mlsanityData to 14 Oct 2026

Papers

New on arXiv

Mon 14 Sep 2026

490 papers

  1. Temporal-Attention Head Specialization During Video Diffusion TrainingDiffusion models → Video generation
  2. Long-Tail Adaptive Flow Matching with Explicit Conditional Consistency Guidance for Precise Multimodal Face SynthesisDiffusion models → Image generation, text-to-image and editing
  3. Authority-Preserving Evaluation of Medical Vision-Language AssistantsMultimodal LLMs / vision-language models → Medical vision-language models
  4. Validating, Not Sampling: Region-Level Robustness of Vision-Language and Vision-Language-Action ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning +1
  5. Interpreting and Steering LLM Agents for Social SimulationsLLM agents and tool use → Social simulation and multi-agent debate +1
  6. Reasoning with Image GenerationLLM reasoning → Multimodal reasoning +1
  7. Register Tokens for Bounded-State Reasoning in Diffusion Language ModelsLLM reasoning → Diffusion reasoning and test-time scaling +1
  8. Fast-Convergent Meta-RL via Gradient-Clustered BS Sampling for Edge CachingDeep reinforcement learning methods → RL for energy, networks and operations
  9. StalePO: Anchored Token-Level Preference Optimization using Legacy Post-Edits in Machine TranslationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  10. ManiSkillFormer: Demonstration-Free Compositional Manipulation via Geometric Contracts and Agentic Skill GraphLLM agents and tool use → Multimodal and embodied agents
  11. Cognitive Admission Control: Risk-Conditioned Assurance for Consequential Actions in Agentic Distributed SystemsLLM agents and tool use → Agent threats, guardrails and governance
  12. Agentic Search Spaces for Tabular Machine LearningLLM agents and tool use → General LLM agent frameworks and benchmarks
  13. BLINDSPOT: A Benchmark for Safety and Refusal Calibration in Long-Horizon Tool-Using AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  14. Assurance Envelopes for Autonomous Coding Agents: Minimum-Cost Evidence for Software ChangeLLM agents and tool use → Software engineering coding agents
  15. Policy Gradient over History-Dependent Policy Classes for LQR with Domain RandomizationDeep reinforcement learning methods → RL for games and combinatorial optimization
  16. AgentGuard: Learning Execution Guardrails from Anomalous Coding-Agent TrajectoriesLLM agents and tool use → Software engineering coding agents +1
  17. Cheap Talk Stabilizes Strategic Interaction in LLM AgentsLLM agents and tool use → Social simulation and multi-agent debate
  18. Spurious Tool Use: When RL Agents Learn the Wrong Reason to ActLLM reasoning → Reasoning for agents, planning and code +1
  19. Towards Surrogate Based Dequantization of Quantum Reinforcement LearningDeep reinforcement learning methods → Quantum reinforcement learning
  20. Efficient Reasoning Distillation: Small Video-Language Models via Synthetic CoT and Difficulty-Aware Fine-TuningLLM reasoning → Multimodal reasoning +1
  21. CADWorld: Computer-Use Benchmark for Long-Horizon Computer-Aided DesignLLM agents and tool use → Multimodal and embodied agents
  22. SceneBench: A Hierarchical Benchmark for Vision-Language Understanding of 3D ScenesLLM reasoning → Spatial and embodied reasoning +1
  23. Toward Governance-Aware Autonomous GIS: A Narrative Review of Ethical and Privacy Risks in LLM-Enabled GeoAILLM agents and tool use → Multimodal and embodied agents
  24. Test-Time Unlearning via Sparse AutoencoderLLM safety and security → Machine unlearning +1
  25. Where Should the KV Cache Live? Placement Policies Across GPU, CPU, and SSD for Long-Lived SessionsEfficient LLM inference and serving → KV cache optimization
  26. Calibrate, Then Route: A Measured Study of Learned Request Routing for Disaggregated LLM ServingEfficient LLM inference and serving → Serving systems and request scheduling
  27. Decoy Direction Optimization: A Post-Hoc Defense Against LLM AbliterationLLM safety and security → Safety alignment, refusal and guardrails
  28. Anatomy of Associative Recall in Fixed-State Recurrences: A Matched-State Decomposition, an Interference Wall, and a Curriculum That Breaks ItState-space sequence models (S4, Mamba) → Core SSM architectures for language
  29. LLM Inference in a Flash!Efficient LLM inference and serving → Serving systems and request scheduling
  30. Universal Defenses for Tool-Integrated LLM Agents Against Adversarial AttacksLLM agents and tool use → Agent threats, guardrails and governance +1
  31. Coaching Qwen3 Coder 30B to Think Like a CodeClash Arena AgentLLM reasoning → Reasoning for agents, planning and code +1
  32. RAG-CT: Mitigating Privacy Risks on Retrieval-Augmented Generation Systems via Scanning Prompt DistributionRetrieval-augmented generation → Privacy and security of RAG
  33. Distilling Foundation Models for Agentic What-If Reasoning:Cost, Latency, and Governance in a Hybrid LLM+SLM ArchitectureLLM agents and tool use → General LLM agent frameworks and benchmarks
  34. Corrupt Plans, Clean Traces: Evading Chain-of-Thought Monitoring with Plan InjectionLLM reasoning → Prompting and chain-of-thought reasoning
  35. ResSafe: Learning Safety Filtering with Residual Reinforcement Learning for HumanoidsDeep reinforcement learning methods → RL for robot locomotion and manipulation
  36. Bellman Policy OptimizationLLM reasoning → Reinforcement learning for reasoning
  37. Stellar Colosseum: A Many-Agent Harness for Long-Horizon Research in Mathematics and Theoretical Computer ScienceLLM agents and tool use → Educational agents and math problem solving
  38. The Router Within: Eliciting Native Skill Routing from a Frozen LLMLLM agents and tool use → Agent skill learning and evolution
  39. Adversarial Testing of Automated Program Repair Agents for Security VulnerabilitiesLLM agents and tool use → Agent threats, guardrails and governance
  40. Beyond Single-Axis Testing: Paired Evaluation of Compound Robustness in Vision-Language-Action PoliciesVision-language-action models → Failure recovery and robustness
  41. Vulnerability Localization Benchmark: Measuring Agentic Security Analysis at Repository ScaleLLM agents and tool use → Agent threats, guardrails and governance
  42. HypoEvolve: Genetic Algorithms Enable Multi-Agent LLMs to Discover Scientific HypothesesLLM agents and tool use → Web, search, and research agents
  43. Safe Meta-Reinforcement Learning via Information Space ReachabilityDeep reinforcement learning methods → Safe and constrained RL
  44. Authorization Architectures for Tool-Using AI AgentsLLM agents and tool use → Agent threats, guardrails and governance
