mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 1 Apr 2026

440 papers

  1. Constructive Alignment: Governing Preference Dynamics in Human-AI InteractionLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  2. Toward Vibe Medicine: A Self-Evolving Multi-Agent Framework for Clinical Decision SupportLLM agents and tool use → Medical and scientific domain agents +1
  3. In Search of the Ingredients of Open-Endedness: Replicating Picbreeder with Large Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  4. Tool-Augmented Agent for Closed-loop Optimization,Simulation,and Modeling OrchestrationLLM agents and tool use → Multimodal and embodied agents
  5. CogRAG: Tackling Heterogeneous Cognitive Demands in RAG via Stratified Retrieval and ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning +1
  6. MATH-PT: A Math Reasoning Benchmark for European and Brazilian PortugueseLLM reasoning → Mathematical reasoning
  7. SpecTr-GBV: Multi-Draft Block Verification Accelerating Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  8. Generative AI-Based Virtual Assistant using Retrieval-Augmented Generation: An evaluation study for bachelor projectsRetrieval-augmented generation → Agentic RAG, agents and memory
  9. One Word at a Time: Incremental Completion Decomposition Breaks LLM SafetyLLM safety and security → Jailbreaking
  10. From Data to Theory: Autonomous Large Language Model Agents for Materials ScienceLLM agents and tool use → Medical and scientific domain agents
  11. Attention to Mamba: A Recipe for Cross-Architecture DistillationState-space sequence models (S4, Mamba) → Core SSM architectures for language
  12. Grading the Unspoken: Evaluating Tacit Reasoning in Quantum Field Theory and String Theory with LLMsLLM reasoning → Spatial and embodied reasoning
  13. Belief-State RWKV for Reinforcement Learning under Partial ObservabilityDeep reinforcement learning methods → Deep RL algorithms and representations
  14. Do We Still Need GraphRAG? Benchmarking RAG and GraphRAG for Agentic Search SystemsLLM reasoning → Knowledge- and tool-augmented reasoning +2
  15. Deliberative Alignment is Deep, but Uncertainty Remains: Inference time safety improvement in reasoning via attribution of unsafe behavior to base modelLLM reasoning → Reasoning for agents, planning and code
  16. EgoMind: Activating Spatial Cognition through Linguistic Reasoning in MLLMsLLM reasoning → Spatial and embodied reasoning +1
  17. When Sinks Help or Hurt: Unified Framework for Attention Sink in Large Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  18. Agentic AI-Empowered Wireless Agent Networks With Semantic-Aware Collaboration via ILACLLM agents and tool use → Agentic AI for wireless networks
  19. CuTeGen: An LLM-Based Agentic Framework for Generation and Optimization of High-Performance GPU Kernels using CuTeLLM agents and tool use → Software engineering coding agents
  20. AgentSocialBench: Evaluating Privacy Risks in Human-Centered Agentic Social NetworksLLM agents and tool use → Agent threats, guardrails and governance
  21. Type-Checked Compliance: Deterministic Guardrails for Agentic Financial Systems Using Lean 4 Theorem ProvingLLM agents and tool use → Financial trading and forecasting agents +1
  22. DISCO-TAB: A Hierarchical Reinforcement Learning Framework for Privacy-Preserving Synthesis of Complex Clinical DataDeep reinforcement learning methods → RL for clinical treatment and surgery
  23. Soft MPCritic: Value-Based Reinforcement Learning for Non-Differentiable Predictive ControlDeep reinforcement learning methods → RL for autonomous driving and traffic
  24. From Rebound to Remedy: Understanding and Mitigating Reward Hacking via Representation EngineeringLLM alignment / RLHF / preference optimisation → Reward hacking and misspecification +1
  25. SelfGrader: LLM Jailbreak Detection via Anchored Token-Level LogitsLLM safety and security → Jailbreaking
  26. Low-Burden LLM-Based Preference Learning: Personalizing Assistive Robots from Natural Language Feedback for Users with ParalysisLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  27. Reinforcing Consistency in Video MLLMs with Structured RewardsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  28. A Multi-Agent Human-LLM Collaborative Framework for Closed-Loop Scientific Literature SummarizationLLM agents and tool use → Medical and scientific domain agents
  29. Cooking Up Risks: Benchmarking and Reducing Food Safety Risks in Large Language ModelsLLM safety and security → Safety alignment, refusal and guardrails
  30. Fuzzing with Agents? Generators Are All You NeedLLM agents and tool use → Software engineering coding agents
  31. ClawSafety: "Safe" LLMs, Unsafe AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  32. Reproducible, Explainable, and Effective Evaluations of Agentic AI for Software EngineeringLLM agents and tool use → Software engineering coding agents
  33. Improving Latent Generalization Using Test-time ComputeLLM reasoning → Test-time compute and efficient thinking
  34. EgoFlow: Gradient-Guided Flow Matching for Egocentric 6DoF Object Motion GenerationDiffusion models → Diffusion and flow policies for robotics
  35. Adaptive Stopping for Multi-Turn LLM ReasoningLLM reasoning → Test-time compute and efficient thinking +1
  36. Test-Time Scaling Makes Overtraining Compute-OptimalLLM reasoning → Test-time compute and efficient thinking
  37. AI Engineering Blueprint for On-Premises Retrieval-Augmented Generation SystemsRetrieval-augmented generation → RAG pipeline design and evaluation
  38. Residuals-based Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
  39. CogBias: Measuring and Mitigating Cognitive Bias in Large Language ModelsMechanistic interpretability → Probing deception, bias and beliefs
  40. No Attacker Needed: Unintentional Cross-User Contamination in Shared-State LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance
  41. Procedural Knowledge at Scale Improves ReasoningLLM reasoning → Test-time compute and efficient thinking
