mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 3 Jun 2026

548 papers

  1. From Refuse to Richness: Rubric Rewards for Long-Form Hallucination Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  2. HC-RAG: Evidence-Centric Retrieval-Augmented Generation over Heterogeneous Financial FilingsRetrieval-augmented generation → Legal and financial RAG
  3. Stateful Guardrails for Multi-Turn LLM Systems: A Conversational Risk Accumulation FrameworkLLM safety and security → Safety alignment, refusal and guardrails
  4. HyperSU: Corpus-Driven Semantic-Unit Hypergraph for Retrieval-Augmented GenerationRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  5. ProHiFlo: Hierarchical Flow Matching with Functional Guidance for De Novo Protein GenerationDiffusion models → Flow matching, time series and science
  6. PreAct-Bench: Benchmarking Predictive Monitoring in LLMsLLM safety and security → Safety alignment, refusal and guardrails
  7. SocraticPO: Policy Optimization via Interactive GuidanceLLM reasoning → Reinforcement learning for reasoning
  8. SHAPE: Coalition-Aware Expert Pruning for Sparse Mixture-of-Experts LLMsMixture-of-experts → Expert routing strategies
  9. TENP: Trapezoidal Expert Neuron Pruning For Mixture-of-ExpertsMixture-of-experts → MoE large language models
  10. Streaming Knowledge Compilation: Proactive Materiality-Scored Pinning for Time-Evolving LLM WikisEfficient LLM inference and serving → KV cache optimization
  11. MM-Matryoshka: Towards Budget-Elastic Visual Document Retrieval via a 2D Multimodal Matryoshka Training FrameworkMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  12. Attack Selection in Agentic AI Control Evaluations Meaningfully Decreases SafetyLLM agents and tool use → Agent threats, guardrails and governance
  13. EpiEvolve: Self-Evolving Agents for Streaming Pandemic Forecasting under Regime ShiftsSynthetic data and self-improvement for LLMs → Model collapse from synthetic data
  14. LEVANTE-bench: Multi-Scale Comparison of VLMs to Children Using Cognitive Tasks (or, "Is Your VLM Smarter Than a 5th Grader?")Multimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  15. Can We Predict The Human Preference For Text-to-Image Content Prior To Generation And Is It Even Useful To Do So?Diffusion models → Diffusion and flow policies for robotics
  16. SHIELDS: Automating OS Hardening with Iterative Multi-Agent RemediationLLM agents and tool use → Agent threats, guardrails and governance
  17. FlowPRO: Reward-Free Reinforced Fine-Tuning of Flow-Matching VLAs via Proximalized Preference OptimizationVision-language-action models → Efficient VLA inference and adaptation +1
  18. Step-by-Step Optimization-like Reasoning in LLMs over Expanding Search SpacesLLM reasoning → Reinforcement learning for reasoning
  19. Output Type Before Quality: A Standards-Derived XAI Admissibility Rubric for Autonomous-Driving SafetyEnd-to-end autonomous driving → Adversarial scenarios and safety testing
  20. Selective-Advantage Entropy-Adaptive Horizon GRPO: Asymmetric Token-Level Discounting for Efficient Reinforcement Learning of Language ModelsLLM reasoning → Reinforcement learning for reasoning +1
  21. When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent TrajectoriesLLM agents and tool use → Software engineering coding agents
  22. Would you still call this Dax? Novel Visual References in VLMs and HumansMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  23. Harnessing Generalist Agents for Contextualized Time SeriesLLM agents and tool use → Financial trading and forecasting agents
  24. ReasoningFlow: Discourse Structures for Understanding LLM Reasoning TracesLLM reasoning → Reasoning benchmarks and evaluation
  25. UniPixie: Unified and Probabilistic 3D Physics Learning via Flow MatchingDiffusion models → Video generation
  26. VASO: Formally Verifiable Self-Evolving Skills for Physical AI AgentsLLM agents and tool use → Agent skill learning and evolution +1
  27. Human oversight of agentic systems in practice: Examining the oversight work, challenges, and heuristics of developers using software agentsLLM agents and tool use → Software engineering coding agents
  28. Synthetic Contrastive Reasoning for Multi-Table Q&ALLM reasoning → Knowledge- and tool-augmented reasoning
  29. Pattern Selectivity is Not Task-Causal Structure: A Cross-Architecture Mechanistic Study of Composed-Task Circuits in 1B-Class Language ModelsMixture-of-experts → MoE large language models +1
  30. Mamba-Assisted Non-Markovian Closure for Reduced-Order ModelingState-space sequence models (S4, Mamba) → Core SSM architectures for language
  31. A Taxonomy of Runtime Faults in Model Context Protocol ServersLLM agents and tool use → Agent threats, guardrails and governance
  32. The Invisible Hand of Physics: When Video Diffusion Models Know More Than They ShowDiffusion models → Video generation
  33. Multimarginal flow matching with optimal transport potentialsDiffusion models → Flow matching, time series and science
  34. LoRi: Low-Rank Distillation for Implicit ReasoningLLM reasoning → Prompting and chain-of-thought reasoning
  35. What Should Agents Say? Action-state Communication for Efficient Multi-Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  36. Agentic Monte Carlo: Simulating Reinforcement Learning for Black-Box AgentsLLM agents and tool use → Reinforcement learning for LLM agents
  37. Policy-Conditioned Counterfactual Credit for Verifiable Reinforcement Learning of Long-Horizon Language AgentsDeep reinforcement learning methods → RL training of language and agent models
  38. How Far Did They Go? The Persuasive Tactics of Covert LLM Agents in a Discontinued Field ExperimentLLM agents and tool use → Social simulation and multi-agent debate
  39. Flash-WAM: Modality-Aware Distillation for World Action ModelsWorld models → Embodied and robot world models
  40. Towards Persistent Case-Based Memory for Autonomous Data Science: A CBR-Augmented R&D-Agent with a Locally Deployable Small Language ModelLLM agents and tool use → Web, search, and research agents
  41. Inverse Manipulation through Symbolic Planning and Residual Operator LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  42. Search-Time Contamination in Deep Research Agents: Measuring Performance Inflation in Public Benchmark EvaluationLLM reasoning → Knowledge- and tool-augmented reasoning +1
  43. HyFAD: Hybrid Time-Frequency Diffusion with Frequency-Aware Embedding for Time Series ImputationDiffusion models → Flow matching, time series and science
  44. DeployBench: Benchmarking LLM Agents for Research Artifact DeploymentLLM agents and tool use → Web, search, and research agents
  45. A New Quaternion-Joint Cable-Driven Redundant Manipulator Configuration and its Control Through FABRIK and Residual Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  46. Domain-Conditioned Safety in Frontier Computer-Using Agents: A 793-Episode Browser Benchmark, a Coding-Domain Cross-Reference, and a Reproducibility Audit of Recent Red-TeamingLLM agents and tool use → Agent threats, guardrails and governance +1