  45. Discrete Beckmann Transport Models for One-Step Language Modeling and ReasoningLLM reasoning → Diffusion reasoning and test-time scaling +2
  46. The Model Proposes, the Code Disposes: A Pre-Registered Ablation of a Verifier-and-Acceptance Stage in an LLM-Orchestrated Offensive-Security AgentLLM agents and tool use → Agent threats, guardrails and governance
  47. Learning Multimodal One-step Flow Policy via Value-weighted Optimal TransportOffline RL and imitation learning from data → Diffusion and flow policies for offline RL +1
  48. Using Agentic AI for contextualized and multifaceted code review at EricssonLLM agents and tool use → Software engineering coding agents
  49. WLA3: World Latent Action Modeling for Semantics, Dynamics, and KinematicsVision-language-action models → Human-video and latent-action pretraining
  50. LynnReal-Omni: Native multi-modal Video Generation for Agentic Visual WorkflowsDiffusion models → Video generation +1
  51. LongAgent: History-Guided Agentic Search for Longitudinal Outcome PredictionLLM agents and tool use → Medical and scientific domain agents
  52. CiteGuard-RAG: A Validation-Centered AI System for Evidence-Grounded Question AnsweringRetrieval-augmented generation → RAG robustness and adaptive retrieval
  53. AlgoEvo: Self-Evolving Agentic Search for Automated Algorithm DiscoveryLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  54. Atria Dawn: The Dawn of Agentic SuperintelligenceLLM agents and tool use → General LLM agent frameworks and benchmarks
  55. VC-Attention: Value Smoothing and Softmax Casting for Low-bit AttentionDiffusion models → Video generation
  56. When Should a World Model Move? Loss-Conditioned State ExecutionWorld models → World models for language agents
  57. Navigating Sparse Evidence: Agentic Visual RAG via Explicit Context Selection and ConsolidationRetrieval-augmented generation → Multimodal RAG +1
  58. RAPID: A Real-Time Defense Against Unauthorized Model Distillation for Text-to-Image ServicesDiffusion models → Robustness, privacy and adversarial aspects
  59. When the World Lies: Backdoor Attacks on Latent World Models for Downstream ControlWorld models → World model security and GUI agents
  60. EvoOntology: A Self-Evolving Ontology Layer for Data AgentsLLM agents and tool use → Web, search, and research agents +1
  61. Assembling the CREW: A Collaborative Multi-agent Reinforcement Learning Framework for Automated Related Work GenerationLLM agents and tool use → General LLM agent frameworks and benchmarks
  62. Continuous Manifold-Decomposed Impedance Retargeting for Contact-Rich Imitation LearningOffline RL and imitation learning from data → Robot manipulation imitation learning
  63. Beyond Accuracy: Robustness, Cost, and Governance Trade-offs for Vision-Language Models in Templated Document ExtractionMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  64. Backward SDEs-based Diffusion for Physics-Constrained GenerationDiffusion models → Inverse problems and image restoration
  65. NoteVQA: Benchmarking VLMs on Real-Life Questions from Human CommunitiesMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  66. RESKILL: Explicit Failure Attribution and Structured Repair for Interactive Language AgentsLLM agents and tool use → Tool learning and function calling
  67. V-ICAL Bench: Evaluating Video In-Context Learning for Multimodal Agents in Interactive EnvironmentsLLM agents and tool use → Multimodal and embodied agents
  68. MambaMPD: A Mamba-Driven Segmentation Framework for Marine Pollution Detection from Remote Sensing ImageryState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  69. Don't Send What You Don't Need: Question-Guided Token Pruning as a Privacy Defense for Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  70. Circuit-MLLM: Topological Logic-Guided Latent-Space Visual Reasoning for Circuit Schematic UnderstandingLLM reasoning → Multimodal reasoning +2
  71. CiteShade: Citation Laundering in Multi-Source Retrieval-Augmented Generation and Its Counterfactual DefenseRetrieval-augmented generation → Privacy and security of RAG
  72. Predictive Likelihood Ratios for Language Model Watermark DetectionLLM safety and security → Watermarking generated content and models
  73. Empathy Is Steerable but Multi-Axial: Mechanism Geometry and Persona Effects in LLMsMechanistic interpretability → Activation steering methods
  74. MedDiME: Efficient Latent Diffusion with Adaptive Masking for Medical Counterfactual GenerationDiffusion models → Medical imaging and segmentation
  75. Principal-timestep Restricted Init via Sparse Matrix-decomposition in Flow-matchingDiffusion models → Flow matching, time series and science
  76. Human-Grounded Calibration for Long-Text Image-Text Congruence in Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  77. Flow-Matched Motion Priors: Online Optimal-Transport Rewards for Imitation LearningOffline RL and imitation learning from data → Imitation learning methods
  78. DeepSeek-V4-Flash on AMD gfx90a: Correctness Recovery and Inference Performance EngineeringMixture-of-experts → Efficient MoE training and inference systems
  79. IROH: Insightful Ranking Of Humor using Multi-Stage Hybrid Retrieval with Rationale-Distilled LLM Judges for JOKER 2026 Track Task 1 EnglishKnowledge distillation → Knowledge distillation for LLMs
  80. VideoScout: Learning Agentic Active Exploration with Adaptive Reasoning Pacing for Long Video UnderstandingLLM reasoning → Multimodal reasoning +2
  81. A Unified Vision-Language Model for PSMA PET/CT Report Generation, Visual Question Answering, and Lesion SegmentationMultimodal LLMs / vision-language models → Medical vision-language models
  82. The Magnitude Mirage: Rethinking Confidence for Reasoning-Intensive RetrievalRetrieval-augmented generation → RAG robustness and adaptive retrieval
  83. GRIN+: Towards Fast Yet Effective Machine Unlearning for Imbalanced Medical DataLLM safety and security → Machine unlearning
  84. DIDO: Distilling Interaction-Centric Dynamics into One-Step Denoising for World Action ModelsWorld models → Embodied and robot world models
  85. Specifying Reward Functions for RL Without Environment SamplingLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  86. Strong and Compact Policies for Submodular Markov Decision Processes via LP-Based Submodular OrienteeringDeep reinforcement learning methods → RL theory and sample complexity
  87. The Misery of Mechanistic Interpretability: A Formal PerspectiveMechanistic interpretability → Circuits and mechanistic analysis
  88. Automating Attack Graph Construction for Agentic Pentesting. Towards Neuro-Symbolic Vulnerability HuntingLLM reasoning → Reasoning for agents, planning and code +1