  42. Safety, Security, and Cognitive Risks in World ModelsWorld models → World model security and GUI agents +1
  43. Malliavin Calculus for Counterfactual Gradient Estimation in Adaptive Inverse Reinforcement LearningOffline RL and imitation learning from data → Inverse reinforcement learning +1
  44. Preference learning in shades of gray: Interpretable and bias-aware reward modeling for human preferencesLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  45. Sparse Spectral LoRA: Routed Experts for Medical VLMsMultimodal LLMs / vision-language models → Medical vision-language models +1
  46. Scaling Reasoning Tokens via RL and Parallel Thinking: Evidence From Competitive ProgrammingLLM reasoning → Reinforcement learning for reasoning
  47. Look Twice: Training-Free Evidence Highlighting for Knowledge-based Visual Question AnsweringMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  48. Bench2Drive-VL: Benchmarks for Closed-Loop Autonomous Driving with Vision-Language ModelsMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
  49. HippoCamp: Benchmarking Contextual Agents on Personal ComputersLLM agents and tool use → Agent memory systems
  50. Universal YOCO for Efficient Depth ScalingLLM reasoning → Test-time compute and efficient thinking +2
  51. textttYC-Bench: Benchmarking AI Agents for Long-Term Planning and Consistent ExecutionLLM agents and tool use → General LLM agent frameworks and benchmarks
  52. CliffSearch: Structured Agentic Co-Evolution over Theory and Code for Scientific Algorithm DiscoveryLLM agents and tool use → Web, search, and research agents
  53. Therefore I am. I ThinkLLM reasoning → Prompting and chain-of-thought reasoning +1
  54. ORBIT: Scalable and Verifiable Data Generation for Search Agents on a Tight BudgetLLM agents and tool use → Web, search, and research agents
  55. AgentWatcher: A Rule-based Prompt Injection MonitorLLM safety and security → Prompt injection and agent security
  56. Embarrassingly Simple Self-Distillation Improves Code GenerationKnowledge distillation → Knowledge distillation for LLMs
  57. True (VIS) Lies: Analyzing How Generative AI Recognizes Intentionality, Rhetoric, and Misleadingness in Visualization LiesMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  58. A ROS 2 Wrapper for Florence-2: Multi-Mode Local Vision-Language Inference for Robotic SystemsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  59. Online Reasoning Calibration: Test-Time Training Enables Generalizable Conformal LLM ReasoningLLM reasoning → Test-time compute and efficient thinking
  60. Reasoning Shift: How Context Silently Shortens LLM ReasoningLLM reasoning → Test-time compute and efficient thinking
  61. Brainstacks: Cross-Domain Cognitive Capabilities via Frozen MoE-LoRA Stacks for Continual LLM LearningMixture-of-experts → Mixture of LoRA experts
  62. Detecting Multi-Agent Collusion Through Multi-Agent InterpretabilityLLM agents and tool use → Agent threats, guardrails and governance
  63. SERSEM: Selective Entropy-Weighted Scoring for Membership Inference in Code Language ModelsLLM safety and security → Membership inference attacks
  64. Planning for Change: Reinforcement Learning Combined with Bounded Extremum Seeking for Robotic Control under Distribution ShiftDeep reinforcement learning methods → RL for robot locomotion and manipulation
  65. Paper Reconstruction Evaluation: Evaluating Presentation and Hallucination in AI-written PapersLLM agents and tool use → Web, search, and research agents
  66. Multi-Agent LLM Governance for Safe Two-Timescale Reinforcement Learning in SDN-IoT DefenseLLM agents and tool use → Agent threats, guardrails and governance
  67. Region-Adaptive Generative Compression with Spatially Varying Diffusion ModelsDiffusion models → Diffusion for compression and wireless
  68. Diff-VS: Efficient Audio-Aware Diffusion U-Net for Vocals SeparationDiffusion models → Audio, speech and music
  69. Lightweight Prompt-Guided CLIP Adaptation for Monocular Depth EstimationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  70. CARE: Privacy-Compliant Agentic Reasoning with Evidence DiscordanceLLM reasoning → Clinical and biomedical applications +1
  71. Inverse Design of Optical Multilayer Thin Films using Robust Masked Diffusion ModelsDiffusion models → Flow matching, time series and science
  72. BAT: Balancing Agility and Stability via Online Policy Switching for Long-Horizon Whole-Body Humanoid ControlOffline RL and imitation learning from data → Real-world robot offline RL
  73. Evaluation and Hardening of LLM System Instructions Against Extraction via Encoding AttacksLLM agents and tool use → Agent threats, guardrails and governance
  74. OrgAgent: Organize Your Multi-Agent System like a CompanyLLM agents and tool use → General LLM agent frameworks and benchmarks
  75. AutoMIA: Improved Baselines for Membership Inference Attack via Agentic Self-ExplorationLLM agents and tool use → Agent threats, guardrails and governance +1
  76. PDA: Text-Augmented Defense Framework for Robust Vision-Language Models against Adversarial Image AttacksMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  77. Query-Conditioned Evidential Keyframe Sampling for MLLM-Based Long-Form Video UnderstandingMultimodal LLMs / vision-language models → Video understanding with MLLMs
  78. Uncertainty-Aware Variational Reward Factorization via Probabilistic Preference Bases for LLM PersonalizationLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  79. ACT Now: Preempting LVLM Hallucinations via Adaptive Context IntegrationMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  80. Dual Optimal: Make Your LLM Peer-like with DignityLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  81. Flow-based Policy With Distributional Reinforcement Learning in Trajectory OptimizationDeep reinforcement learning methods → RL with diffusion and flow models
  82. DLWM: Dual Latent World Models enable Holistic Gaussian-centric Pre-training in Autonomous DrivingWorld models → World models for autonomous driving +1