  47. Streaming Communication in Multi-Agent ReasoningLLM reasoning → Reasoning for agents, planning and code +1
  48. Reinforcement Learning from Rich Feedback with Distributional DAggerLLM reasoning → Reinforcement learning for reasoning +2
  49. Failed Reasoning Traces Tell You What Is Fixable (But Not by Reading Them)LLM reasoning → Test-time compute and efficient thinking
  50. Towards Efficient and Evidence-grounded Mobility Prediction with LLM-Driven AgentLLM agents and tool use → Multimodal and embodied agents
  51. 3D-GlioPREDICT: 3D Latent Diffusion for Post-Radiotherapy Brain MRI Prediction in Patients with GliomaDiffusion models → Medical imaging and segmentation
  52. Arithmetic Pedagogy for Language ModelsLLM reasoning → Mathematical reasoning
  53. FoeGlass: Simple In-Context Learning Is Enough for Red Teaming Audio Deepfake DetectorsLLM safety and security → Audio jailbreaks and speech backdoors
  54. Boosting Self-Consistency with RankingLLM reasoning → Test-time compute and efficient thinking
  55. Strabo: Declarative Specification and Implementation of Agentic Interaction ProtocolsLLM agents and tool use → General LLM agent frameworks and benchmarks
  56. Self-Reflective APIs: Structure Beats Verbosity for AI Agent RecoveryLLM agents and tool use → General LLM agent frameworks and benchmarks
  57. MetaPoint: Unlocking Precise Spatial Control in Agentic Visual GenerationLLM agents and tool use → Multimodal and embodied agents
  58. Imbuing Large Language Models with Bidirectional Logic for Robust Chain RepairLLM reasoning → Test-time compute and efficient thinking
  59. Invariant Gradient Alignment for Robust Reasoning DistillationLLM reasoning → Test-time compute and efficient thinking +1
  60. Generalization of World Models under Environmental Variability for Vision-based Quadrotor NavigationWorld models → World models for navigation
  61. Depth-Attention: Cross-Layer Value Mixing for Language ModelsEfficient LLM inference and serving → KV cache optimization
  62. DAR: Deontic Reasoning with Agentic HarnessesLLM reasoning → Reasoning for agents, planning and code +1
  63. GARL: Game-Theoretic Reinforcement Learning for Multi-Agent Strategic PrioritisationLLM agents and tool use → Reinforcement learning for LLM agents
  64. From Agent Traces to Trust: A Survey of Evidence Tracing and Execution Provenance in LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance
  65. Food-R1: A Unified Multi-Task Food Vision-Language Model with Reinforcement LearningMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  66. AlphaQ: Calibration-Free Bit Allocation for Mixture-of-Experts QuantizationMixture-of-experts → MoE large language models
  67. Potential-Guided Flow Matching for Vision-Language-Action Policy ImprovementVision-language-action models → Efficient VLA inference and adaptation +1
  68. From Prompt to Process: a Process Taxonomy and Comparative Assessment of Frameworks Supporting AI Software Development AgentsLLM agents and tool use → Software engineering coding agents
  69. SemBlock: Semantic Boundary Dynamic Blocks for Diffusion LLMsDiffusion models → Discrete and text diffusion
  70. UAT: Unified Audio-Text Diffusion for Audio Generation, Editing, and CaptioningDiffusion models → Audio, speech and music
  71. Sequential Data Poisoning in LLM Post-TrainingLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  72. Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement LearningLLM alignment / RLHF / preference optimisation → Reward hacking and misspecification +1
  73. Geometry-Aware Distillation for Prompt Tuning Biomedical Vision-Language ModelsMultimodal LLMs / vision-language models → Medical vision-language models
  74. SURF: Separation via Unsupervised Remixing FlowDiffusion models → Audio, speech and music
  75. Caliper: Probing Lexical Anchors versus Causal Structure in LLMsLLM reasoning → Causal reasoning in LLMs
  76. BreastGPT: A Multimodal Large Language Model for the Full Spectrum of Breast Cancer Clinical RoutineMultimodal LLMs / vision-language models → Medical vision-language models
  77. BEATS: Bootstrapping E-commerce Attribute Taxonomies for Search through Iterative Human-AI CollaborationSynthetic data and self-improvement for LLMs → Self-evolving search agents
  78. WAM-Nav: Asymmetric Latent World-Action Modeling for Unified Visual NavigationWorld models → World models for navigation
  79. Provably Auditable and Safe LLM Agents from Human-Authored OntologiesLLM agents and tool use → Agent threats, guardrails and governance
  80. GRAIL: Gradient-Reweighted Advantages for Reinforcement Learning with Verifiable RewardsLLM reasoning → Reinforcement learning for reasoning +1
  81. D3-MoE:Dual Disentangled Diffusion Mixture-of-Experts for Style-Controllable End-to-End Autonomous DrivingEnd-to-end autonomous driving → Imitation-learning end-to-end planners
  82. Optimizing the Cost-Quality Tradeoff of Agentic Theorem Provers in LeanLLM agents and tool use → Educational agents and math problem solving
  83. Agent Planning Benchmark: A Diagnostic Framework for Planning Capabilities in LLM AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  84. HapTile: A Haptic-Informed Vision-Tactile-Language-Action Dataset for Contact-Rich Imitation LearningOffline RL and imitation learning from data → Robot manipulation imitation learning
  85. R-APS: Compositional Reasoning and In-Context Meta-Learning for Constrained Design via Reflective Adversarial Pareto SearchLLM reasoning → Reasoning benchmarks and evaluation +1
  86. Learning While Acting: A Skill-Enhanced Test-Time Co-Evolution Framework for Online Lifelong Learning AgentsLLM agents and tool use → Agent skill learning and evolution
  87. Scenario Generation for Risk-Aware Reinforcement Learning with Probably Approximately Safe GuaranteesDeep reinforcement learning methods → Safe and constrained RL
  88. BiasGRPO: Stabilizing Bias Mitigation in High-Variance Reward Landscapes via Group-Relative Policy OptimizationLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  89. NoRA: Evaluating Grounded Reasonableness in Visual First-person Normative Action ReasoningLLM reasoning → Multimodal reasoning +1
  90. The Right Measure for Physics-Constrained Generation: A Co-Area Correction for Posterior-Consistent PDE Inverse ProblemsDiffusion models → Flow matching, time series and science
  91. UModel: An Agent-Ready Observability Data Modeling Method at ScaleLLM agents and tool use → Software engineering coding agents
  92. Crafting Your Evolving Dreams: Concept-Incremental Versatile CustomizationDiffusion models → Image generation, text-to-image and editing
  93. PersonaTree: Structured Lifecycle Memory for Person Understanding in LLM AgentsLLM agents and tool use → Agent memory systems
  94. Inference-Time Vulnerability Beyond Shallow Safety: Alignment Along Generation TrajectoriesLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  95. Activation Steering of Video Generation Models via Reduced-Order Linear Optimal ControlMechanistic interpretability → Activation steering methods