  89. Beyond Safe Answers: Segment-Aware Listwise Alignment for Reasoning Safety in Large Reasoning ModelsLLM reasoning → Reasoning for agents, planning and code +2
  90. Misleading the Planner through Deceptive Resumes: Registration-Time Injection in Centralized Multi-Agent SystemsLLM agents and tool use → Agent threats, guardrails and governance
  91. StereoPatch: Patch-Aligned RGB-Depth Fusion for Spatial Perception in Robot ManipulationOffline RL and imitation learning from data → Robot manipulation imitation learning
  92. Evaluating Losslessness in Speculative Decoding Under Finite-Precision InferenceEfficient LLM inference and serving → Speculative decoding
  93. The Troy Moment: How LLM Agents Adjudicate the Decision Point Under Impossible Tasks, Claimed Authority, and Peer InformationLLM agents and tool use → Software engineering coding agents
  94. BVB: Benchmarking Agentic Video Understanding via Programmatic Reconstruction in BlenderDiffusion models → Video generation +1
  95. HISPO: Hierarchical Importance-Sampling Policy Optimization with Entropy-Derived SegmentsLLM reasoning → Reinforcement learning for reasoning
  96. AnchorGUI: Asymmetric Memory for Dual-Scale Learning in GUI NavigationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  97. MarKey: Marginal Utility Guided Greedy Keyframe Selection for Long Video UnderstandingMultimodal LLMs / vision-language models → Video understanding with MLLMs
  98. Who Teaches Which Token? Verifier-Gated Multi-Expert On-Policy Distillation for Scientific ReasoningLLM reasoning → Prompting and chain-of-thought reasoning +1
  99. Dynamics-Informed Reinforcement Learning for Agile and Energy-Efficient Locomotion of a Monopedal Hopping QuadcopterDeep reinforcement learning methods → RL for robot locomotion and manipulation
  100. SkillLift: Learning Dense Rubrics from Sparse Oracles for Efficient Skill EvolutionLLM agents and tool use → Agent skill learning and evolution
All 490
  1. From Prediction to Decision: World-Model-Guided Action Selection for Continuous Pile ExcavationWorld models → Embodied and robot world models
  2. Translator vs. Challenger: Adversarial Agentic Learning for C-to-Rust TranslationLLM agents and tool use → General LLM agent frameworks and benchmarks
  3. RSIAgent: Autonomous Exploration for Recursive Self-improvement in New EnvironmentsSynthetic data and self-improvement for LLMs → Self-evolving LLM agents
  4. MAPS: Memory-Aware Predictive Scheduling Framework for Large Language Model ServingEfficient LLM inference and serving → Serving systems and request scheduling
  5. Diffusion Trajectory Modeling for Semantic CorrespondenceDiffusion models → Diffusion foundations and sampling
  6. Concept-Grounded Reasoning with Prompt-Driven Localization for Interpretable Structured Report GenerationLLM reasoning → Clinical and biomedical applications
  7. Planning in the Backbone: DiffAdapterVLA for Native Continuous Trajectory Generation with Driving VLMsMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
  8. Evaluation Metrics for Safe Reinforcement LearningDeep reinforcement learning methods → Safe and constrained RL
  9. The Universe of Universes: Benefit Yield Functions, Implosion Thresholds, and Infrastructure-Aware Optimization in Multi-LLM SystemsRetrieval-augmented generation → Agentic RAG, agents and memory
  10. Reducing the Output-Mode Gap in Speech Language Models via Joint-Output On-Policy DistillationKnowledge distillation → Speech and audio distillation
  11. When Agents Slow Down: Understanding LLM Agents' Test-Time Strategies via Elo-per-token AnalysisLLM reasoning → Reasoning for agents, planning and code +1
  12. Admissable: Training Reinforcement Learning Agents against Adversarial MissingnessDeep reinforcement learning methods → Adversarial robustness and RL in finance
  13. Reason What Matters: Retrieval-Grounded Reasoning for Universal Multimodal EmbeddingsLLM reasoning → Multimodal reasoning
  14. Why LLM Agents Collapse Without Oversight: The Enforcement Gap as the Mechanism Behind Emergence World FailuresLLM agents and tool use → Agent threats, guardrails and governance
  15. Impute-EM: Native Mixed-State Diffusion Models for Heterogeneous Data ImputationDiffusion models → Flow matching, time series and science
  16. Artificial entrepreneurial cognition: Locating and causally steering an opportunity recognition dial inside large language models (LLMs)Mechanistic interpretability → Knowledge and representations inside LLMs
  17. Empirical Evaluation of Open-Source Large Language Models for Retrieval-Augmented Generation in ESG DomainRetrieval-augmented generation → RAG pipeline design and evaluation
  18. ProtoGuide: Prototype-Driven Guidance for Class-Conditional Graph GenerationDiffusion models → Flow matching, time series and science
  19. CWM: Controllable White-Box Meta-Prompting for Adaptive Retrieval-Augmented Generation and Reasoning AbilityLLM reasoning → Knowledge- and tool-augmented reasoning +1
  20. Unsupervised Point Cloud Registration via Training-Time Semantic GuidanceKnowledge distillation → Detection and dense prediction distillation
  21. HarnessVLN: Unifying Training-Free Embodied Navigation through an Agent HarnessLLM agents and tool use → Multimodal and embodied agents
  22. Rethinking Correctness for Uncertainty Estimation in Clinical Prediction with Vision-Language ModelsLLM reasoning → Clinical and biomedical applications +1
  23. Temporal Self-Distillation: Faster Inference in Discrete Diffusion Language ModelsDiffusion models → Discrete and text diffusion +2
  24. STHMoE: Hypergraph-Enhanced Heterogeneous Dependency Coordination for LLM-Based Urban Traffic Data ForecastingMixture-of-experts → MoE for time series and graphs
  25. GRAVA: Grounded Reasoning-to-Action Representation and Learning for Autonomous DrivingVision-language-action models → VLA for autonomous driving +1
  26. CITECHOICE: A Causal Audit of How Document Presentation Redistributes Citation Credit in Agentic SearchLLM agents and tool use → Web, search, and research agents
  27. LieSpline-DP: Lie-Group B-Spline Diffusion Policy for Smooth Robot ManipulationDiffusion models → Diffusion and flow policies for robotics +1
  28. EMR: Self-Evolving Medical Multi-Agent System via Experience Mining and ReuseLLM agents and tool use → Medical and scientific domain agents +1
  29. T-LoopFormer: Token-Level Elastic-Depth Looped Transformers for Latent Reasoning with Dynamic RoutingEfficient LLM inference and serving → Efficient reasoning and agent inference