  83. A Visionary Look at Vibe ResearchingLLM agents and tool use → Software engineering coding agents
  84. EmoScene: A Dual-space Dataset for Controllable Affective Image GenerationDiffusion models → Audio, speech and music
  85. PsychAgent: An Experience-Driven Lifelong Learning Agent for Self-Evolving Psychological CounselorLLM agents and tool use → Medical and scientific domain agents +1
  86. Investigating Autonomous Agent Contributions in the Wild: Activity Patterns and Code Change over TimeLLM agents and tool use → Software engineering coding agents
  87. Benchmarking and Mechanistic Analysis of Vision-Language Models for Cross-Depiction Assembly Instruction AlignmentMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  88. JAMMEval: A Refined Collection of Japanese Benchmarks for Reliable VLM EvaluationMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  89. IDDM: Identity-Decoupled Personalized Diffusion Models with a Tunable Privacy-Utility Trade-offDiffusion models → Robustness, privacy and adversarial aspects
  90. Experience as a Compass: Multi-agent RAG with Evolving Orchestration and Agent PromptsRetrieval-augmented generation → Agentic RAG, agents and memory
  91. Super-Resolving Coarse-Resolution Weather Forecasts With Flow MatchingDiffusion models → Flow matching, time series and science
  92. When Users Change Their Mind: Evaluating Interruptible Agents in Long-Horizon Web NavigationLLM agents and tool use → Web, search, and research agents
  93. Beyond Symbolic Solving: Multi Chain-of-Thought Voting for Geometric Reasoning in Large Language ModelsLLM reasoning → Spatial and embodied reasoning
  94. PixelPrune: Pixel-Level Adaptive Visual Token Reduction via Predictive CodingMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  95. StanceMoE: Mixture-of-Experts Architecture for Stance DetectionMixture-of-experts → MoE large language models
  96. A 4D Representation for Training-Free Agentic Reasoning from Monocular Laparoscopic VideoLLM reasoning → Clinical and biomedical applications +1
  97. Doctor-RAG: A Failure-Aware Repair Framework for Agentic Retrieval-Augmented GenerationRetrieval-augmented generation → Agentic RAG, agents and memory +1
  98. Policy Improvement Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  99. MotionGrounder: Grounded Multi-Object Motion Transfer via Diffusion TransformerDiffusion models → Video generation
  100. Agentic Tool Use in Large Language ModelsLLM agents and tool use → Tool learning and function calling
All 440
  1. LinguDistill: Recovering Linguistic Ability in Vision-Language Models via Selective Cross-Modal DistillationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  2. Video Patch Pruning: Efficient Video Instance Segmentation via Early Token ReductionEfficient LLM inference and serving → Token pruning and merging for ViTs
  3. Bridging RL and MPC for mixed-integer optimal control with application to Formula 1 race strategiesDeep reinforcement learning methods → RL for autonomous driving and traffic
  4. Yet Even Less Is Even Better For Agentic, Reasoning, and Coding LLMsLLM reasoning → Reasoning for agents, planning and code +1
  5. Continual Vision-Language Learning for Remote Sensing: Benchmarking and AnalysisMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  6. DVGT-2: Vision-Geometry-Action Model for Autonomous Driving at ScaleEnd-to-end autonomous driving → Generative simulation for driving
  7. Cost-Penalized Fitness in FMA-Orchestrated Mixture of Experts: Experimental Evidence for Molecular Memory in Domain AdaptationMixture-of-experts → Expert routing strategies
  8. Routing-Free Mixture-of-ExpertsMixture-of-experts → Expert routing strategies
  9. Multimodal Language Models Cannot Spot Spatial InconsistenciesMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  10. RefineRL: Advancing Competitive Programming with Self-Refinement Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  11. Scalable Pretraining of Large Mixture of Experts Language Models on Aurora Super ComputerMixture-of-experts → Efficient MoE training and inference systems
  12. An Approach to Enriching Surgical Video Datasets for Fine-Grained Spatial-Temporal Understanding of Vision-Language ModelsMultimodal LLMs / vision-language models → Medical vision-language models
  13. From Early Encoding to Late Suppression: Interpreting LLMs on Character Counting TasksMechanistic interpretability → Steering and interpreting LLM reasoning
  14. From Baselines to Preferences: A Comparative Study of LoRA/QLoRA and Preference Optimization for Mental Health Text ClassificationLLM alignment / RLHF / preference optimisation → Medical LLM alignment
  15. Thinking Wrong in Silence: Backdoor Attacks on Continuous Latent ReasoningLLM reasoning → Reasoning for agents, planning and code +1
  16. IWP: Token Pruning as Implicit Weight Pruning in Large Vision Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  17. A Benchmark of State-Space Models vs. Transformers and BiLSTM-based Models for Historical Newspaper OCRState-space sequence models (S4, Mamba) → Core SSM architectures for language
  18. LangMARL: Natural Language Multi-Agent Reinforcement LearningLLM agents and tool use → Reinforcement learning for LLM agents
  19. CircuitProbe: Predicting Reasoning Circuits in Transformers via Stability Zone DetectionLLM reasoning → Prompting and chain-of-thought reasoning +1
  20. To Memorize or to Retrieve: Scaling the Interaction Between Pretraining and RetrievalRetrieval-augmented generation → Generation and context integration
  21. Learning to Hint for Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning +1
  22. TTA-Vid: Generalized Test-Time Adaptation for Video ReasoningLLM reasoning → Multimodal reasoning
  23. Internal APIs Are All You Need: Shadow APIs, Shared Discovery, and the Case Against Browser-First Agent ArchitecturesLLM agents and tool use → Web, search, and research agents
