Recognition
  204. Off-Policy Evaluation with Strategic Agents via Local Disclosure
  205. Bootstrap Theory of Representational Emergence (TBER): Explanatory Insufficiency, Transition Regimes, and the Emergence of New Representational Levels
  206. Phun-Bench: Evaluating LLMs on Phonological Understanding in Chinese
  207. TargetSEC: Plug-and-Play In-the-Wild Speech Emotion Conversion via Arousal-Conditioned Latent Style Diffusion
  208. Trio: Learning Time-Series Forecasting with Temporal-Spatial-Sample Attention and Structural Causal Priors
  209. Closed-Form Spectral Regularization for Multi-Task Model Merging
  210. ExMesh: Explicit Mesh Reconstruction with Topology Adaptation
  211. Geometric-Aware Hypergraph Reasoning for Novel Class Discovery in Point Cloud Segmentation
  212. The Capacity of Information-Theoretic Secure Aggregation in Federated Learning
  213. CaliPPer: quantifying, predicting and improving AI model performance for binding prediction
  214. On the conditional equivalence of phase retrieval algorithms
  215. A Held-Out Transition-Pair Falsifier for Long-Horizon Non-Abelian State Tracking
  216. TOPSIS-RAD: Ranking According to Desires
  217. Reconstructing Multi-Decadal Forest Disturbances: A Spatio-Temporal Transformer Approach
  218. Theory of learning of high-dimensional controlled non-linear dynamical systems (I): models and methods
  219. AI Sovereignty: A Qualitative Model of Strategic Competition as AI Becomes an Instrument of National Power
  220. Beyond Waypoints: A Trajectory-Centric Waypointing Paradigm for Vision-Language Navigation
  221. KIT's Submission to Cross-Lingual Voice Cloning in IWSLT 2026
  222. Generative Molecular Morphing for Flexible-Size Design via Unbalanced Optimal Transport
  223. Does Appearance Help? A Systematic Study of Image-Based Re-Identification in Online 3D Multi-Pedestrian Tracking
  224. MMAE: A Massive Multitask Audio Editing Benchmark
  225. DEFINED: A Data-Efficient Computational Framework for Fine-Grained Creativity Assessment in Debate Scenarios
  226. DualGate-Net: A Prior-Gated Dual-Encoder Framework for Histopathology Cell Detection
  227. Adversarial Creation and Detection of AI-Generated Social Bot Content
  228. HKVM-RAG: Key-Value-Separated Hypergraph Evidence Organization for Multi-Hop RAG
  229. Principal Component Analysis for Multivariate Extremes
  230. An Abstract Architecture for Explainable Autonomy in Hazardous Environments
  231. Entropy as a Structural Prior: How a Log-Barrier on DiT Belief Space Drives Musical Diversity and Development
  232. Structure-Preserving Correction Learning for Sparse Bayesian Inference in Brain Source Imaging
  233. AdaTok: Self-Budgeting Image Tokenization with Quality-Preserving Dynamic Tokens
  234. Geometry of Semantic Space: Comparative Study of Discrete and Continuous Models
  235. RETROSPECT: RETROsynthesis via Sequential Prediction, and Chemically Transformed-ranking
  236. OPTIMUS-Prime: Minimal and Sufficient Concept Explanations for Deep Vision Models
  237. EvoGS: Constructing Continuous-Layered Gaussian Splatting with Evolution Tree for Scalable 3D Streaming
  238. UrduMMLU: A Massive Multitask Benchmark for Urdu Language Understanding
  239. TraRA: Trajectory-level Recognition Aggregation for Video Text Spotting in Urban Surveillance
  240. No-Harm Physics-Informed Inverse Learning with Residual-Calibrated Uncertainty
  241. Geodesics of Dynamic Graphs for Regime Change Detection
  242. From Privacy to Workflow Integrity: Communication-Graph Metadata in Autonomous Agent Interoperability
  243. Decision-Aware Evaluation of Physics-Informed Surrogates
  244. Explaining Unsupervised Disease Staging in Huntington's Disease: Insights into Model Representations and Clusters
  245. α-PFN: Fast Entropy Search via In-Context Learning
  246. Explicit Evidence Grounding via Structured Inline Citation Generation
  247. A machine-learning-assisted progressive digit-randomness screening framework for detecting non-random patterns in raw numerical research data
  248. Information-Theoretic Bounds for Sparse Covariance Estimation in the Vertical-Split Distributed Model