  30. Improving Mathematical Reasoning Capabilities in Large Language Models via Reasoning Process Error ClassificationLLM reasoning → Mathematical reasoning
  31. C2Nav: Compare Before You Commit for Zero-Shot Vision-and-Language NavigationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  32. HazardAuditor: From Executable Threats to Safer Computer-Use AgentsLLM agents and tool use → Agent threats, guardrails and governance
  33. AdaVSkip: Adaptive Visual Token Skipping Across Layers For Efficient MLLMs InferenceMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  34. MoME: Mixture-of-Memory Embeddings for Context-Aware Sparse LookupMixture-of-experts → MoE large language models
  35. Refinement-based Flow Policy OptimizationDiffusion models → Diffusion and flow policies for robotics +1
  36. DNF-SR: Dual-Input and Negative-Aware Feature Fine-Tuning for Real-World Image Super-ResolutionDiffusion models → Inverse problems and image restoration
  37. Legislating World-Model-Based Planning with Legal ReasoningWorld models → World models for language agents
  38. Translating the Translator: Decomposing the Cost of English-Forced Inter-Agent CommunicationLLM agents and tool use → General LLM agent frameworks and benchmarks
  39. Enabling Creative Exploration for Vibe Design AgentsLLM agents and tool use → GUI and mobile agents
  40. Branched Optimal Transport AmortizationDiffusion models → Flow matching, time series and science
  41. DA-DLM: Explicitly Modeling Token Dependencies in Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  42. Salesforce Koa: An Enterprise Language Model for Agentic Tool UseLLM reasoning → Reasoning for agents, planning and code +1
  43. What Does an LLM Learn from Reinforcement Learning? A Mechanistic Interpretability Perspective with Fixed-SAE TrackMechanistic interpretability → Steering and interpreting LLM reasoning
  44. BusMA: A Bus Communication Substrate for Multi-Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  45. Data Attribution via Sketched MetadifferentiationLLM safety and security → Machine unlearning
  46. The average-farmer illusion in language-model simulations of agricultural decisionsLLM agents and tool use → Social simulation and multi-agent debate
  47. Pick Your Poison: Learning to Select Poison Sets for Stronger LLM Backdoor AttacksLLM safety and security → Backdoor and data poisoning attacks
  48. Steering Generative Robot Policies with Lexicographic PreferencesDiffusion models → Diffusion and flow policies for robotics
  49. Overflip: Repetition-Induced Label Flips in Guardrail ModelsLLM safety and security → Safety alignment, refusal and guardrails
  50. Semantic-TVM: Structure-Preserving Trustworthy Virtual Memory for Memory-Augmented and Tool-Using AgentsLLM agents and tool use → Agent memory systems
  51. CoMem: Collective-Individual Memory Synergy for Evolutionary Multi-Agent SystemsLLM agents and tool use → Agent memory systems
  52. IMPACT-VLA: Interaction-aware Multimodal Propagation Attribution via Counterfactual Trajectories for Vision-Language-Action PoliciesVision-language-action models → Failure recovery and robustness
  53. Shallow Beliefs: Synthetic document finetuning does not inoculate against emergent misalignment from reward hackingLLM alignment / RLHF / preference optimisation → Reward hacking and misspecification
  54. Intelligence Under Time Constraints: Rethinking Test-Time ComputeLLM reasoning → Test-time compute and efficient thinking
  55. MTAC-IFBench: Benchmarking Instruction-Following in Multi-Turn Agentic CodingLLM agents and tool use → Software engineering coding agents
  56. ActGuard: Pre-execution Action Auditing against Indirect Prompt Injection in LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  57. MemRiskBench: Trace-Aware Risk-Preserving Evaluation for Long-Horizon LLM AgentsLLM agents and tool use → Software engineering coding agents
  58. PhysBrain 1.5: From Vision-Language Models to Physical Foundation ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  59. HiGFRL: Hierarchical Graph Fusion-Driven Reinforcement Learning for Dependency-Aware Task Scheduling in Heterogeneous CloudDeep reinforcement learning methods → RL for energy, networks and operations
  60. Cloud Workflow Scheduling Based on Graph Attention-Driven Hierarchical Reinforcement LearningDeep reinforcement learning methods → RL for energy, networks and operations
  61. Forty Shades of Blue: Quality-Diversity Alignment via Mode-Conditioned Reinforcement LearningLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  62. Real-World Reinforcement Learning with MPC Scaffolding for Dexterous ManipulationDeep reinforcement learning methods → RL for robot locomotion and manipulation
  63. MedVA: An End-to-End Neuro-Symbolic Agentic System for Medical Volume VisualizationLLM agents and tool use → Medical and scientific domain agents
  64. AgentKV: Phase-Aware KV Eviction for Agentic LLMsLLM agents and tool use → Software engineering coding agents +1
  65. Semantic Fibers and Cross-Gram Interference: A Calculus of Safety Drift in Overcomplete RepresentationsLLM safety and security → Safety alignment, refusal and guardrails
  66. One Example Is Enough to Pass Fairness Benchmarks: Rethinking Fairness Evaluation for Aligned LLMsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  67. ModularRSI: Modular and Generalizable Recursive Harness Self-ImprovementSynthetic data and self-improvement for LLMs → Self-evolving LLM agents
  68. RAIN: Region-Aware Inversion Network for Semantic Watermark ExtractionDiffusion models → Robustness, privacy and adversarial aspects
  69. Interpretable Memory Models for Spaced Repetition
  70. Accelerating Floating-Point Satisfiability Solving via Gradient Normalization
  71. Metric-Construction Coupling Inflates Measured Synthetic Dialect Recovery
  72. When the AI Leaves the Tailorshop: Measuring What an LLM Advisor Leaves Behind in Complex Problem Solving
  73. Beyond the Graph: An Adaptive Meta-Learner Fuses Explainability, Weather, and Dynamics for Robust Bus ETA Prediction
  74. Distributional sentiment modeling and anomaly detection for consumer complaint assessment
  75. Open-Qwen-Music: An Auditable Framework for LLM-Based Music Composition and Diffusion Rendering
  76. PalmLeaf-VQA: A Multi-Script Visual Question Answering Benchmark for Historical Palm-Leaf Manuscript Understanding Across Diverse Regions
  77. A literature-guided descriptor-based framework for filtering composition search spaces
  78. NeuralCert: certified computational discovery of extremal mathematical constructions
  79. G"odel's and Scott's Variants of the Ontological Argument in Lean 4 and TPTP THF