  96. NextMotionQA: Benchmarking and Judging Human Motion Understanding with Vision-Language ModelsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  97. Coarse-to-fine Hierarchical Architecture with Sequential Mamba for Brain ReconstructionState-space sequence models (S4, Mamba) → Physiological signal modeling
  98. Description-Code Inconsistency in Real-world MCP Servers: Measurement, Detection, and Security ImplicationsLLM agents and tool use → Agent threats, guardrails and governance
  99. Archi: Agentic Operations at the CMS ExperimentLLM agents and tool use → Web, search, and research agents
  100. FALSIFYBENCH: Evaluating Inductive Reasoning in LLMs with Rule Discovery GamesLLM reasoning → Knowledge- and tool-augmented reasoning
All 548
  1. Fog of Love: Engineering Virtuous Agent Behavior with Affinity-based Reinforcement Learning in a Game EnvironmentDeep reinforcement learning methods → RL for games and combinatorial optimization
  2. COP-Q: Safety-First Reinforcement Learning for Robot Control via Cholesky-Ordered ProjectionDeep reinforcement learning methods → Safe and constrained RL
  3. Revisiting Vul-RAG: Reproducibility and Replicability of RAG-based Vulnerability Detection with Open-Weight ModelsRetrieval-augmented generation → Privacy and security of RAG
  4. Physics-Informed Video Generation via Mixture-of-Experts Latent AlignmentDiffusion models → Video generation +1
  5. Trace-Mediated Peak Bias: Bridging Temporal Credit Assignment and Cognitive Heuristics in Deep Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  6. Query-based Cross-Modal Projector Bolstering Mamba Multimodal LLMMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  7. CoRe-MoE: Contrastive Reweighted Mixture of Experts for Multi-Terrain Humanoid Locomotion with Gait AdaptationMixture-of-experts → MoE in reinforcement learning and robotics
  8. VISTA: Vision-Grounded and Physics-Validated Adaptation of UMI data for VLA TrainingVision-language-action models → Generalist VLA models and benchmarks
  9. Rethinking Continual Experience Internalization for Self-Evolving LLM AgentsLLM reasoning → Reasoning for agents, planning and code +2
  10. Benchmarking Living-Screen-Native GUI Agents on Short-Video PlatformsLLM agents and tool use → GUI and mobile agents
  11. DuDi: Dual-Signal Distillation with Cross-Lingual VerbalizerKnowledge distillation → Knowledge distillation for LLMs
  12. SMADE-IE: Sparse Multi-Agent Framework with Evidence-Driven Debate for Zero-Shot Information ExtractionLLM agents and tool use → General LLM agent frameworks and benchmarks
  13. Test-Time Compute Scaling for ASR with Depth-Conditioned Looped TransformersLLM reasoning → Test-time compute and efficient thinking
  14. Explainably Safe Reinforcement LearningDeep reinforcement learning methods → Safe and constrained RL
  15. RAMPART: Registry-based Agentic Memory with Priority-Aware Runtime TransformationLLM agents and tool use → Agent memory systems
  16. MIRAGE: Mobile Agents with Implicit Reasoning and Generative World ModelsWorld models → World models for language agents +1
  17. MeshFlow: Efficient Artistic Mesh Generation via MeshVAE and Flow-based Diffusion TransformerDiffusion models → 3D, point cloud and scene generation
  18. Beyond Symmetric Alignment: Spectral Diagnostics of Modality Imbalance in Vision-Language Models in the Medical DomainMultimodal LLMs / vision-language models → Medical vision-language models
  19. Hybrid Adversarial Defence for Natural Language Understanding TasksLLM safety and security → Jailbreaking
  20. Parthenon Law: A Self-Evolving Legal-Agent FrameworkLLM agents and tool use → Social simulation and multi-agent debate +1
  21. Plan First, Judge Later, Run Better: A DMAIC-Inspired Agentic System for Industrial Anomaly DetectionLLM agents and tool use → Software engineering coding agents
  22. A Systematic Evaluation of Positional Bias in Multi-Video Summarization with MLLMsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  23. KD-NVC: A Search-and-Distill Framework to Accelerate Neural Video CodingKnowledge distillation → General knowledge distillation methods
  24. Ekka: Automated Diagnosis of Silent Errors in LLM InferenceEfficient LLM inference and serving → Serving systems and request scheduling
  25. VCIFBench: Evaluating Complex Instruction Following for Video UnderstandingMultimodal LLMs / vision-language models → Video understanding with MLLMs
  26. Multi-SPIN: Multi-Access Speculative Inference for Cooperative Token Generation at the EdgeEfficient LLM inference and serving → Speculative decoding
  27. SCI-PRM: A Tool Aware Process Reward Model for Scientific Reasoning VerificationLLM reasoning → Reinforcement learning for reasoning +1
  28. Dynamic Multi-Pair Trading Strategy in Cryptocurrency Markets with Deep Reinforcement LearningDeep reinforcement learning methods → Adversarial robustness and RL in finance
  29. Flow-HOA: Generative Joint Optimization for Ambisonics Encoding via Flow MatchingDiffusion models → Audio, speech and music
  30. MineXplore: An Open-Source Reinforcement Learning Exploration Benchmark for GNSS-Denied Underground EnvironmentDeep reinforcement learning methods → RL for robot navigation and UAV control
  31. Rollout-Level Advantage-Prioritized Experience Replay for GRPOLLM reasoning → Reinforcement learning for reasoning
  32. Cartridges at Scale: Training Modular KV Caches over Large Document CollectionsEfficient LLM inference and serving → KV cache optimization
  33. Temporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon AgentsLLM agents and tool use → Agent memory systems
  34. Agentic AI and Pedagogical Best Practice: The Tension Between Automation and LearningLLM agents and tool use → Educational agents and math problem solving
  35. Scaling Self-Evolving Agents via Parametric MemoryLLM agents and tool use → Agent memory systems +1
  36. MAD: Mapping-Aware World Models for Agile Quadrotor FlightWorld models → World models for navigation
  37. ANN Search: Recall What MattersRetrieval-augmented generation → Vector search and ANN indexes
  38. GeoMin: Data-Efficient Semi-Supervised RLVR via Geometric Distribution ModelingLLM reasoning → Reinforcement learning for reasoning +1
  39. MapAgent: An Industrial-Grade Agentic Framework for City-scale Lane-level Map GenerationLLM agents and tool use → Multimodal and embodied agents
  40. Self-Evolving Deep Research via Joint Generation and EvaluationSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training
  41. Simulate, Reason, Decide: Scientific Reasoning with LLMs for Simulation-Driven Decision MakingLLM reasoning → Reasoning benchmarks and evaluation
  42. Smart Picks in the Dark: Towards Efficient RLVR for Reasoning via Tracing Metacognitive PivotsLLM reasoning → Reinforcement learning for reasoning
  43. SFMambaNet: Spectral-Frequency Enhanced Selective State Space Model for Correspondence PruningState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
  44. Global Sketch-Based Watermarking for Diffusion Language ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
  45. AgentJet: A Distributed Swarm Training Framework for Agentic Reinforcement LearningLLM agents and tool use → Reinforcement learning for LLM agents