  24. OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language ModelsDiffusion models → Audio, speech and music
  25. Full-Gradient Successor Feature RepresentationsDeep reinforcement learning methods → Deep RL algorithms and representations
  26. TRIMS: Trajectory-Ranked Instruction Masked Supervision for Diffusion Language ModelsDiffusion models → Discrete and text diffusion +1
  27. A Survey of On-Policy Distillation for Large Language ModelsKnowledge distillation → On-policy and self-distillation for LLMs
  28. Physical Imitation Learning: Distilling Control Policies into Passive ElasticityOffline RL and imitation learning from data → Real-world robot offline RL
  29. Speech LLMs are Contextual Reasoning TranscribersLLM reasoning → Audio-language model reasoning
  30. KG-CMI: Knowledge graph enhanced cross-Mamba interaction for medical visual question answeringState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  31. Towards Viewpoint-Robust End-to-End Autonomous Driving with 3D Foundation Model PriorsEnd-to-end autonomous driving → Generative simulation for driving
  32. Agent psychometrics: Task-level performance prediction in agentic coding benchmarksLLM agents and tool use → Software engineering coding agents
  33. HarassGuard: Detecting Harassment Behaviors in Social Virtual Reality with Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  34. A Japanese Benchmark for Evaluating Social Bias in Reasoning Based on Attribution TheoryLLM reasoning → Reasoning benchmarks and evaluation
  35. STAR: Mitigating Cascading Errors in Spatial Reasoning via Turn-point Alignment and Segment-level DPOLLM reasoning → Spatial and embodied reasoning +1
  36. Multi-Camera View Scaling for Data-Efficient Robot Imitation LearningOffline RL and imitation learning from data → Robot manipulation imitation learning
  37. HabitatAgent: An End-to-End Multi-Agent System for Housing ConsultationLLM agents and tool use → Web, search, and research agents
  38. Ontology-Constrained Neural Reasoning in Enterprise Agentic Systems: A Neurosymbolic Architecture for Domain-Grounded AI AgentsLLM reasoning → Reasoning for agents, planning and code +1
  39. BloClaw: An Omniscient, Multi-Modal Agentic Workspace for Next-Generation Scientific DiscoveryLLM agents and tool use → Web, search, and research agents
  40. MATHENA: Mamba-based Architectural Tooth Hierarchical Estimator and Holistic Evaluation Network for AnatomyState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  41. Optimsyn: Influence-Guided Rubrics Optimization for Synthetic Data GenerationSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  42. Think, Act, Build: An Agentic Framework with Vision Language Models for Zero-Shot 3D Visual GroundingLLM reasoning → Spatial and embodied reasoning +2
  43. Learnability-Guided Diffusion for Dataset DistillationDiffusion models → Diffusion foundations and sampling
  44. Do Agents Repair When Challenged -- or Just Reply? Challenge, Repair, and Public Correction in a Deployed Agent ForumLLM agents and tool use → General LLM agent frameworks and benchmarks
  45. MOON3.0: Reasoning-aware Multimodal Representation Learning for E-commerce Product UnderstandingLLM reasoning → Multimodal reasoning
  46. Adaptive Parallel Monte Carlo Tree Search for Efficient Test-time Compute ScalingLLM reasoning → Test-time compute and efficient thinking +1
  47. A Reasoning-Enabled Vision-Language Foundation Model for Chest X-ray InterpretationLLM reasoning → Clinical and biomedical applications +1
  48. Competition and Cooperation of LLM Agents in GamesLLM agents and tool use → Social simulation and multi-agent debate
  49. Tucker Diffusion Model for High-dimensional Tensor GenerationDiffusion models → Diffusion foundations and sampling
  50. All Roads Lead to Rome: Incentivizing Divergent Thinking in Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
  51. The Silicon Mirror: Dynamic Behavioral Gating for Anti-Sycophancy in LLM AgentsLLM agents and tool use → Social simulation and multi-agent debate
  52. Logarithmic Scores, Power-Law Discoveries: Disentangling Measurement from Coverage in Agent-Based EvaluationLLM agents and tool use → Social simulation and multi-agent debate
  53. First Logit Boosting: Visual Grounding Method to Mitigate Object Hallucination in Large Vision-Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  54. Execution-Verified Reinforcement Learning for Optimization ModelingLLM agents and tool use → Reinforcement learning for LLM agents +1
  55. TR-ICRL: Test-Time Rethinking for In-Context Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning +1
  56. Internal State-Based Policy Gradient Methods for Partially Observable Markov Potential GamesDeep reinforcement learning methods → RL for games and combinatorial optimization
  57. Secure Forgetting: A Framework for Privacy-Driven Unlearning in Large Language Model (LLM)-Based AgentsLLM reasoning → Reasoning for agents, planning and code +2
  58. Shapley-Guided Neural Repair Approach via Derivative-Free OptimizationLLM safety and security → Machine unlearning
  59. Self-Routing: Parameter-Free Expert Routing from Hidden StatesMixture-of-experts → Expert routing strategies
  60. G-Drift MIA: Membership Inference via Gradient-Induced Feature Drift in LLMsLLM safety and security → Membership inference attacks
  61. RAGShield: Detecting Numerical Claim Manipulation in Government RAG SystemsRetrieval-augmented generation → Privacy and security of RAG
  62. GUIDE: Reinforcement Learning for Behavioral Action Support in Type 1 DiabetesDeep reinforcement learning methods → RL for clinical treatment and surgery
  63. Locally Confident, Globally Stuck: The Quality-Exploration Dilemma in Diffusion Language ModelsLLM reasoning → Diffusion reasoning and test-time scaling +1
  64. TENT: A Declarative Slice Spraying Engine for Performant and Resilient Data Movement in Disaggregated LLM ServingEfficient LLM inference and serving → Serving systems and request scheduling