  80. When Does Test-Time Physical Diagnosis Pay? A Frozen Policy Buys Evidence It Never Reads
  81. On The Robustness-Resolution Tradeoff In Temporal Quantization Of Event Streams
  82. Machine Learning for Underwater Optical Wireless Communication Systems: A Comprehensive Survey
  83. Beyond the Survey: A Systematic Empirical Study of Detection and Association in Visual MOT
  84. AgentPProf: Semantic Profiler for Long Horizon AI Agents
  85. Regularized Emphatic Temporal-Difference Learning: Stability under Constant Stepsizes
  86. Democratizing Clinical Tumor Whole Genome Sequencing: 18-hour End-to-end Analysis via Trillion-parameter Large Language Models Locally Deployed on Consumer-grade Hardware
  87. Stability-Constrained Approximation in Spline KANs: Exact Layer Balancing and Budget-Compatible Saturation
  88. DualCount: Structurally Consistent Density and Point Modeling for Zero-Shot Object Counting
  89. Timbre Analysis of the Hulusi, a Southwestern Chinese Free-Reed Instrument, using Machine Learning
  90. The Neverwhere Visual Parkour Benchmark Suite
  91. Learned Look-Ahead Splitting Rule for CART
  92. ReMova: Fine-tuning LLMs for English to Belarusian translation
  93. How Good Are Time-Series Foundation Models for Pedestrian Crowd Count Forecasting? A Cross-Dataset Comparative Study
  94. On the Expressive Power of Implicit Line-Graph Higher-Order Weisfeiler--Leman
  95. Balancing Trial and Reorder: A Hybrid Sequential Transformer-GBDT Ranker for On-Demand Delivery
  96. Physics Informed Random Feature Neural Networks for Solving PDEs
  97. Implementing a White-Box Undetectable Backdoor for Random Fourier Features
  98. Negation Beyond the Verbal Channel: Temporal Multimodal Correlates in Dialogue
  99. ParsHate: A Benchmark Dataset for Hate and Target Detection in Persian
  100. Where Post-Training Quantization Breaks Text Embedders: A Measured Map Across Four Embedder Families
  101. Attention Mean Fields Predict Average Representation Dynamics and Reveal Context-Specific Computation
  102. Bounded Adjustment with Reliability-Guided Embedding for Imbalanced Learning with Noisy Labels
  103. Geometry vs Structure: Graph-Based Diagnostics for LiDAR Point-Cloud Simulation Fidelity
  104. Certified Uncertainty Propagation in One-Shot Federated Bayesian Models via Posterior Event Transport
  105. Autonomous Droplet Navigation via Model-Based Reinforcement Learning
  106. UDAV: Uncertainty-Driven Adaptive VLM Waypoint Planner
  107. How Humans and LLMs Read Gender into "Gender-Neutral" Physical Descriptions
  108. Mini-batch Sampling Strategies for Long-Tailed Image Classification: An Empirical Study on CIFAR-100-LT
  109. EBL: Efficient Broad Learning for Distributed Adaptive Harmonic Analysis
  110. Federated stochastic bilevel optimization with fully first-order gradients
  111. Multi-Label Proportion Learning for Sea-Ice Type Prediction
  112. Auto-HSI: Personalized human control of a robot swarm on demand by using LLMs for online automatic code generation
  113. From Momentary Emotion Inference to Sustained Emotion Support: Evaluating a Companion Agent in a Longitudinal Study
  114. Channel-Informed Neural Network for Physical Layer Key Generation
  115. Breaking the 1.58-bit Barrier for Ternary LLMs
  116. Cross-Anatomy Transfer Versus Sparse Interpolation in Digital-Twin-Oriented Aortic Fluid-Structure Interaction Surrogates
  117. FairLint-DL: An IDE-Native Tool for Fairness Debugging of Deep Learning Software
  118. ConGraspXL: Controllable Constraint-Conditioned Dexterous Grasping Motion Synthesis
  119. Generative models for simulation based filtering: Formulations and Empirical Comparisons
  120. Robust Fault Detection in Mechanical Multimodal Time Series via Self-Supervised Cross-Modal Reconstruction
  121. Efficient One-to-Many Translation with Joint Multi-Stream Diffusion
  122. Racing in Volume with Flow Ensembles
  123. Sequence Recognition in Bharatnatyam dance
  124. CLEAR: Cross-Source Evidence Adjudication for Large Language Models in Medicine
  125. Closing the Loop: Branch-and-Bound for Scalable Verification of Nonlinear Neural Feedback Systems
  126. Intelligent Interaction Techniques (IIxT) - Proposal
  127. Nationally Consistent, Locally Incomplete: A Bayesian Remote-Sensing Audit of Rooftop Photovoltaic Registries
  128. Symmetric solution of the Bellman optimality equation for repeated harmony game
  129. Drift Field Net: Learning Ocean Lagrangian advection fields from in-situ and satellite observations
  130. ProtoLIP: From Sentence-Level to Object-Level Evidence Disentanglement
  131. Differentially Private Semantic Plans for Aggregate Insight Generation
  132. Scaling Laws for Physics-Aware ACOPF Surrogate Learning
  133. Semantic-Aware Neural Video Codec for Error-Resilient Low-Latency Transmission
  134. The record is part of the task: matched-record evaluation of text classifiers across maintenance, safety and recall reporting
  135. Compute-Optimal Pretrain--Fine-tune in Ridge Gradient Descent
  136. Mapping U.S. Federal AI Governance Against Sector Vulnerability
  137. The AI-Enabled Scientific Frontier
  138. The Pain Axis: LLMs Represent Self-Directed Harm and Act on It
  139. Metacognitive Steering: Learning the Structure of Scientific Judgment
  140. Copula Adapted Directed Acyclic Graph for Cluster Representation of Biomedical Data
  141. Improving Reduced-Order Rotating Detonation Engine Models with Data Assimilation and Machine Learning
  142. How I learned to stop worrying and love StopGrads: Stationarity, Convergence, and a case study on Flow Map Learning
  143. Artificial intelligence and biosecurity: capabilities, threat pathways, and defense-in-depth governance
  144. Hyperbolic Contrastive Learning with Entailment for Spatial Transcriptomics
  145. A Sentinel-2 benchmark dataset for deep-learning active-fire segmentation across 25 California wildfires
  146. Permutation-Based Stegomalware in Large Language Models: Threats and Countermeasures
  147. AI-Driven Feedback Systems, Digital Labour, and Silent Quitting: Transforming African Workplaces
  148. Occupancy Network-Guided Autonomous Robotic Partial Nephrectomy
  149. Skeletal Prototypes on Iterative Nerve Expansions
  150. Multisource Remote Sensing and Geospatial Analysis of Vineyard Wildfire Impacts and Resilience: The 2019 Kincade Fire
  151. GPEvac: GNN-Based PPO for Adaptive Evacuation Routing During Shooting Events
  152. Computer-assisted global regularity across nonlinear families of three-dimensional periodic Navier-Stokes flows
  153. LLMs as Master Forgers: Generating Synthetic Time Series Data for Manufacturing