  46. Voices Across Registers: Corpus-Conditioned Vernacular Jailbreaks against Aligned LLMs via Fanfiction SubgenresLLM safety and security → Jailbreaking
  47. Entity Binding Failures in Speech LLM Reasoning: Diagnosis and Chain-of-Thought InterventionLLM reasoning → Reasoning benchmarks and evaluation
  48. Self-Optimizing Control of Continuous Processes Based on Reinforcement LearningDeep reinforcement learning methods → RL for energy, networks and operations
  49. Learning What to Learn: Stage-Specific Data Sets for SFT-then-RL in Small Language Model ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  50. OSCAR: Omni-Embodiment Action-Conditioned World Model for RoboticsWorld models → Embodied and robot world models
  51. Stepwise Reasoning Enhancement for LLMs via External Subgraph GenerationLLM reasoning → Knowledge- and tool-augmented reasoning
  52. Bridging Short Videos and Live Streams: Reasoning-Guided Multimodal LLMs for Cross-Domain Representation LearningLLM reasoning → Multimodal reasoning
  53. D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft ModelsEfficient LLM inference and serving → Speculative decoding
  54. MemoryDocDataSet: A Benchmark for Joint Conversational Memory and Long Document ReasoningLLM reasoning → Reasoning for agents, planning and code
  55. LoopMoE: Unifying Iterative Computation with Mixture-of-Experts for Language ModelingMixture-of-experts → MoE large language models
  56. 3DThinkVLA: Endowing Vision-Language-Action Models with Latent 3D Priors via 3D-Thinking-Guided Co-trainingLLM reasoning → Spatial and embodied reasoning +1
  57. Cascading Hallucination in Agentic RAG: The CHARM Framework for Detection and MitigationLLM reasoning → Hallucination detection and mitigation +2
  58. Hyper-ICL: Attention Calibration with Hyperbolic Anchor Distillation for Multimodal In-Context LearningMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  59. Stateful Visual Encoders for Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  60. DSA: Dynamic Step Allocation for Fast Autoregressive Video GenerationDiffusion models → Video generation
  61. What If Prompt Injection Never Left? Rethinking Agent Security through Cross-Session Stored Prompt InjectionLLM reasoning → Reasoning for agents, planning and code +2
  62. Trivium: Temporal Regret as a First-Class Objective for Causal-Memory ControllersLLM agents and tool use → Agent memory systems
  63. FlexNPU: Transparent NPU Virtualization for Dynamic LLM Prefill-Decode Co-locationEfficient LLM inference and serving → Serving systems and request scheduling
  64. Not All Errors Are Equal: Consequence-Aware Reasoning Compute AllocationLLM reasoning → Test-time compute and efficient thinking
  65. Context-as-AI-Service: Surfacing Cross-File Dependency Chains for LLM-Generated Developer DocumentationLLM agents and tool use → Software engineering coding agents
  66. Read the Trace, Steer the Path: Trajectory-Aware Reinforcement Learning for Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  67. Online Skill Learning for Web Agents via State-Grounded Dynamic RetrievalLLM agents and tool use → Web, search, and research agents
  68. Rethinking Sales Lead Scoring with LLM-based Hierarchical Preference RankingLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
  69. Geometry-Preserving Unsupervised Alignment for Heterogeneous Foundation ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  70. From Symbolic to Geometric: Enabling Spatial Reasoning in Large Language ModelsLLM reasoning → Spatial and embodied reasoning
  71. Deliberate Evolution: Agentic Reasoning for Sample-Efficient Symbolic Regression with LLMsLLM reasoning → Reasoning for agents, planning and code +1
  72. Frames2LoRA: Parametric Video Internalization for Vision-Language ModelsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  73. Policy Gradient for Continuous-Time Robust Markov Decision ProcessesDeep reinforcement learning methods → RL theory and sample complexity
  74. From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance
  75. Generalizable Multi-Task Learning for Wireless Networks Using Prompt Decision TransformersDeep reinforcement learning methods → RL for energy, networks and operations
  76. Neural Galerkin Normalizing Flows for Bayesian Inference of Diffusions with Inaccessible BoundariesDiffusion models → Diffusion foundations and sampling
  77. Answer Self-Consistency with Margin-Triggered Question Re-Arbitration for the CVPR 2026 VidLLMs ChallengeLLM reasoning → Multimodal reasoning
  78. The Digital Apprentice: A Framework for Human-Directed Agentic AI DevelopmentLLM agents and tool use → Agent threats, guardrails and governance
  79. Exploring Cross-Scenario Generality of Agentic Memory Systems: Diagnostics and a Strong BaselineLLM agents and tool use → Agent memory systems
  80. Organizational Control Layer: Governance Infrastructure at the Execution Boundary of LLM Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  81. Offline-to-Online Learning in Linear BanditsOffline RL and imitation learning from data → Offline RL algorithms
  82. LazyAttention: Efficient Retrieval-Augmented Generation with Deferred Positional EncodingRetrieval-augmented generation → Generation and context integration
  83. Argus-Retriever: Vision-LLM Late-Interaction Retrieval with Region-Aware Query-Conditioned MoE for Visual Document RetrievalMixture-of-experts → MoE large language models
  84. Efficient and Training-Free Single-Image Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  85. When Can You Trust Your Synthetic Users? Diagnostics and Corrections for LLM Consumer Panels
  86. Natural Language Input, Semantic Track Representation, and LLM Inference: Making the Maritime Information Exchange Model Tractable
  87. Proxy-Validated LLM UX Micro-Simulations: An Artifact-First Protocol for Early-Stage Decision Support
  88. Diagnostic Foundation for Evaluating LLMs' Research Integrity as Co-Scientists
  89. Predicting consumer-technology ownership without a diffusion history
  90. Lost in Historical Time? A Polish History Matura Benchmark for Large Language Models
  91. Are Large Language Models Reliable Reviewers? A Benchmark for Error Detection in Financial Documents
  92. The "Knowledge-Behavior Gap" in Cultural Taboo Safety of Large Language Models
  93. Class-Structure Preservation Beats Diversity: A Comprehensive Benchmark of Text Augmentation Methods for Imbalanced Text Classification
  94. Mimicry without understanding: the origins of decision bias in large language models
  95. SDAM: Structure-Difference-Aware Memory Evolution for Complex Text-to-SQL
  96. StorySpark: Module-wise Evolutionary Search for Story Premise Generation
  97. Marginally Useful: An Information-Gap Identity in Conformal Prediction
  98. Schema-Aware Localisation (SAL): Live Schema Grounding and Hallucination Validation for Oracle NL2SQL
  99. How Indian Dermatologists are Utilizing Artificial Intelligence for Clinical Practice and Workflow Management: A Nationwide Survey with a Special Focus on atopic dermatitis