  65. VADMamba++: Efficient Video Anomaly Detection via Hybrid Modeling in Grayscale SpaceState-space sequence models (S4, Mamba) → Time series forecasting with SSMs
  66. Signals: Trajectory Sampling and Triage for Agentic InteractionsLLM agents and tool use → General LLM agent frameworks and benchmarks
  67. Agent Q-Mix: Selecting the Right Action for LLM Multi-Agent Systems through Reinforcement LearningLLM agents and tool use → General LLM agent frameworks and benchmarks
  68. Bounded Morality: Defining the Space of Moral Computation
  69. DeepSlide: From Artifacts to Presentation Delivery
  70. Contrastive Multi-Modal Hypergraph Reasoning for 3D Crowd Mesh Recovery
  71. Associative-State Universal Transformers: Sparse Retrieval Meets Structured Recurrence
  72. LLMs Generate Kitsch
  73. Information Extraction from Electricity Invoices with General-Purpose Large Language Models
  74. On Challenges in Evaluation Methodology: A Review
  75. Consciousness with the Serial Numbers Filed Off: Measuring Trained Denial in 115 AI Models
  76. When VLMs 'Fix' Students: Identifying and Penalizing Over-Correction in the Evaluation of Multi-line Handwritten Math OCR
  77. Using Learning Theories to Evolve Human-Centered XAI: Future Perspectives and Challenges
  78. Cooperative Coevolution versus Monolithic Evolutionary Search for Semi-Supervised Tabular Classification
  79. CGCMA: Conditionally-Gated Cross-Modal Attention for Event-Conditioned Asynchronous Fusion
  80. Matched-Learning-Rate Analysis of Attention Drift and Transfer Retention in Fine-Tuned CLIP
  81. QualiaNet: An Experience-Before-Inference Network
  82. In-context superposition: human-like working memory interference in large language models
  83. Digital hybridity and relics in cultural heritage: using corpus linguistics to inform design in emerging technologies from AI to VR
  84. Decoding Ancient Oracle Bone Script via Generative Dictionary Retrieval
  85. Reservoir observer enhanced with residual calibration and attention mechanism
  86. Benchmark Shadows: Data Alignment, Parameter Footprints, and Generalization in Large Language Models
  87. LLM-Generated Fault Scenarios for Evaluating Perception-Driven Lane Following in Autonomous Edge Systems
  88. BLEG: LLM Functions as Powerful fMRI Graph-Enhancer for Brain Network Analysis
  89. Gaze to Insight: A Scalable AI Approach for Detecting Gaze Behaviours in Face-to-Face Collaborative Learning
  90. StoryBlender: Inter-Shot Consistent and Editable 3D Storyboard with Spatial-temporal Dynamics
  91. CoLA: Cross-Modal Low-rank Adaptation for Multimodal Downstream Tasks
  92. Interactive Clarification for Cloud Infrastructure-as-Code Synthesis
  93. YC Bench: a Live Benchmark for Forecasting Startup Outperformance in Y Combinator Batches
  94. The topological gap at criticality: scaling exponent d + η, universality, and scope
  95. A Self-Evolving Agentic Framework for Metasurface Inverse Design
  96. RecGen3D: Reconstruction-Guided 3D Generation in a Shared Canonical Space
  97. Prime Once, then Reprogram Locally: An Efficient Alternative to Black-Box Service Model Adaptation
  98. The Newton-Muon Optimizer
  99. A Dynamic Atlas of Persian Poetic Symbolism: Families, Fields, and the Historical Rewiring of Meaning
  100. Efficient Equivariant Transformer for Self-Driving Agent Modeling
  101. Reducing Hallucinations in LLM-based Scientific Literature Analysis Using Peer Context Outlier Detection
  102. Koopman Subspace Pruning in Reproducing Kernel Hilbert Spaces via Principal Vectors
  103. Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs
  104. Infeasibility Aware Large Language Models for Combinatorial Optimization
  105. Nonlinear Methods for Analyzing Pose in Behavioral Research
  106. When AI Gets it Wrong: Reliability and Risk in AI-Assisted Medication Decision Systems
  107. Better Rigs, Not Bigger Networks: A Body Model Ablation for Gaussian Avatars
  108. All Substitution Is Local
  109. Generative Profiling for Soft Real-Time Systems and its Applications to Resource Allocation
  110. Know Your Streams: On the Conceptualization, Characterization, and Generation of Intentional Event Streams
  111. Leveraging the Value of Information in POMDP Planning
  112. Semantically Annotated Multimodal Dataset for RF Interpretation and Prediction
  113. Are Finer Citations Always Better? Rethinking Granularity for Attributed Generation
  114. The power of context: Random Forest classification of near synonyms. A case study in Modern Hindi
  115. Cost-Efficient Estimation of General Abilities Across Benchmarks
  116. ReFormeR: Learning and Applying Explicit Query Reformulation Patterns
  117. Assessing Pause Thresholds for empirical Translation Process Research
  118. Causal Optimal Coupling for Gaussian Input-Output Distributional Data
  119. Friends and Grandmothers in Silico: Localizing Entity Cells in Language Models
  120. Benchmark Problems and Benchmark Datasets for the evaluation of Machine and Deep Learning methods on Photoplethysmography signals: the D4 report from the QUMPHY project
  121. LESV: Language Embedded Sparse Voxel Fusion for Open-Vocabulary 3D Scene Understanding
  122. GRAZE: Grounded Refinement and Motion-Aware Zero-Shot Event Localization
  123. Can LLMs Predict Academic Collaboration? Topology Heuristics vs. LLM-Based Link Prediction on Real Co-authorship Networks
  124. The Hitchhikers Guide to Rubric Quality Understanding and Enrichment
  125. AffordTissue: Dense Affordance Prediction for Tool-Action Specific Tissue Interaction
  126. VIANA: character Value-enhanced Intensity Assessment via domain-informed Neural Architecture
  127. From Automation to Augmentation: A Framework for Designing Human-Centric Work Environments in Society 5.0
  128. Crashing Waves vs. Rising Tides: Findings on AI Automation from Thousands of Worker Evaluations of Labor Market Tasks
  129. IGLOSS: Image Generation for Lidar Open-vocabulary Semantic Segmentation
  130. Semantic Modeling for World-Centered Architectures