  154. DenseFace: Bias Mitigation in Face Recognition via Density-Aware Probabilistic Matching
  155. Safe Error Correction for Language Models: Frozen-Base Adjustment with Capability Preservation
  156. Optimal Pruning for Neural Architectures using Fisher Information Distances
  157. A Decision-Support Audit Protocol for Supervision Drift in Proxy-Labeled Credit-Risk Prediction
  158. SWB-DM: A Calibrated Sliced-Wasserstein-Barycenter Aggregator with Delayed-Momentum Caching for Byzantine-Robust Federated Learning under Partial Participation
  159. Evaluating Open-Weight E-Commerce Agents with Environment-Grounded Verification
  160. MUUNRiver-Bench: Diagnosing Relation-Dependent Music Retrieval with Multimodal Instructions
  161. Is INT8 Portable? A Cross-Platform Measurement Study of Quantized Inference on Embedded and Automotive Accelerators
  162. Predicting Social Media Engagement using Machine Learning
  163. A Chosen Future Can Still Be Rewritten: Causal Writability in Video Models
  164. Disentangling Representation Evolution in Transformers through Directional Decomposition
  165. Discovery Foundation Models: Toward Open-Ended Discovery Intelligence
  166. Mind2Dialogue: Training Human-Aware Language Models by Simulating User Mental States
  167. Verifiable by Construction: Claim-Level Evaluation of Verbatim Citation in Clinical Question Answering
  168. Privacy-Aligned Personalized Federated Learning with Compact Adaptation and Variable-Length Gaussian Communication
  169. Recurrent Graph Neural Networks with Set-Based Aggregation
  170. Pilot Early, Commit Late: A Real-Options Model of Enterprise AI Adoption under Rapid Technological Progress
  171. SlipSense: Multimodal Tactile Learning for Low-Latency and Generalized Slip Detection
  172. Bridging Control, Inference, Transport, and Thermodynamics: From Theory to Applications in Learning
  173. Quenched Ensemble Sampling
  174. Anatomical Grounding and Leakage-Aware Multimodal Contrastive Learning for Alzheimer's Disease Classification from Structural MRI
  175. Inoculation Midtraining with Learned Neologisms
  176. Privacy-enhanced federated learning via asynchronous aggregation and local differential perturbation
  177. Thin-shell stability of Gaussian cooling: logconcave sampling with sesteric complexity from a cold start
  178. LLM-Based Schema-Aware Split Learning for Privacy-Preserving Mental Distress Prediction Across Heterogeneous Surveys
  179. Task-Directed Residual AddUNet:Perfect-Reconstruction Routing for Full-Rate Representations
  180. K-Bench: a clinically calibrated benchmark for evaluating large language models in high-risk mental health conversations
  181. Learning to Coach for Experiential Learning
  182. Before You Poll with LLMs: A Deliberative Diagnostic Framework
  183. Proportional-Fair Resource Allocation and Dual-Threshold Early-Exit Inference for Secure Cooperative Multi-Layer Edge Intelligence
  184. Per-Matrix Optimality Is Not Enough: Three-Level Optimization for Low-Rank LLM Compression
  185. TRACE: Two-Stage Detector-Response Estimation With Angular Cosine Expansion for Ring Artifact Correction in Photon-Counting CT
  186. Integrating Multi-view Multi-light Surface Reconstruction into Cultural Heritage Workflows
  187. Sharp Regret Bounds and a Task-Covariance Correction for Spectral Representation Learning
  188. Accelerating Transfer-Learning-Based Autotuning with Predictive LLVM IR Performance Ranking
  189. Delegating Authorization to Misaligned Agents: Coalitional Alignment and Safe Control
  190. SURE-Map: Self-Correcting Streaming Geometric Foundation Models
  191. KnowBench: Effort Reduction as a Unified, Deployment-Grounded Benchmark for Clinical AI
  192. Learning under Target Shift: Optimal Density Ratio Estimation and Importance-Weighted Regression
  193. MoveBench: A Benchmark for Global-Scale Wildlife Movement Forecasting
  194. Transfer Learning for Socioeconomic Estimation in Forced-Displacement Settings
  195. Event-Native Symbolic-Temporal Spike Encoding Framework for Heterogeneous Cyber Streams
  196. Sylvas: Synergistic Learning Value based Device Scheduling in Federated Continual Learning
  197. Enabling Streaming User Transcription in Full-Duplex Speech-to-Speech Models
  198. Sequential Adapter Stacking for Cross-Lingual Low-Resource ASR
  199. TopoRig: Topology-Agnostic Facial Rigging via Multi-Source Supervision
  200. Look Before You Leap: Factual Decoding with Internal Attribution Signals
  201. Design of a Deep Learning Credit Risk Early Warning System Integrating Multi-source Heterogeneous Data
  202. Merging the Knowledge of LLMs for Automatic Speech Recognition
  203. A Language-Guided Multimodal Foundation Model for Zero-Shot and Multi-Task Brain Signal Analysis
  204. Transforming harmonic coefficients for 3D splat compression
  205. Are LLMs Good Financial User Simulators? Multi-view Investor Logic Alignment (MILA)
  206. Bench2Dex: Benchmarking Visuo-Tactile Bimanual Dexterous Manipulation Across Dexterous Hands
  207. Solving Finite-sum Coupled Compositional Optimization via Multi-block-Single-probe Estimator
  208. Data storytelling meets interpretable machine learning: Decoding AI decisions for non-experts without revealing sensitive data and model details
  209. Knowledge-Enriched Structured EHR Features for 30-Day Hospital Readmission Prediction on MIMIC-IV
  210. Predicting build orientation for SLM dental parts: a comparison of rotation representations and direct vector regression
  211. New Conditions for Philosophers to Catch the Wave of Citizen Deliberation in the Age of Artificial Intelligence in advance
  212. More Than Just Access: Generative AI as Communication Intermediary for Blind and Low-Vision Users
  213. EEG-Xplain: Decoding Neural Black-Boxes of EEG Foundation Models
  214. Can a Neural Encoding Model Replicate an fMRI Visualization Study?
  215. Scalability and Performance Evaluation of Federated Learning Frameworks: A Comparative Analysis
  216. Projection-Free Multi-level Algorithms for Stochastic Constrained Compositional Optimization
  217. Benchmarking Intra-Patient 3D Deformable Multimodal Image Registration
  218. CIDERS: Cloud-Edge LLM Collaborative Learning via Accelerating Personalized Bilevel Optimization
  219. KaiNinja: Extending Native 3D Generators to the Part Level
  220. From Model Patterns to Abstract Semantics in Compositional Zero-Shot Learning
  221. SAM3D-Part: Interactive Part Selection and Generation from 3D Objects
  222. Potential of Artificial Intelligence Algorithms for Identification of Relevant Diagnostic and Prognostic Biomarkers of Early-Stage Liver Cancer