  100. UniCA: Bi-directional Cross-Attention with Positive Similarity Loss for Robust Multi-Modal Retrieval
  101. HMARS: A Hierarchical Multi-Agent Memory System for Long-Context Reasoning
  102. A Geometry-Informed Computer Vision Method for Detecting and Examining Overtaking Vehicles From A Bicycle
  103. Hypothesis-Disciplined Multi-Agent Automated Formalization of Asymptotic Statistical Theory
  104. Towards Multi-Agent-Simulation-Based Community Note Evaluation
  105. RadSEM: A Finding-by-Finding Metric for Clinical Consistency in Radiology Reports
  106. Do Large Language Models Have Emotions?
  107. Tractogram foundation model
  108. LMT: A Bayesian Framework for Causal Discovery from Textual Alarm Records in Manufacturing Systems
  109. Representation Curriculum: Stagewise Training for Robust Ranking and Allocation
  110. Optuna Constrained Tree-Structured Parzen Estimator Is a Joint Density Generalization of c-TPE
  111. SinkRec: Mitigating Semantic State Sink in Long Sequence Recommendation with Memory-Conditioned Gated Delta Networks
  112. Failure Modes of Deep Multi-Agent RL in Asynchronous Pricing: Reproducible Triggers, Trace Diagnostics, and a Partial Fix
  113. TD-Grokking: Learning from Zero-Reward Problems by Training-Time Decomposition
  114. WHU-Infra3D: A Full-stack Multi-modal Dataset and Benchmark for 3D Roadside Infrastructure Inventory
  115. Toward Calibrated, Fair, and accurate Deepfake Detection
  116. Hyperparameter Learning for Latent Factorization of Tensors for Representation Learning to Large-scale Dynamic Weighted Directed Network
  117. Operator Fusion for LLM Inference on the Tensix Architecture
  118. FailureScope: Cross-Regime Behavioral Diagnosis of Language Model Weaknesses
  119. Seq103: A Unified Neuroevolution Framework for Compact Sequence Architecture Discovery
  120. PereStruct: Multimodal Semantic Assembly for Robust Historical Document Parsing
  121. Need We Teach Foundation Models What is a Generative Image? Gradient-Free Generative Artifact Detection via Analytic Spectral Adaptation
  122. Real-Time Industrial Defect Detection on Edge Hardware Using Fine-Tuned YOLOv8: A Systematic Benchmark on the NEU Surface Defect Database and MVTec AD with Automotive & Battery Manufacturing Extensions
  123. What neurosurgeons need to see: synthetic intra-operative MRI from ultrasound for brain-shift compensation in brain tumour surgery
  124. QDS-SNN: Energy-efficient Quantum Deeply-Supervised Spiking Neural Network Algorithm for Traffic Sign Recognition
  125. SC3: The Multi-Solvent Solubility Challenge and Benchmark
  126. FADRW: A Feature-Aware Modulated and Dynamically Reweighted Loss for Few-Shot Linguistic Steganalysis
  127. DSU-Net: An Attention-Enhanced Dense Skip U-Net for Breast Lesion Segmentation in Mammographic Images
  128. Attention-Guided Autoencoder Fusion for Insulator Defect Detection Using UAV Transmission-Line Imaging
  129. Architecturally Significant MLOps Guidelines for ML Model Integration and Deployment: a Gray Literature Review
  130. Attention Consistent Longitudinal Medical Visual Question Answering Guided by Vision Foundation Models
  131. Position: Don't Just "Fix it in Post": A Science of AI Must Study Training Dynamics
  132. GOPAgen: Codec-Aware Agentic Long-Video Understanding with Structured Memory
  133. CARVE-Q: Quantum-Proposed, Classically Certified Interactive Driving Repair
  134. Characterizing the Impact of NVFP4 Quantization for Low-Power Edge AI Deployment
  135. Exploring LLMs for South Asian Music Understanding and Generation
  136. Dominant-Layer ZO: A Single Layer Dominates Zeroth-Order Fine-Tuning of LLMs
  137. BRepCLIP: Contrastive Multimodal Pretraining on BRep Primitives for CAD Understanding
  138. Severity-Aware Curriculum Learning with Multi-Model Response Selection for Medical Text Generation
  139. The Role of Instructional Guidance in Generative AI-Assisted Learning: Empirical Evidence from Construction Engineering Education
  140. Robust Scene Transfer for PointGoal Navigation via Privileged Sensor Guided Contrastive Learning
  141. A Multi-Model Metric-based Selection Framework for Abstractive Text summarization
  142. Unpaired RGB-Thermal Gaussian-Splatting Using Visual Geometric Transformers
  143. LLM-Guided ANN Index Optimization for Human-Object Interaction Retrieval
  144. Sparse Functional Singular Value Decomposition for Biclustering and Triclustering Longitudinal Data
  145. Localizing Prompt Ambiguity in Large Language Models with Probe-Targeted Attribution
  146. Learned Subspace Compression for Communication-Efficient Pipeline Parallelism
  147. Towards Unified and Data-Efficient Prognostics and Health Management with Tabular Foundation Models
  148. AlloGen: Conformation-Selective Binder Generation with Differential State Scoring
  149. Formal Concept Lattices are Good Semantic Scaffolds for Concept-Based Learning
  150. PSEBench: A Controllable and Verifiable Benchmark for Evaluating LLMs in Patient Safety Event Triage
  151. A Two-Channel F-Transform Representation for Early Trajectory Characterization in Iterated Correlation Dynamics
  152. ORACLE-CT: Anatomy-Aware Support Pooling for CT Classification
  153. Horse Eye Blink Detection and Classification for Equine Affective State Assessment
  154. Disentangled Fine-Grained Prototype Learning for Incomplete Image-Tabular Classification
  155. Insurance of Agentic AI
  156. Brick-Composer: Using MLLMs for Assembly with Diverse Bricks
  157. Multilingual Coreference Resolution via Cycle-Consistent Machine Translation
  158. MIRAI: Prediction and Generation of High-Impact Academic Research
  159. GOTabPFN: From Feature Ordering to Compact Tokenization for Tabular Foundation Models on High-Dimensional Data
  160. Sharp First-Order Lower Bounds for Higher-Order Smooth Nonconvex Optimization
  161. Uncertainty-Aware Adaptive Sensor Fusion for Autonomous Navigation
  162. Ten Headache Specialists versus Artificial Intelligence for Clinical Literature Summarization: A Critical Evaluation and Comparison
  163. DP-MacAdam: Differentially Private Mechanism with Adaptive Clipping and Adaptive Momentum
  164. Zero knowledge verification for frontier AI training is possible
  165. Minimizing the Hidden Cost of Scales: Graph-Guided Ultra-Low-Bit Quantization for Large Language Models
  166. ComplexityMT: Benchmarking the Interaction Between Text Complexity and Machine Translation
  167. Assessing the Carbon Emissions and Energy Consumption of U.S. Hyperscale Data Centers
  168. Executable Schema Contracts: From Automatic Ingestion to Multi-Source Retrieval
  169. CausalPOI: Spatio-Temporal Graph-Based Causal Modeling for Cold-Start POI Check-in Forecasting
  170. A Motivational Architecture for Conversational AGI
  171. Mutation Without Variation: Convergence Dynamics in LLM-Driven Program Evolution
  172. Agents' Last Exam
  173. Trust, but Don't Verify: Epistemic Blind Spots in LLM Source Evaluation
  174. LeanMarathon: Toward Reliable AI Co-Mathematicians through Long-Horizon Lean Autoformalization
  175. Willing but Unable: Separating Refusal from Capability in Code LLMs via Abliteration
  176. Residual Modeling for High-Fidelity Learned Compression of Scientific Data
  177. Stability vs. Manipulability: Evaluating Robustness Under Post-Decision Interaction in LLM Judges
  178. Can AI Refute Economic Theory? Evidence from Beyond the Knowledge Cutoff
  179. Generalized TV--ℓp Structured Priors for Bayesian T1 Mapping
  180. Learning-Augmented Online Minimization with Dual Predictions
  181. Deep Learning-assisted AMD Staging based on OCT and OCT Angiography
  182. SHALA-LLM: Smartly Handling Ambiguous Labels in Aligning LLMs
  183. Three-Dimensional Retinal Microvasculature Restoration in OCT Angiography
  184. Evidence-Guided Neural Architecture Selection under Uncertainty for Subject-Specific Blood Glucose Forecasting