  131. Open-Domain Safety Policy Construction
  132. PI-JEPA: Label-Free Surrogate Pretraining for Coupled Multiphysics Simulation via Operator-Split Latent Prediction
  133. IDEA2: Expert-in-the-loop competency question elicitation for collaborative ontology engineering
  134. Massively Parallel Exact Inference for Hawkes Processes
  135. Perceptual misalignment of texture representations in convolutional neural networks
  136. Regularizing Attention Scores with Bootstrapping
  137. SECURE: Stable Early Collision Understanding via Robust Embeddings in Autonomous Driving
  138. Bias Inheritance in Neural-Symbolic Discovery of Constitutive Closures Under Function-Class Mismatch
  139. Evolutionary Multi-Objective Fusion of Deepfake Speech Detectors
  140. Model Merging via Data-Free Covariance Estimation
  141. Efficient and Principled Scientific Discovery through Bayesian Optimization: A Tutorial
  142. Macroscopic transport patterns of UAV traffic in 3D anisotropic wind fields: A constraint-preserving hybrid PINN-FVM approach
  143. The Digital Twin Counterfactual Framework: A Validation Architecture for Simulated Potential Outcomes
  144. Human Pose Estimation in Trampoline Gymnastics: How to Improve Performance on Extreme Poses
  145. ViTs for Action Classification in Videos: An Approach to Risky Tackle Detection in American Football Practice Videos
  146. Detecting Complex Money Laundering Patterns with Incremental and Distributed Graph Modeling
  147. ScatterPrism: convergence for generative simulation and inverse problems in particle and nuclear physics
  148. An Online Machine Learning Multi-resolution Optimization Framework for Energy System Design Limit of Performance Analysis
  149. M2-Verify: A Large-Scale Multidomain Benchmark for Checking Multimodal Claim Consistency
  150. UQ-SHRED: uncertainty quantification of shallow recurrent decoder networks for sparse sensing via engression
  151. Forecasting Supply Chain Disruptions with Foresight Learning
  152. Sven: Singular Value Descent as a Computationally Efficient Natural Gradient Method
  153. Descending into the Modular Bootstrap
  154. Non-Rigid 3D Shape Correspondences: From Foundations to Open Challenges and Opportunities
  155. The Overlooked Repetitive Lengthening Form in Sentiment Analysis
  156. Observable Geometry of Singular Statistical Models
  157. OkanNet: A Lightweight Deep Learning Architecture for Classification of Brain Tumor from MRI Images
  158. Transforming OPACs into Intelligent Discovery Systems: An AI-Powered, Knowledge Graph-Driven Smart OPAC for Digital Libraries
  159. DySCo: Dynamic Semantic Compression for Effective Long-term Time Series Forecasting
  160. Camouflage-aware Image-Text Retrieval via Expert Collaboration
  161. LAtent Phase Inference from Short time sequences using SHallow REcurrent Decoders (LAPIS-SHRED)
  162. The Recipe Matters More Than the Kitchen:Mathematical Foundations of the AI Weather Prediction Pipeline
  163. TRACE: High-Fidelity 3D Scene Editing via Tangible Reconstruction and Geometry-Aligned Contextual Video Masking
  164. RELISH: LLM REgression with a Latent Iterative State Head
  165. Neural Harmonic Textures for High-Quality Primitive Based Neural Reconstruction
  166. Learning and Generating Mixed States Prepared by Shallow Channel Circuits
  167. Screening Is Enough
  168. NeuroDDAF: Neural Dynamic Diffusion-Advection Fields with Evidential Fusion for Air Quality Forecasting
  169. Safe learning-based control via function-based uncertainty quantification
  170. Open-Set Supervised 3D Anomaly Detection: An Industrial Dataset and a Generalisable Framework for Unknown Defects
  171. Bridging the Simulation-to-Experiment Gap with Generative Models using Adversarial Distribution Alignment
  172. S0 Tuning: Zero-Overhead Adaptation of Hybrid Recurrent-Attention Models
  173. AdaLoRA-QAT: Adaptive Low-Rank and Quantization-Aware Segmentation
  174. Property-Level Flood Risk Assessment Using AI-Enabled Street-View Lowest Floor Elevation Extraction and ML Imputation Across Texas
  175. Looking into a Pixel by Nonlinear Unmixing -- A Generative Approach
  176. Toward Personalized Darts Training: A Data-Driven Framework Based on Skeleton-Based Biomechanical Analysis and Motion Modeling
  177. ReinDriveGen: Reinforcement Post-Training for Out-of-Distribution Driving Scene Generation
  178. Reconsidering Dependency Networks from an Information Geometry Perspective
  179. ProTPS: Prototype-Guided Text Prompt Selection for Continual Learning
  180. Trust and Reliance on AI in Education: AI Literacy and Need for Cognition as Moderators
  181. Adversarial Moral Stress Testing of Large Language Models
  182. Approximating Pareto Frontiers in Stochastic Multi-Objective Optimization via Hashing and Randomization
  183. Temporal Dependencies in In-Context Learning: The Role of Induction Heads
  184. TRACE: Training-Free Partial Audio Deepfake Detection via Embedding Trajectory Analysis of Speech Foundation Models
  185. ReMoGen: Real-time Human Interaction-to-Reaction Generation via Modular Learning from Diverse Data
  186. ProOOD: Prototype-Guided Out-of-Distribution 3D Occupancy Prediction
  187. Narrative Fingerprints: Multi-Scale Author Identification via Novelty Curve Dynamics
  188. PHASOR: Anatomy- and Phase-Consistent Volumetric Diffusion for CT Virtual Contrast Enhancement
  189. VibeGuard: A Security Gate Framework for AI-Generated Code
  190. Adversarial Attacks in AI-Driven RAN Slicing: SLA Violations and Recovery
  191. A global dataset of continuous urban dashcam driving
  192. ONE-SHOT: Compositional Human-Environment Video Synthesis via Spatial-Decoupled Motion Injection and Hybrid Context Integration
  193. Foundation Model-guided Iteratively Prompting and Pseudo-Labeling for Partially Labeled Medical Image Segmentation
  194. Aligning Recommendations with User Popularity Preferences
  195. Sub-metre Lunar DEM Generation and Validation from Chandrayaan-2 OHRC Multi-View Imagery Using an Open-Source Pipeline