  223. ModaLens: Measuring Image Sensitivity in Report-Conditioned Medical VLMs
  224. FedLTLib: A Comprehensive Benchmark for Federated Long-Tail Learning
  225. Beyond AI Literacy: A Structured Review and Exploratory Meta-Analysis of Measures for Competent Generative-AI Use
  226. Where to Compute and How to Interact: Operator-Readable Adaptation with Gauge-Aware Transport
  227. Multi-View Molecular Representation Learning with Hierarchical Graphs and Contextualized Fingerprints
  228. Diversified and Perceptible Counterfactual Examples Leveraging Expert Knowledge
  229. Through the Eyes of the Beholder: Biometric and Demographic Conditioning for Multimodal Sexism Detection
  230. Self-Evolving Memory for Generative Recommendation
  231. What a gated sensing pipeline never looks at: bandwidth reduction and the misses behind it
  232. Big Brains and Changing Environments: Cause or Consequence?
  233. PIVOT: Physics-Grounded Verification for AI-Generated Audio-Video Detection
  234. Can We Trust the Judges? Validation of Factuality Evaluation Methods via Answer Perturbation
  235. Don't Count the Edits, Judge by the Outcome Alone: Reward-Based Evaluation for Grammatical Error Correction
  236. Bayesian Optimisation Using Product-of-Experts Gaussian Process Models with Uncertainty Calibration
  237. Multi-Stage NeRF for Efficient 3D Coronary Artery Reconstruction from Two Narrow-Angle Angiographic Projections
  238. The Token Before the Value Is the Key: How Hybrid Architectures Organize Induction Circuits
  239. Option-Aware Retrieval and Task-Specific VLM Adaptation for Medical VQA
  240. To Each Language Its Tokenizer: Modular Tokenizers for Efficient Multilingual LLMs
  241. Beyond Noise: Understanding and Overcoming Temperature Effects in Analog DNN Inference
  242. Assessing nnU-Net Generalization across Brain Tumor Populations in BraTS-GoAT 2026
  243. Psychosis involves a deficit of information compression in connected speech
  244. End-to-End Verifiable and Robust Federated Learning
  245. Authorship attribution and aesthetic evaluation of AI poetry: a case study with Haiku
  246. SyntheticDoc: A Large Synthetic Dataset for Document Unwarping and Illumination Correction
  247. Same path, different: a mechanistic comparison of looped and stacked transformer encoders on 12-lead ECG
  248. Rotation-Based Subspace Tracking for Robust Kernel PCA on Streaming Data
  249. Data-driven Prediction of Satellite-observed Avalanche Activity from Snowpack Simulations
  250. CatchMonitor: a machine learning system for automated fish discard quantification
  251. GSLAD: Prototype-Regularized Graph Structure Learning for Multivariate Time Series Anomaly Detection
  252. On Detecting Multiple Simultaneous Change-points in High Dimensional Non-Stationary Time Series
  253. Temperature Fragility and the Conditional Benefits of Truncation Sampling
  254. Spook the Machine: Gamified Exploration of Human Imagination of Machine Fear
  255. Turkish MMLU Pro: Traceable Option Augmentation and Its Validity Limits in Turkish Multiple-Choice Evaluation
  256. Online local learning for generative thermodynamic computing
  257. Graph Matching Relaxations and Amortization for Supervised Graph Prediction
  258. On the role of the tokenizer in ECG transformer models
  259. Single-condition neural solvers encode transferable response spaces for parametric differential equations
  260. A Conservative OCR-Enabled Workflow for R214 Sodium Screening of South African Packaged Foods
  261. Empirical Evaluation of Task-Based Permission Scoping Architecture for AI Agents
  262. ViCo-SAM3: Vision-Conditioned Alignment for Open-Vocabulary Camouflaged Object Segmentation
  263. Can AI systems have free will?
  264. BSC-Net: A Small-Branch-Sensitive Structural Continuity Network for Coronary Vessel Segmentation and Quantitative Angiographic Analysis
  265. When Tool Calls Succeed but Workflows Fail: Anomalies at the Agent-Tool Boundary
  266. CodeTS: Verifiable Text-to-Time Series Generation via Executable Code
  267. ESG: Generating Physically Consistent Dynamic 3D Scenes from Text Descriptions
  268. A Game-Theoretic Framework for Incentive-Compatible AI training Under Renewable-Energy Constraints
  269. WebCraftBench: Evaluating Web Application Generation from a Software Testing Perspective
  270. Divide, Consult, Conquer: Capability Laundering Through Aligned LLMs
  271. Representing Clinical Conditions on Vital Signs from Healthy Individuals using Latent Modeling
  272. SlopShape: Identifying AI-Generated Commercial Web Content
  273. CapsuleMotion: A Lightweight Real-Time Visual Motion Predictor for Capsule Endoscopy
  274. Robust and Efficient Communication for Multi-Agent Learning
  275. Approximating Smooth Functionals with ReLU Networks
  276. End-to-End Cell Detection via Instance-aware Graph Modeling
  277. Robust Multi-Model Fitting through Learning Neighbor Regions
  278. Parameter-Efficient Adaptation of Pretrained Language Models for Time-Series Forecasting
  279. Dynamic Semantic Compression for Efficient Latent-Space Inference in Large Language Models
  280. Query-Conditioned Spherical Centroid Aggregation for Multimodal Retrieval
  281. Hypergraph-Regularized Gramian Volumes for Multimodal Retrieval
  282. Clean Scores, Buried Evidence, and Confident Wrong: A Receipt-Based Audit of Frontier Agentic QA
  283. Learning from Reliable Negatives: Confidence-Anchored Test-Time Adaptation for GUI Grounding
  284. When Correlations Mislead: Confounder-Aware Multi-View Urban Region Representation Learning
  285. ProIQA: A Process-Based Framework for Fine-Grained Math Item Quality Assessment
  286. Math for AI safety: an invitation for mathematicians
  287. AlignUS: MRI-Guided Ultrasound Representation Learning for ALS Classification from Tongue Images
  288. Draining Fictitious Knots: Restoring Distance-Awareness Guarantees for High-Dimensional Spline Networks
  289. Learning CNF Formulas from Uniform Random Solutions: Near-Tight Sample Complexity for Valiant's Algorithm
  290. Improving the Last-Iterate Guarantees of Anytime Algorithms for Stochastic Monotone Variational Inequalities
  291. BioDCASE: Active Learning for Bioacoustics
  292. Conformal Individual Treatment Effect Estimation under Networked Interference
  293. Bandits with Probing: Optimal Regret and the Limits of Winner Feedback
  294. A 25-μs/inf Event-driven Graph Neural Network Processor with Spatiotemporal Caching and Spline Convolution for Ultra-low-latency AI at the Edge
  295. Pre-PEFT Probing: Weight Statistics and Perturbation Robustness for Layer Selection in VLM Vision Encoders
  296. Closed-form Bayesian homography estimation from noisy point correspondences
  297. Deep Learning-based Intelligent Diagnosis of Congenital Uterine Anomalies in 3D Ultrasound
  298. Long-to-Short Video Evidence Reasoning for Grounded Question Answering
  299. MAST: Label-Efficient, Robust, and Generalizable Sound Detection for Biodiversity Monitoring via Masked Audio Pretraining and Self-Training
  300. From Ideas to Actions: A Public-Data Decision-Support Toolchain Across the Venture Lifecycle
  301. Augmenting Large Audio-Language Models with Frame-Level Grounding for Fine-Grained Temporal Perception
  302. Failure-Guided Co-Evolution of Prompts and Training Data
  303. Issue Bias in Generative AI Writing Assistance: Political Issues and LLMs in the Swedish 2026 Election
  304. TEAR: Table Extraction with Attribute Recommendation from Texts via Large Language Models
  305. Interpreting hierarchical organisation of speaker embeddings
  306. Semiotic Relations and Proof Methods: A Cross-Genre Study of Argument Structure with Large Language Models
  307. Convergence rates for generative drifting flows: fixed-scale obstructions and multihead acceleration
  308. What Limits Us? Analyzing Self-Reported Limitations in NLP Research
  309. Reconstructing Is Not Acting: Action-Centric Latent Dynamics Modeling
  310. MUSE: A Theory-Harnessed Story Engine for Vibe Narrativizing
  311. Does Attention-Guided Masking Really Help Object Discovery in Object-Centric Learning?
  312. VisInteract: Towards Dynamic Interactive Text-to-Visualization under Imperfect Queries
  313. Low-Dimensional Embeddings for Gaussian Kernels on Manifolds
  314. EECTracker: Swarm Motion Prior-Guided Feature Compensation for Airborne Optical UAV Swarm Tracking
  315. Nearly Minimax-Optimal Regret for Linear Contextual Bandits with Arbitrary Adaptive Action Sets
  316. PACE: Progressive Angular-to-Norm Contrastive Embedding
  317. Weakly Supervised Spatial Grounding for Discriminative Attention-Based Ultrasound-Histopathology Alignment in Prostate Cancer Grading
  318. Multi-source Transfer Learning of Time Series with a Shapelet-based Distance Measure
  319. Automated Perceptually-Motivated Assessment of Photographic Consistency in Paired Clinical Photographs: Pipeline Development and Internal Evaluation