  249. Learning Perspectivist Social Meaning via Demographic-Conditioned Fusion Embeddings
  250. Beyond Linear and Overcomplete Regimes: A Mean-Field Analysis of Bottleneck Autoencoders
  251. Native3D: End-to-End 3D Scene Generation via Unified Mesh-Texture Modeling and Semantic Alignment
  252. OffQ: Taming Structured Outliers in LLM Quantization by Offsetting
  253. 3DMorph: Single-Image-Guided Local 3D Shape Editing and Morphing
  254. DIFFRACT: Neuralized Utility Maximization for Wireless Networks by Differentiable Programming
  255. Beyond Post-hoc Explanation: Toward Glassbox AI via Probabilistic Mediation
  256. Style or Content? Evaluating Style Classifiers with Controlled Content Overlap
  257. GP-Adapter: Gaussian Process CLIP-Adapter for Few-Shot Out-of-Distribution Detection
  258. SigmaScale: LLM Compression with SVD-based Low-Rank Decomposition and Learned Scaling Matrices
  259. MetaConfigurator: AI-Assisted RDF Authoring from JSON Data
  260. The discovery of the effects of women employment participation on the fertility of developing countries: A panel data approach
  261. Detecting Temporally Localized Manipulations in Authentic Video Streams
  262. Residual-Controlled Multiplier Learning for Stochastic Constrained Decision-Making
  263. An Adaptive Data cleaning Framework for Noisy Label Detection
  264. Bias in Filter Feature Selection Evaluation: A Meta-Analysis of Datasets, Baselines, and Experimental Design Choices
  265. Modeling semantic association in self-paced reading with language model embeddings
  266. Beyond Universality: The GCC-FER Dataset and Culture-Aware Adaptation for Dynamic Facial Expression Recognition
  267. Constructing VAE Latent Spaces with Prescribed Topology
  268. Meaning in Order, Order in Meaning: Semantic R-precision for Keyphrase Evaluation
  269. Front-to-Attractors: Modifying the Front-to-Front Heuristic in Bidirectional Search
  270. Hierarchical Forecast Reconciliation for Urban Rail Transit Demand Prediction under Operational Disruptions
  271. ForensicConcept: Transferable Forensic Concepts for AIGI Detection
  272. Hierarchical Semantic-Constrained Heterogeneous Graph for Audio-Visual Event Localization
  273. Never Seen Before: Benchmarking Genuine Zero-Shot Composed Image Retrieval with Consistent Video-Sourced Datasets
  274. CF-JEPA: Mask-free forward prediction with asymmetric encoder utilization for time-series representation learning
  275. Phonetic Error Analysis of Raw Waveform Acoustic Models
  276. GuideCAD: A Lightweight Multimodal Framework for 3D CAD Model Generation via Prefix Embedding
  277. An Integrated Roadside Sensing and Communication Framework for Vulnerable Road User Safety at Signalized Intersections
  278. Towards Unified Song Generation and Singing Voice Conversion with Accompaniment Co-Generation
  279. Principles of Concept Representation in Sentence Encoders
  280. Don't Pause: Streaming Video-Language Synchrony for Online Video Understanding
  281. Accelerating Reproducible Research in Synthetic EHR Generation
  282. Heterogeneous Effects of Green Finance on Urban Decarbonization: Evidence from 285 Cities in China
  283. Contrastive Training with LLM-generated Near-Misses for Robust Code-Switching Speech Recognition
  284. Accelerating Multi-Objective Bayesian Optimisation via Predictive-Gradient Catalysts
  285. DaX: Learning General Pathology Representations Across Scales
  286. CL-CLIP: CLIP-Based Continual Learning Framework with Cost-Volume Category Decoupling for Object Detection
  287. Accounting for Context: Shaping Moral Credences for Value Alignment
  288. From Vision to Text: A Compact Multimodal Approach for Robust, Cross-Domain Presentation Attack Detection on ID Cards
  289. OpenHalDet: A Unified Benchmark for Hallucination Detection across Diverse Generation Scenarios
  290. MVSegNet: A Lightweight Boundary-Aware Network for Fetal Lateral Ventricle Segmentation and Atrial Width Estimation in Prenatal Ultrasound
  291. Deep Single-Index Fr'echet Regression
  292. When is 3D Worth It? A Resource-Performance Frontier for CNNs and Transformers in Lung CT
  293. Didact: A Cross-Domain Capability Discovery System for Defence
  294. Uniform Stability and Generalization Error of GD and SGD on Fixed-Point Parameters