  185. Biomazon: A Multimodal Dataset for 3D Forest Structure and Biomass Modeling in the Amazon Basin
  186. Environment-Robust Representation Learning with Empirical Bayes
  187. Oblivious Learning and Collusive Pricing
  188. TabSODA: Tabular Diffusion based Imputation with Skip Pattern Detection and Ordinal Awareness
  189. Recovering Physically Plausible Human-Object Interactions from Monocular Videos
  190. An interpretable and trustworthy AI framework for large-scale longitudinal structure-pain association studies using data from the Osteoarthritis Initiative (OAI)
  191. LightVesselNet: An Ultra-Lightweight Sub-100K Parameter Network for Retinal Blood Vessel Segmentation
  192. TopoPult-SSL: Gland-Mask-Free Cross-Device Meibomian Gland Segmentation via Self-Distilled Weak Clinical Priors
  193. Trajectory Dynamics in Language Model Hidden States Predict Human Processing Costs Beyond Surprisal
  194. PJ-RoPE: A Fourier-Jet-Affine Position Space for Relative Attention
  195. SentinelBench: A Benchmark for Long-Running Monitoring Agents
  196. Self-supervised User Profile Generation for Personalization
  197. A prism hierarchy of learning regimes in large linear autoencoders
  198. Uncertainty Aware Functional Behavior Prediction and Material Fatigue Assessment for Circular Factory
  199. GITCO: Gated Inference-Time Context Optimization in TSFMs
  200. A Model of Multi-turn Human Persuadability Using Probabilistic Belief Tracing
  201. Mean--Fluctuation Dynamics at the Edge of Stability
  202. I Know What You Meme, Even If it Emerged Today: Understanding Evolving Memes through Open-World Knowledge Acquisition
  203. Statistically Reliable LLM-Based Ranking Evaluation via Prediction-Powered Inference
  204. Do Models Share Safety Representations? Cross-Model Steering for Safe Visual Generation
  205. Personal AI Agent for Camera Roll VQA
  206. Anomaly Detection for Electro-Hydrostatic Actuators using LSTM Autoencoder
  207. Learning Manifold and Ito Dynamics with Branched Neural Rough Differential Equations
  208. Aggregating LLM-Based Weak Verifiers for Spatial Layout Generation
  209. Sharp Low-Degree Thresholds for Planted-vs-Planted Testing
  210. Data-efficient flood depth prediction through domain-aware coreset selection and tabular foundation models
  211. REGEN: Reference-Guided Synthetic Multivariate Time Series Generation for Forecasting
  212. X-Band UAV-enabled Integrated Sensing and Communications for Vehicular Networks
  213. NIV: Neural Axis Variations for Variable Font Generation
  214. VideoKR: Towards Knowledge- and Reasoning-Intensive Video Understanding
  215. Harnessing Source Heterogeneity for Cluster-Structured Transfer Learning
  216. Scaling Laws for Behavioral Foundation Models over User Event Sequences
  217. Oklch+: A Three-Parameter Extension of Oklab for Improved Color Difference Prediction
  218. Alpha-RTL: Test-Time Training for RTL Hardware Optimization
  219. From Attack Simulation to SIEM Rule: Deterministic Detection-as-Code Synthesis with Probe-Level Traceability
  220. DiffSlack: Learning under Nonlinear Inequality Constraints via Learnable Slack Variables
  221. Deterministic Envelopes for Tamed SGLD: Decoupling Stochastic Gradient Noise and Localizing Taming
  222. OLIVE: Online Low-Rank Incremental Learning for Efficient Adaptive Exoskeletons
  223. Differentiable Efficient Operator Search
  224. STRIDE: Training Data Attribution via Sparse Recovery from Subset Perturbations
  225. Controllable Dynamic 3D Shape Generation via 3D Trajectories and Text
  226. Beyond Text Following: Repairable Arbitration Reversals in Audio-Language Models
  227. Multi-Column RBF Neural Network Using Adaptive and Non-Adaptive Particle Swarm Optimization
  228. An Open-Source Two-Stage Computer Vision Pipeline for Fine-Grained Vehicle Classification using Vision Transformers
  229. GeM-NR: Geometry-Aware Multi-View Editing for Nonrigid Scene Changes
  230. Phase transitions for the noisy transformer model in arbitrary dimension
  231. BBOmix: A Tabular Benchmark for Hyperparameter Optimization of Unsupervised Biological Representation Learning
  232. Generating Financial Time Series by Matching Random Convolutional Features
  233. Activation-Based Active Learning for In-Context Learning: Challenges and Insights
  234. Deep Embedded Multiplicative DMD for Algebra-Preserving Koopman Learning
  235. Preserving Data Privacy in Learning Causal Structure with Fully Homomorphic Encryption
  236. Geometry Gaussians: Decoupling Appearance and Geometry in Gaussian Splatting
  237. Self-Evaluation Is Already There: Eliciting Latent Judge Calibration in Base LLMs with Minimal Data
  238. Audio Interaction Model
  239. Graph Set Transformer
  240. Continual Visual and Verbal Learning Through a Child's Egocentric Input
  241. Evaluating Large Language Models in Dynamic Clinical Decision-Making with Standardized Patient Cases
  242. RePercENT: Scaling Disentangled Representation Learning Beyond Two Modalities
  243. Who Needs Labels? Adapting Vision Foundation Models With the Metadata You Already Have
  244. Knowledge Index of Noah's Ark
  245. Identifying Gems from Roman RAPIDly
  246. ZipSplat: Fewer Gaussians, Better Splats
  247. Light or Full Verb? A Minimal-Pair Dataset for Probing Phraseological Competence in Language Models
  248. Automatic Generation of Titles for Research Papers Using Language Models
  249. AutoLab: Can Frontier Models Solve Long-Horizon Auto Research and Engineering Tasks?
  250. Fast & Faithful Function Vectors
  251. Learning What Not to Impute: An Uncertainty-Aware Diffusion Framework for Meaningful Missingness
  252. InstantRetouch: Efficient and High-Fidelity Instruction-Guided Image Retouching with Bilateral Space
  253. RIDE: An Open Dataset and Benchmark for Train Delay Prediction
  254. MaCo-GAN: Manifold-Contrastive Adversarial Learning for Single Image Super-Resolution
  255. FLAGG: Flexible Autoregressive Graph Generation
  256. UniCAD: A Unified Benchmark and Universal Model for Multi-Modal Multi-Task CAD
  257. Autonomous heterogeneous catalyst discovery with a self-evolving multi-agent digital twin
  258. Graph Cascades: Contagion-Based Mesoscopic Rewiring for Structure-Aware Graph Machine Learning
  259. Learning Control-Affine Reduced-Order Models via Autoencoders
  260. In-Context Graphical Inference
  261. Anchor3R: Streaming 3D Reconstruction with Transient Anchors for Long-Horizon Visual Mapping
  262. Validity Threats for Foundation Model Research
  263. Enhancing the MADDPG Algorithm for Multi-Agent Learning via Action Inference and Importance Sampling
  264. Handwriting Extraction and Analysis of Signature Lists in Swiss Popular Initiatives
  265. TaDA: Calibrated Probe Gating for Task-Domain LoRA Merging
  266. CIPER: A Unified Framework for Cross-view Image-retrieval and Pose-estimation
  267. M3Eval: Multi-Modal Memory Evaluation through Cognitively-Grounded Video Tasks
  268. SharedRequest: Privacy-Preserving Model-Agnostic Inference for Large Language Models
  269. New Benchmarking Shows Limited Generalization Power of TCR Antigenic Epitope Prediction Models
  270. Multi-Camera AR Guidance System for Surgical Instrument Handling and Assembly: Investigating Workload and Efficiency
  271. DeliChess: A Multi-party Dialogue Dataset for Deliberation in Chess Puzzle Solving
  272. Probing Outcome-Level Resemblance and Mechanism-Level Alignment in LLM Risk Decisions: Evidence from the St. Petersburg Game
  273. SAID: Accelerating Diffusion-Based Language Models via Scaffold-Aware Iterative Decoding
  274. Be Fair! Can Machine Learning Engineering Agents Adhere to Fairness Constraints?
  275. Plan, Watch, Recover: A Benchmark and Architectures for Proactive Procedural Assistance
  276. NLLog: Lightweight, Explainable SOC Anomaly Detection via Log-to-Language Rewriting
  277. Clinical Assistant for Remote Engagement Link (CARE-link): A Web-Based Electronic Health Records Software for Managing Diabetes