  320. SparseTalk - Sparsifying 3D Gaussian Language Fields for Efficient 3D Visual Question Answering
  321. woma: a real-time foundation model and its fine-tuned models for endoscopy
  322. Medical Knowledge Simplification for Patients in the Era of LLMs: A Case Study on Diabetes
  323. Omni-Streaming Thinking
  324. DepthBenchCAD: When Does Deeper Auditing Yield More Reliable Conclusions?
  325. Eigenvalue-Decomposition Cost Denoising for Predict-then-Optimize
  326. When the Wrong Key Wins: Understanding and Detecting Hallucinations in LLMs
  327. Physics Informed Neural Network model for the dynamical study of Abdominal Aortic Aneurysm
  328. ChatGPT Images 2.5 in the Wild: A Launch-Period Dataset and Detector Evaluation
  329. LG-VLN: A Zero-Shot Vision-and-Language Navigation Framework with LangGraph State Orchestration
  330. OpenAI4S: Code as Action, Science as Sessions
  331. Generate to Explore, Select to Exploit: Aligning LLM-based Headline Generation with Personalized Recommendation
  332. ER-EDF: A Psychology-Grounded Emotion Regulation Framework for Speech Empathetic Dialogue Generation in Large Audio-Language Models
  333. Beyond Numerical Time Series: A Unified Benchmark for Multimodal Forecasting with Heterogeneous Context
  334. mathbbSL(n) Representation Learning: An Intrinsic Mixed-Curvature Space with Higher Curvature Capacities and Deeper Order-Aware Composition
  335. Task-Distribution-Aware Counterweight Synthesis and Constrained Co-Design for Serial Manipulators
  336. Ensemble-Conditioned Molecular Design
  337. Rethinking Procedural Audio Pre-training: Source Scaling and Objective Adaptation
  338. Sensory Precision Inference for Multimodal Arbitration under Uncertainty
  339. Bridging the Gap in ECG-Based Emotion Recognition: A Unified Evaluation of Deep Learning Models
  340. Not All Prompts Are Equal: Exploration-Guided Prompt Scaffolding for Multimodal Reinforcement Post-Training
  341. Ensemble Complexity in Photovoltaic Forecasting
  342. Zero-SNR Analyticity of the Scalar MMSE Is Equivalent to Gaussianity
  343. Structured Features Overfit Where Random Features Grok
  344. Personalizing Personal Health Interfaces: Co-Design with Generative AI
  345. Mirror, Mirror on the Wall: Prompt Echoing in Small Instruct Language Models
  346. SpliTEE: Fast and Private LLM Inference by Coupling GPU-Assisted Trusted Execution Environments with Differential Privacy
  347. MoARa: Module-Aware Rank Allocation and Structure-Preserving Decomposition for Low-Rank LLM Pre-training
  348. Horizon-specific Expert Fusion for Photovoltaic Power Forecasting
  349. Tele360: Real-Time Feed-Forward Human Reconstruction from Sparse Unposed Cameras
  350. Validating Hybrid-State Cache Recovery for GLM-5.3-Flash with vLLM and LMCache
  351. TwinICL: Diagnosing Multimodal In-Context Learning through Paired Counterfactuals
  352. SALUTE: Benchmarking and Adapting LLMs for the Defense Domain
  353. Shared KV Caching for Replicated 27B Inference: Correctness Failures and Performance Boundaries
  354. G-ray: Ray-Level Relative Geometric Position Encoding in Multi-View Vision Transformers under Camera Heterogeneity
  355. PIDS-Bench: Evaluating Prompt-Injection Detectors Under Over-Defense, Obfuscation, and Distribution Shift
  356. Four Ledgers, Not One Score: Responsible Communication of LLM-Judge Calibration in Biomedical ML
  357. ABSOL: Aggregated Bayesian Subsampling Orchestrated with LLMs
  358. HGTO: A Unified Graph-Based Physics-Informed Formulation for Structural Topology Optimization
  359. Typhoon ASR Streaming: Steerable Low-Latency Thai Speech Recognition with Real-Time Shallow Fusion
  360. Learned Bow Control on a Measured Bowed-String Model: a Revised Minimum-Bow-Force Law, a Recurrent Controller, and the Domain of a Supervision Ceiling
  361. Biomedical Reference Generation Remains Unreliable across 26 Large Language Models
  362. Converting Sequenced Fuzzy Cognitive Maps to Causal Virtual Worlds with Large Video Generators
  363. LiftGCN: Efficient Energy-Preserving Graph Learning via Joukowski Spectral Lifting for Finite Element Stress Prediction
  364. Learning to Solve Stochastic Controls with Unknown Drifts and Running Rewards: Theory, Algorithms and Convergence
  365. Towards a knowledge-enhanced single-cell foundation model
  366. Online Language Adaptive Sampling for Better Distributed Cross-lingual Gains
  367. A Corpus-Aligned Uthmani-to-Standard Quranic Word Mapping and a Deterministic Recitation Validator
  368. MoVT: Video-Augmented Motion Tokenizer for Text-to-Motion Generation
  369. Can We Triage LLM Translation Errors in Classical Texts Without Human References? Source Novelty, GEMBA Scoring, and Budgeted Review through Pali-to-English Translation
  370. Geometric Flow enhanced Graph Coarsening
  371. High-Probability Nash Regret for Decentralized Learning in Markov α-Potential Games: Episodic and Fully Online Asynchronous Algorithms with Applications to Markov Congestion Games
  372. CAL-MOS: Bridging Layers with Adapters for Robust MOS Prediction Across Speech Foundation Models
  373. Distributed Fast Fixed-Point Algorithms for Composite Monotone Inclusions over Networks
  374. ThreshGuide: Class-Aware Labeled-Guided Thresholding for Semi-Supervised 3D Abdominal Multi-Organ Segmentation
  375. Cross-Block Conditioning in Deep Boltzmann Machines for Statistical Data Fusion
  376. Linearized PINN with pretrained nonlinear layers
  377. Steady-State Convergence of Stochastic Approximation
  378. Geometric Signatures of Conceptual Reorganization: A Counterfactual Embedding Framework for Detecting Scientific Revolutions
  379. Externalizing Requirement-to-Repair Artifacts as Observable Traces for LLM-Based Program Repair
  380. Neural-Network Solutions to Real-Space Charge Density and Generalization
  381. Shapley Value Estimation for Multi-Site Data with Blockwise-Missing Features
  382. What Makes a 3D Scene Editable? A Factorized Benchmark of Fidelity, Locality, Consistency, and Preservation
  383. An explicit solution of the five-expert prediction PDE and the exact optimality set of COMB
  384. PeerPen: AI-Assisted Writing for Online Mental Health Peer Support
  385. SeqMaestro: From nucleotide sequences to biological hypotheses through interpretable machine learning
  386. Interpolation Is Not Invariance: Pair Count Is Not Coverage in Transformation Audits
  387. Proximal-Only Transmission Matrix Recovery of an Arbitrarily Deformed Graded-Index Multimode Fiber
  388. GGUF-Metadata Prediction of Single-Sequence llama.cpp Throughput Across Three Systems
  389. Domain Generalization for Smartphone-Based Human Activity Recognition: A Systematic Analysis of Components and Interactions
  390. Dream-RSI: Recursive Self-Improvement through Evolving Worlds