  295. SVHighlights: Towards Extremely Long Sport Video Highlight Detection
  296. DRIFT: From Robustness Gaps to Invariance Manifolds for AI-Generated Image Detection
  297. polyDAG: Polynomial Acyclicity Constraints for Efficient Continuous Causal Discovery in Visual Semantic Graphs
  298. SpectCount: Spectrotemporal Counting via Synthetic Signals Improves Large Audio Language Models
  299. EASE-TTT: Evidence-Aligned Selective Test-Time Training for Long-Context Question Answering
  300. Beyond Skeletons: Learning Animation Directly from Driving Videos with Same2X Training Strategy
  301. TALAN: Task-Aligned Latent Adaptation Networks for Targeted Post-Training of Large Language Models
  302. LUCID: Learning Unified Control for Image Deflaring and Exposure Mastery in Nighttime Photography
  303. Lighting-Aware Representation Learning under Controllable Lighting Variation
  304. Blockchain Infrastructure for Intelligent Cyber--Physical--Social Systems:Post-Quantum Security, Interoperability, and Trustworthy Data Economies in the Era of Embodied AI
  305. GRASP: Geometry-aware Residual Alignment for Scalable Pretraining Data Attribution
  306. Data-Constrained Language Model Pretraining: Improved Regularization and Scaling Laws
  307. GlucoFM-Bench: Benchmarking Time-Series Foundation Models for Blood Glucose Forecasting
  308. An Expanded Synthetic Conversation Dataset for Multi-Turn Smishing Detection
  309. A Cross-view Fusion Framework for Robust 6-DoF Grasp Pose Estimation
  310. Neuro-Symbolic Learning for Long-Horizon Task Planning Under Complex Logical Constraints
  311. Evidence-Grounded Ensemble Diagnosis of 802.11 Packet Captures: A Multi-Stage Pipeline with Deterministic Reliability Scoring
  312. Multi-FRuGaL: Multimodal Flexible Redundancy-aware Decomposed Gated Learning for Cancer Diagnosis and Prognosis
  313. Product units in gated recurrent units improve nuclear-mass prediction
  314. Are Large Language Models Suitable for Graph Computation? Progress and Prospects
  315. Modeling Nonlinear Feature Interactions with Product-Unit Residual Networks
  316. FS-DVS: A Frequency-Selective Dynamic Visual Sensing Paradigm for Enhancing Information Completeness
  317. Stability beyond Bounded Differences: Sharp Generalization Bounds under Finite Lp Moments
  318. The Geometry of Last-Layer Model Stealing
  319. CFRNet: Cycle-Consistent Fixed-Point Training for Real-Time Blind Face Restoration on Consumer Embedded NPUs
  320. Physics-Driven Semantic Scattering Structure Understanding of Aircraft Target in SAR Images
  321. The Dark Regulome: Disentangling Predictability from Regulation in Genomic Foundation Models
  322. Hearing the Unspoken: Language Model Priors for Acoustic Adversarial Attacks
  323. Learning Fair Demand Models
  324. Architecture Shapes Transfer Specificity in Implicit Neural Representations
  325. VideoSEG-O3: A Multi-turn Reinforcement Learning Framework for Reasoning Video Object Segmentation
  326. Terastal: Layer-Variant-based Scheduling for Real-Time Multi-DNN Workloads on Heterogeneous Accelerators
  327. AMD-FCG: An Enhanced Function Call Graph Dataset with Integrated Topological Features for Malware Detection and Classification
  328. The Effect of Training Task Diversity on In-Context Learning through the Lens of Low-Dimensional Subspaces
  329. Breaking the Lock-in: Diversifying Text-to-Image Generation via Representation Modulation
  330. Quantifying Media Representation Dynamics Across 25 Years of News Reporting on Policing-related Deaths
  331. Interpreting Learning Under Competing Models: Joint and Stepwise Approaches for Dynamic Cognitive Diagnosis
  332. Learning All-Terrain Locomotion for a Planetary Rover with Actively Articulated Suspension
  333. Explain Like I'm 5 or Whatever I Choose: Evaluating the Potential for Interactive Complexity in Language Model Responses
  334. Federated Foundation Models over Vehicular Networks
  335. Empirical Transfer Operators and Finite-Sample Change Detection for Noisy Expanding Interval Maps
  336. What Your Posts Reveal: A Benchmark and Agentic Framework for User-Level Privacy Leakage on Social Media