  278. A General Framework for Dynamic Consistent Submodular Maximization
  279. STaR-Quant: State-Time Consistent Post-Training Quantization for Diffusion Large Language Models
  280. What Type of Inference is Active Inference?
  281. Mean-based algorithms: A lower bound and regret
  282. AdaKoop: Efficient Modeling of Nonlinear Dynamics from Nonstationary Data Streams with Koopman Operator Regression
  283. Data Attribution in Large Language Models via Bidirectional Gradient Optimization
  284. Scene-Centric Unsupervised Video Panoptic Segmentation
  285. Can Crowdsourcing Survive the LLM Era? A Community Survey on Human Data Collection
  286. Toward Multi-Domain and Long-Tailed Quantization via Feature Alignment and Scaling
  287. Worker Utility as Hysteresis: A Preisach Model of Transaction Acceptance in Gig Labour Markets
  288. 'Your AI Text is not Mine': Redefining and Evaluating AI-generated Text Detection under Realistic Assumptions
  289. CDPM-Align: Multi-Scale Guidance-Aligned Diffusion Pretraining for Robust Few-Shot Anatomical Landmark Detection
  290. Hierarchical Space Partition for Surface Reconstruction
  291. HD-DinoMoE: A Class-Aware Hierarchical Dual Mixture-of-Experts Network for Scleral Anomaly Segmentation in Complex Acquisition Scenarios
  292. Abduction Prover in Isabelle/HOL
  293. Towards Pretraining Text Encoders for TabPFN
  294. Recent Advances and Trends in Learning-based 3D Representations
  295. AICompanionBench: Benchmarking LLMs-as-Judges for AI Companion Safety
  296. Provably Reduced Sample Cost in Prior-Guided Hyperparameter Optimization
  297. IRIS-GAN: Staged Specialist Detection of Deepfake Faces
  298. Learning Empirically Admissible Neural Heuristics for Combinatorial Search
  299. Beyond Missing Rates: Rethinking Incomplete Multi-View Clustering with Protocol Divergence
  300. Uncertainty-Aware End-to-End Co-Design of Neural Network Processors: From Training and Mapping to Fabrication
  301. MusaCoder: Native GPU Kernel Generation with Full-Stack Training on Moore Threads GPU
  302. Large Language Models in K-12 Education: Alignment with State Curriculum Standards and Student Personas
  303. Bayesian learning for the stochastic shortest path problem
  304. Drift-Augmented Scoring: Text-Derived Noise Robustness for Zero-Shot Audio-Language Classification
  305. 3D Temporal Analysis for Autism Spectrum Disorder Screening During Attention Tasks
  306. Prediction Under Imperfect Compression: A Theory of Approximate MDL
  307. Signed Dual Attention: Capturing Signed Dependencies in Time Series Forecasting
  308. A French Corpus Annotated for Multiword Expressions with Adverbial Function
  309. Reconciling Causality and Non-Equilibrium Thermodynamics with Hamiltonian Causal Models
  310. OA-CutMix: Correcting the Label Bias of CutMix
  311. Beyond Objective Equivalence: Constraint Injection for LLM-Based Optimization Modeling on Vehicle Routing Problems
  312. Dream.exe: Can Video Generation Models Dream Executable Robot Manipulation?
  313. Fast Cubical Persistent Homology on 2D and 3D Images via Union-Find, Pruning, and Lookup Tables
  314. BayaHAR: Lightweight Bayesian Few-Shot User Adaptation for On-Device Personalized Human Activity Recognition
  315. A Pathology Foundation Model for Gastric Cancer with Real-World Validation
  316. Z-FLoc: Zero-Shot Floorplan Localization via Geometric Primitives
  317. AIP: A Graph Representation for Learning and Governing Agent Skills
  318. Tree-Based Formalization of Multi-Agent Complementarity in Human-AI Interactions
  319. UniFair: A unified fair clustering approach based on separation and compactness
  320. Measuring Model Robustness via Fisher Information: Spectral Bounds, Theoretical Guarantees, and Practical Algorithms
  321. Do Foundation Models See Biology? Evaluating Attention Coherence with Spatial Transcriptomics in Glioblastoma
  322. Near-Optimal Decentralized Stochastic Convex Optimization over Networks
  323. Beyond Structural Symmetries: Linear Mode Connectivity via Neuron Identifiability
  324. An Empirical Audit of Input Encoders for Multi-Channel Signal Transformers
  325. TIDE: Proactive Multi-Problem Discovery via Template-Guided Iteration
  326. Curvature-aware dynamic precision approach for physics-informed neural networks
  327. Contrastive Learning and Correlation Clustering for Sequences of Network Telescope Data
  328. Multilingual Long-Form Speech Instruction Following: KIT's Submission to IWSLT 2026
  329. StrokeTimer: Robust Representation Learning for Ischemic Stroke Onset-Time Estimation from Non-contrast CT
  330. Data Efficient Complex Feature Fusion Network For Hyperspectral Image Classification
  331. ReConFuse: Reconstruction-Error Guided Semantic Fusion for AI-Generated Video Detection
  332. Enhancing MedSAM with a Lightweight Box Predictor for Medical Image Segmentation
  333. A New Angle on Bones: Robust Pose Estimation in X-Ray and Ultrasound
  334. Graph-Guided Universum Learning in Generalized Eigenvalue Proximal SVMs for Alzheimer's Disease Classification
  335. From Cone Geometry to Monge Structure: Local Defects and Global Regret in High-Dimensional Optimal Transport
  336. QPredSGG: Hybrid Quantum Predicate Learning for Long-Tailed Scene Graph Generation
  337. MeshWeaver: Sparse-Voxel-Guided Surface Weaving for Autoregressive Mesh Generation
  338. Real-Time Automatic License Plate Recognition Using YOLOv8, SORT Tracking, and Temporal Data Interpolation
  339. Read What You Hear: Reference-Free Hypotheses Evaluation with Acoustic Discrepancy
  340. Learning Long Range Spatio-Temporal Representations over Continuous Time Dynamic Graphs with State Space Models
  341. Fitting scattered data with optional monotonicity constraints on GPU: LipFit package
  342. Towards Accurate Model Selection in Deep Unsupervised Domain Adaptation
  343. Why Muon Outperforms Adam: A Curvature Perspective
  344. CRAFT: Cost-aware Refinement And Front-aware Tuning of Prompts
  345. LifeSide: Benchmarking Agents as Lifelong Digital Companions
  346. U-Net-Accelerated Quality-Diversity Optimization for Climate-Adaptive Urban Layouts
  347. Instance-Level Post Hoc Uncertainty Quantification in Object Detection
  348. BiNSGPS: Geometry Problem Solving via Bidirectional Neuro-Symbolic Interaction
  349. ALINC: Active Learning for Inductive Node Classification via Graph Sampling
  350. QO-Bench: Diagnosing Query-Operator-Preserving Retrieval over Typed Event Tuples
  351. CYGNET: Cypher Gate for Neural Execution Triage and Cost Containment
  352. VentAgent: When LLMs Learn to Breathe -- Multi-Objective Arbitration for ARDS Ventilation
  353. Learning symplectic model reduction based on an approximation theorem of symplectic embeddings
  354. QuBLAST: A Framework for Quantizing Large Language Models with Block-Level Compression Approach and Activation Scaling Strategy