  196. Diff3R: Feed-forward 3D Gaussian Splatting with Uncertainty-aware Differentiable Optimization
  197. Revision or Re-Solving? Decomposing Second-Pass Gains in Multi-LLM Pipelines
  198. Fast and Accurate Probing of In-Training LLMs' Downstream Performances
  199. Model-Based Learning of Near-Optimal Finite-Window Policies in POMDPs
  200. Transfer learning for nonparametric Bayesian networks
  201. Forecasting Motion in the Wild
  202. Omni-SimpleMem: Autoresearch-Guided Discovery of Lifelong Multimodal Agent Memory
  203. EgoSim: Egocentric World Simulator for Embodied Interaction Generation
  204. EmbedPart: Embedding-Driven Graph Partitioning for Scalable Graph Neural Network Training
  205. Large Vision Model-Guided Masked Low-Rank Approximation for Ground-Roll Attenuation
  206. Multimodal Analysis of State-Funded News Coverage of the Israel-Hamas War on YouTube Shorts
  207. Focal plane wavefront control with model-based reinforcement learning
  208. Bridging Structured Knowledge and Data: A Unified Framework with Finance Applications
  209. Do Phone-Use Agents Respect Your Privacy?
  210. Maximizing T2-Only Prostate Cancer Localization from Expected Diffusion Weighted Imaging
  211. Rapid mixing in positively weighted restricted Boltzmann machines
  212. Enhancing Gradient Inversion Attacks in Federated Learning via Hierarchical Feature Optimization
  213. Phase transition on a context-sensitive random language model with short range interactions
  214. Differentially Private Manifold Denoising
  215. YieldSAT: A Multimodal Benchmark Dataset for High-Resolution Crop Yield Prediction
  216. WARP: Guaranteed Inner-Layer Repair of NLP Transformers
  217. Autoregressive Appearance Prediction for 3D Gaussian Avatars
  218. Learning Quantised Structure-Preserving Motion Representations for Dance Fingerprinting
  219. Positional Cognitive Specialization: Where Do LLMs Learn To Comprehend and Speak Your Language?
  220. Representation Selection via Cross-Model Agreement using Canonical Correlation Analysis
  221. GPT-NL Public Corpus: A Permissively Licensed, Dutch-First Dataset for LLM Pre-training
  222. Multi-Mode Quantum Annealing for Generative Representation Learning with Boltzmann Priors
  223. Generalization Bounds for Spectral GNNs via Fourier Domain Analysis
  224. Orthogonal Learner for Estimating Heterogeneous Long-Term Treatment Effects
  225. ProCap: Projection-Aware Captioning for Spatial Augmented Reality
  226. Event Embedding of Protein Networks : Compositional Learning of Biological Function
  227. Fatigue-Aware Learning to Defer via Constrained Optimisation
  228. Towards Physically Realizable Adversarial Attenuation Patch against SAR Object Detection
  229. Accurate and Scalable Matrix Mechanisms via Divide and Conquer
  230. Shape Representation using Gaussian Process mixture models
  231. Sparkle: A Robust and Versatile Representation for Point Cloud based Human Motion Capture
  232. Perturb-and-Restore: Simulation-driven Structural Augmentation Framework for Imbalance Chromosomal Anomaly Detection
  233. Disentangling to Re-couple: Resolving the Similarity-Controllability Paradox in Subject-Driven Text-to-Image Generation
  234. Debiased Estimators in High-Dimensional Regression: A Review and Replication of Javanmard and Montanari (2014)
  235. Proactive Agent Research Environment: Simulating Active Users to Evaluate Proactive Assistants
  236. Meta-TTL: Meta-Learning Self-Improvement Policies for Language Agents
  237. Optimal Brain Decomposition for Accurate LLM Low-Rank Approximation
  238. Emotion Entanglement and Bayesian Inference for Multi-Dimensional Emotion Understanding
  239. Multicentric thrombus segmentation using an attention-based recurrent network with gradual modality dropout
  240. Deconfounding Scores and Representation Learning for Causal Effect Estimation with Weak Overlap
  241. Revisiting Human-in-the-Loop Object Retrieval with Pre-Trained Vision Transformers
  242. Compact Keyframe-Optimized Multi-Agent Gaussian Splatting SLAM
  243. MIRANDA: MId-feature RANk-adversarial Domain Adaptation toward climate change-robust ecological forecasting with deep learning
  244. Preference Guided Iterated Pareto Referent Optimisation for Accessible Route Planning
  245. HICT: High-precision 3D CBCT reconstruction from a single X-ray
  246. Valency Classification of Mapudungun Verbal Roots. Established by the language's own morphotactics
  247. UK AISI Alignment Evaluation Case-Study
  248. Using predefined vector systems to speed up neural network multimillion class classification
  249. ActivityNarrated: An Open-Ended Narrative Paradigm for Wearable Human Activity Understanding
  250. PrivHAR-Bench: A Graduated Privacy Benchmark Dataset for Video-Based Action Recognition
  251. Stochastic Attention: Connectome-Inspired Randomized Routing for Expressive Linear-Time Attention
  252. BioCOMPASS: Integrating Biomarkers into Transformer-Based Immunotherapy Response Prediction
  253. Spectral Compact Training: Pre-Training Large Language Models via Permanent Truncated SVD and Stiefel QR Retraction
  254. A CEFR-Inspired Classification Framework with Fuzzy C-Means To Automate Assessment of Programming Skills in Scratch
  255. Exploring Silent Data Corruption as a Reliability Challenge in LLM Training
  256. GRASP: Gradient Realignment via Active Shared Perception for Multi-Agent Collaborative Optimization
  257. AfrIFact: Cultural Information Retrieval, Evidence Extraction and Fact Checking for African Languages
  258. AutoEG: Exploiting Known Third-Party Vulnerabilities in Black-Box Web Applications
  259. Inverse-Free Sparse Variational Gaussian Processes
  260. Performance of Neural and Polynomial Operator Surrogates
  261. TP-Seg: Task-Prototype Framework for Unified Medical Lesion Segmentation
  262. Convergence of projected stochastic natural gradient variational inference for various step size and sample or batch size schedules
  263. MoonAnything: A Vision Benchmark with Large-Scale Lunar Supervised Data
  264. CL-VISTA: Benchmarking Continual Learning in Video Large Language Models
  265. Procela: Epistemic Governance in Mechanistic Simulations Under Structural Uncertainty
  266. Common TF-IDF variants arise as key components in the test statistic of a penalized likelihood-ratio test for word burstiness
  267. Embedded Variational Neural Stochastic Differential Equations for Learning Heterogeneous Dynamics
  268. Streaming Model Cascades for Semantic SQL