  355. A Four-Valued Normative Intermediate Representation for ASP-Oriented Compliance Reasoning
  356. COMBINER: Composed Image Retrieval Guided by Attribute-based Neighbor Relations
  357. Distributional Approximate Nearest Neighbour Search for Uncertainty-Aware Retrieval
  358. Learning Admissible Heuristics via Cost Partitioning
  359. 4D Reconstruction from Sparse Dynamic Cameras
  360. Synthetic Personalities: How Well Can LLMs Mimic Individual Respondents Using Socio-Economic Microdata?
  361. Fine-grained Fragment Retrieval in Multi-modal Long-form Dialogues
  362. HalfNet: Randomized Neural Networks with Learned Subspace Geometry
  363. Reconstructing Unobservable Temperature Fields via Simulation-Aided Intelligent Sensing
  364. ReSGA: A Large Tail Risk Model for Learning Value-at-Risk and Expected Shortfall
  365. SurvPFN: Towards Foundation Models for Survival Predictions
  366. Neetyabhas: A Framework for Uncertainty-Aware Public Policy Optimization in Rational Agent-Based Models
  367. LDARNet: DNA Adaptive Representation Network with Learnable Tokenization for Genomic Modeling
  368. Trading Engagement for Sustainability: Carbon-Aware Re-ranking for E-commerce Recommendations
  369. Beyond Retrieval: Learning Compact User Representations for Scalable LLM Personalization
  370. Impostor: An Agent-Curated Benchmark for Realistic AIGC Manipulation Localization
  371. Dynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models
  372. Optical-Guided Neural Collapse for SAR Few-Shot Class Incremental Learning
  373. Echo-Infinity: Learning Evolving Memory for Real-Time Infinite Video Generation
  374. GENEB: Why Genomic Models Are Hard to Compare
  375. Treat Traffic Like Trees: A Semantic-Preserving Hierarchical Graph-Based Expert Framework for Encrypted Traffic Analysis
  376. SparDA: Sparse Decoupled Attention for Efficient Long-Context LLM Inference
  377. SANE Schema-aware Natural-language Evaluation of Biological Data
  378. Modeling and Interpreting Teamwork Dynamics in Cancer Care Outcome Prediction
  379. Beyond Prompt-Based Planning: MCP-Native Graph Planning-based Biomedical Agent System
  380. Episodic Memory Temporal Consistency for Cooperative Multi-Agent Reinforcement Learning
  381. LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models
  382. IMPose: Interactive Multi-person Pose Estimation with Dynamic Correction Propagation
  383. Evaluating Reasoning Fidelity in Visual Text Generation
  384. When Both Layers Learn: Training Dynamics of Representing Linear Models via ReLU Networks
  385. ChessMimic: Per-Rating Transformer Models for Human Move, Clock, and Outcome Prediction in Online Blitz Chess
  386. Adaptive Calibration for Fair and Performant Facial Recognition
  387. ParetoPilot: Zero-Surrogate Offline Multi-Objective Optimization via Infer-Perturb-Guide Diffusion
  388. SePO: Self-Evolving Prompt Agent for System Prompt Optimization
  389. ChannelTok: Efficient Flexible-Length Vision Tokenization
  390. CyberGym-E2E: Scalable Real-World Benchmark for AI Agents' End-to-End Cybersecurity Capabilities
  391. Token Rankings are Unforgeable Language Model Signatures
  392. Imagine Before You Draw: Visual Prompt Engineering for Image Generation
  393. The Meta-Agent Challenge: Are Current Agents Capable of Autonomous Agent Development?
  394. Radiomic Feature Selection Using Gradient Loss of Deep Neural Network for Lung Cancer Stage Detection
  395. On Out-of-sample Embedding in UMAP
  396. Listening to the Workforce: Measuring Construction Worker Safety Attitudes from Social Media Discourse Using LLMs
  397. RowNet: A Memory Transformer for Tabular Regression
  398. Scaling Datasets for Multi-Sensor, Multi-Agent, and Multi-Domain Learning in Autonomous Systems
  399. INTACT: Ego-Guided Typed Sparse Evidence Retrieval for Heterogeneous Collaborative Perception
  400. Flatness and Generalization: Learning Multi-Index Models with Homogeneous Neural Networks
  401. Implicit Fuzzification via Bounded Noise Injection for Robust Medical Image Segmentation
  402. The price of multi-group transductive learning
  403. Loss-Conditional PINNs for Parametric PDE Families
  404. L-TGVN: Leveraging Longitudinal Priors for Personalized Rapid MRI
  405. CleanCodec: Efficient and Robust Speech Tokenization via Perceptually Guided Encoding
  406. Motion-Guided Causal Disentanglement for Robust Multi-View Cine Cardiac MRI Diagnosis
  407. (Mis)generalization of Helpful-only Fine-tuning
  408. Ultra-Fast Neural Video Compression
  409. An Empirical Study of Data Scale, Model Complexity, and Input Modalities in Visual Generalization
  410. An Ensembled Latent Factor Model via Differential Evolution and Gradient Descent Optimization
  411. Low-Rank Decay for Grokking in Scale-Invariant Transformers: A Spectral-Geometric View
  412. Knockoffs-based False Discovery Rate Control and Simplification for Deep Neural Networks
  413. TANDEM: Bi-Level Data Mixture Optimization with Twin Networks
  414. DPDL: Towards Differential Privacy Preservation in Decentralized Stochastic Learning on Non-IID Data
  415. Physics-Informed Neural Network Modeling of Biodegradable Contaminant Transport through GCL/SL Composite Liners
  416. Shortcomings and capacities of real-constrained neural networks in complex spaces
  417. When Clients Stop Following: A Cognitive Conceptualization Diagram-driven Framework for Strategic Counseling
  418. TITAN-FedAnil+: Trust-Based Adaptive Blockchain Federated Learning for Resource-Constrained Intelligent Enterprises
  419. Revisiting Privacy Amplification by Subsampling in Selective Release DPSGD
  420. LCSHBench: A Multilingual, Consensus-Grounded Benchmark for Library of Congress Subject Heading Assignment
  421. REGAIN: REconciliation GAIN-driven Auxiliary Direction Learning
  422. DLLG: Dynamic Logit-Level Gating of LLM Experts
  423. When Do Fewer Coordinates Suffice in DP-SGD?
  424. DSIRM: Learning Query-Bridged Discrete Semantic Identifiers for E-commerce Relevance Modeling
  425. Selective Coupling of Decoupled Informative Regions: Masked Attention Alignment for Data-Free Quantization of Vision Transformers
  426. VT-3DAD: Cross-Category 3D Anomaly Detection via Visual-Text Normal Space Alignment
  427. GlossAssist -- A Tool to Simplify Corpus Creation and Study the Effect of NLP Models in Low-Resource Documentation Settings
  428. MeshTok: Efficient Multi-Scale Tokenization for Scalable PDE Transformers
  429. Multi-Granularity 3D Kidney Lesion Characterization from CT Volumes
  430. Spatially Grounded Concept Bottleneck Models via Part-Factorized Attention
  431. Disentangling Answer Engine Optimization from Platform Growth: A Log-Based Natural Experiment on ChatGPT Referral Traffic
  432. MorphoQuant: Modality-Aware Quantization for Omni-modal Large Language Models
  433. HYolo: An Intelligent IoT-Based Object Detection System Using Hypergraph Learning
  434. Robust Multi-view Clustering against Imperfect Information
  435. Expectations vs. Realities: The Cost of MSE-Optimal Forecasting Under Conditional Uncertainty
  436. Noisy memory encoding explains negative polarity illusions
  437. Literature-Guided Minimax Optimization of Virtual Epilepsy Neurostimulation
  438. Federated Learning for Multi-Center Sepsis Early Prediction with Privacy-Preserving
  439. A Geometric Characterization of the Stationary Plateau for Two-Layer Neural Networks
  440. Measuring What Matters: Synthetic Benchmarks for Concept Bottleneck Models
  441. Parameter-Efficient Fine-Tuning with Learnable Rank
  442. OpenRFM: Dissecting Relational In-Context Learning
  443. PureLight: Learning Complex Luminaires with Light Tracing
  444. Toward a Generalized Defense Across Sparse, Continuous, and Structured Parameter Attacks
  445. Testing Neural Networks via Bayesian-Guided Exploration of Decision Landscapes
  446. Latent Anchor-Driven Test Generation for Deep Neural Networks
  447. Folded Transport MCMC: Eliminating Label Switching by Sampling on a Fundamental Domain
  448. XSSR: Cross-Domain Self-Supervised Representative Selection for Efficient Annotation in Medical Image Segmentation