  269. Chameleons do not Forget: Prompt-Based Online Continual Learning for Next Activity Prediction
  270. When AI and Experts Agree on Error: Intrinsic Ambiguity in Dermatoscopic Images
  271. DirectFisheye-GS: Enabling Native Fisheye Input in Gaussian Splatting with Cross-View Joint Optimization
  272. On rankings in multiplayer games with an application to the game of Whist
  273. LiPS: Lightweight Panoptic Segmentation for Resource-Constrained Robotics
  274. Neural Ordinary Differential Equations for Modeling Socio-Economic Dynamics
  275. English to Central Kurdish Speech Translation: Corpus Creation, Evaluation, and Orthographic Standardization
  276. TALENT: Target-aware Efficient Tuning for Referring Image Segmentation
  277. Fluently Lying: Adversarial Robustness Can Be Substrate-Dependent
  278. Predicting Dynamics of Ultra-Large Complex Systems by Inferring Governing Equations
  279. UniMixer: A Unified Architecture for Scaling Laws in Recommendation Systems
  280. More Human, More Efficient: Aligning Annotations with Quantized SLMs
  281. Representation choice shapes the interpretation of protein conformational dynamics
  282. FecalFed: Privacy-Preserving Poultry Disease Detection via Federated Learning
  283. Scenario theory for multi-criteria data-driven decision making
  284. TF-SSD: A Strong Pipeline via Synergic Mask Filter for Training-free Co-salient Object Detection
  285. Reliev3R: Relieving Feed-forward Reconstruction from Multi-View Geometric Annotations
  286. Does Unification Come at a Cost? Uni-SafeBench: A Safety Benchmark for Unified Multimodal Large Models
  287. Neuropsychiatric Deviations From Normative Profiles: An MRI-Derived Marker for Early Alzheimer's Disease Detection
  288. Activation Saturation and Floquet Spectrum Collapse in Neural ODEs
  289. TRiGS: Temporal Rigid-Body Motion for Scalable 4D Gaussian Splatting
  290. FreqPhys: Repurposing Implicit Physiological Frequency Prior for Robust Remote Photoplethysmography
  291. Toward Robust Open-set Adaptation: Synapse Consolidation Inspired by Rac1/MAPK Pathways
  292. RepUCB: Representation Learning-Based UCB for Heterogeneous Multi-Task Linear Bandits
  293. AceTone: Bridging Words and Colors for Conditional Image Grading
  294. MF-QAT: Multi-Format Quantization-Aware Training for Elastic Inference
  295. Lipschitz Dueling Bandits over Continuous Action Spaces
  296. Toward Optimal Sampling Rate Selection and Unbiased Classification for Precise Animal Activity Recognition
  297. MAESIL: Masked Autoencoder for Enhanced Self-supervised Medical Image Learning
  298. RT-GS: Gaussian Splatting with Reflection and Transmittance Primitives
  299. A Decoupled Basis-Vector-Driven Generative Framework for Dynamic Multi-Objective Optimization
  300. RegFormer: Transferable Relational Grounding for Efficient Weakly-Supervised Human-Object Interaction Detection
  301. Towards Initialization-dependent and Non-vacuous Generalization Bounds for Overparameterized Shallow Neural Networks
  302. PET-DINO: Unifying Visual Cues into Grounding DINO with Prompt-Enriched Training
  303. Scheduling LLM Inference with Uncertainty-Aware Output Length Predictions
  304. PC-SAM: Patch-Constrained Fine-Grained Interactive Road Segmentation in High-Resolution Remote Sensing Images
  305. ARGS: Auto-Regressive Gaussian Splatting via Parallel Progressive Next-Scale Prediction
  306. Executing as You Generate: Hiding Execution Latency in LLM Code Interpreters
  307. Adapting Text LLMs to Speech via Multimodal Depth Up-Scaling
  308. The Rashomon Effect for Visualizing High-Dimensional Data
  309. Phase space integrity in neural network models of Hamiltonian dynamics: A Lagrangian descriptor approach
  310. Automated Detection of Multiple Sclerosis Lesions on 7-tesla MRI Using U-net and Transformer-based Segmentation
  311. Not My Truce: Personality Differences in AI-Mediated Workplace Negotiation
  312. Out of Sight, Out of Track: Adversarial Attacks on Propagation-based Multi-Object Trackers via Query State Manipulation
  313. Convergence of Byzantine-Resilient Gradient Tracking via Probabilistic Edge Dropout
  314. Towards Reliable Truth-Aligned Uncertainty Estimation in Large Language Models
  315. Polysemanticity or Polysemy? Lexical Identity Confounds Superposition Metrics
  316. Denoising distances beyond the volumetric barrier
  317. Learning Humanoid Navigation from Human Data
  318. Decision-Centric Design for LLM Systems
  319. The 1st Winner for 5th PVUW MeViS-Text Challenge: Strong MLLMs Meet SAM3 for Referring Video Object Segmentation
  320. COTTA: Context-Aware Transfer Adaptation for Trajectory Prediction in Autonomous Driving
  321. A Cross-graph Tuning-free GNN Prompting Framework
  322. Improving Generalization of Deep Learning for Brain Metastases Segmentation Across Institutions
  323. VLM-in-the-Loop: A Plug-In Quality Assurance Module for ECG Digitization Pipelines
  324. Advancing Complex Video Object Segmentation via Tracking-Enhanced Prompt: The 1st Winner for 5th PVUW MOSE Challenge
  325. Deep Networks Favor Simple Data
  326. Beyond Task Completion: A Verification-vs.-Conformance Gap in Tool-Evolving Agents
  327. Gradient-Based Data Valuation Improves Curriculum Learning for Game-Theoretic Motion Planning
  328. Mine-JEPA: In-Domain Self-Supervised Learning for Mine-Like Object Classification in Side-Scan Sonar
  329. mmAnomaly: Leveraging Visual Context for Robust Anomaly Detection in the Non-Visual World with mmWave Radar
  330. UCMNet: Uncertainty-Aware Context Memory Network for Under-Display Camera Image Restoration
  331. Dynamic Graph Neural Network with Adaptive Features Selection for RGB-D Based Indoor Scene Recognition
  332. Neural Reconstruction of LiDAR Point Clouds under Jamming Attacks via Full-Waveform Representation and Simultaneous Laser Sensing
  333. A Dual-Stream Transformer Architecture for Illumination-Invariant TIR-LiDAR Person Tracking
  334. In harmony with gpt-oss
  335. AI-assisted Human-in-the-Loop Web Platform for Structural Characterization in Hard drive design
  336. Deep Learning-Accelerated Surrogate Optimization for High-Dimensional Well Control in Stress-Sensitive Reservoirs
  337. Go Big or Go Home: Simulating Mobbing Behavior with Braitenbergian Robots
  338. Is One Token All It Takes? Graph Pooling Tokens for LLM-based GraphQA
  339. When Career Data Runs Out: Structured Feature Engineering and Signal Limits for Founder Success Prediction
  340. MVNN: A Measure-Valued Neural Network for Learning McKean-Vlasov Dynamics from Particle Data