mlsanityData to 14 Oct 2026

Papers

New on arXiv

Tue 3 Mar 2026

433 papers

  1. Beyond the 'Diff': Addressing Agentic Entropy in Agentic Software DevelopmentLLM agents and tool use → Software engineering coding agents
  2. DeepReviewer 2.0: A Traceable Agentic System for Auditable Scientific Peer ReviewLLM agents and tool use → Web, search, and research agents
  3. Evaluating Prompting Strategies for Chart Question Answering with Large Language ModelsLLM reasoning → Prompting and chain-of-thought reasoning
  4. Thinking into the Future: Latent Lookahead Training for TransformersLLM reasoning → Test-time compute and efficient thinking
  5. An experimental study of KV cache reuse strategies in chunk-level caching systemsRetrieval-augmented generation → Generation and context integration +1
  6. Expected Reward Prediction, with Applications to Model RoutingLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  7. Locally Coherent Parallel Decoding in Diffusion Language ModelsDiffusion models → Discrete and text diffusion +1
  8. Multi-Agent Debate with Memory MaskingLLM reasoning → Reasoning for agents, planning and code +1
  9. GSI Agent: Domain Knowledge Enhancement for Large Language Models in Green Stormwater InfrastructureLLM agents and tool use → Multimodal and embodied agents
  10. CraniMem: Cranial Inspired Gated and Bounded Memory for Agentic SystemsLLM agents and tool use → Agent memory systems
  11. Form Follows Function: Recursive Stem ModelLLM reasoning → Test-time compute and efficient thinking
  12. Preventing Curriculum Collapse in Self-Evolving Reasoning SystemsLLM reasoning → Reasoning for agents, planning and code +1
  13. Evidence-based Distributional Alignment for Large Language ModelsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  14. VB: Visibility Benchmark for Visibility and Perspective Reasoning in ImagesLLM reasoning → Multimodal reasoning +1
  15. MultiGen: Level-Design for Editable Multiplayer Worlds in Diffusion Game EnginesWorld models → Video-generation world models and simulators
  16. Does Semantic Noise Initialization Transfer from Images to Videos? A Paired Diagnostic StudyDiffusion models → Video generation
  17. Hybrid Orchestration of Edge AI and Microservices via Graph-based Self-Imitation LearningOffline RL and imitation learning from data → Offline multi-agent RL +1
  18. Act-Observe-Rewrite: Multimodal Coding Agents as In-Context Policy Learners for Robot ManipulationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  19. Understanding the Dynamics of Demonstration Conflict in In-Context LearningMechanistic interpretability → Probing deception, bias and beliefs
  20. Benchmark of Benchmarks: Unpacking Influence and Code Repository Quality in LLM Safety BenchmarksLLM safety and security → Safety alignment, refusal and guardrails
  21. Social Norm Reasoning in Multimodal Language Models: An EvaluationLLM reasoning → Multimodal reasoning +1
  22. stratum: A System Infrastructure for Massive Agent-Centric ML WorkloadsLLM agents and tool use → Web, search, and research agents
  23. Build, Judge, Optimize: A Blueprint for Continuous Improvement of Multi-Agent Consumer AssistantsLLM agents and tool use → Social simulation and multi-agent debate
  24. Benchmarking Emergent Coordination in Large-Scale LLM Populations: An Evaluation Framework on the MoltBook ArchiveLLM agents and tool use → General LLM agent frameworks and benchmarks
  25. PinCLIP: Large-scale Foundational Multimodal Representation at PinterestMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  26. RAG-X: Systematic Diagnosis of Retrieval-Augmented Generation for Medical Question AnsweringRetrieval-augmented generation → Medical and biomedical RAG
  27. Verify to Amplify: Improving Reasoning via Learned Chain-of-Thought VerificationLLM reasoning → Test-time compute and efficient thinking
  28. SafeCRS: Personalized Safety Alignment for LLM-Based Conversational Recommender SystemsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  29. Logit-Level Uncertainty Quantification in Vision-Language Models for Histopathology Image AnalysisMultimodal LLMs / vision-language models → Medical vision-language models
  30. Q-Measure-Learning for Continuous State RL: Efficient Implementation and ConvergenceDeep reinforcement learning methods → RL theory and sample complexity
  31. The Controllability Trap: A Governance Framework for Military AI AgentsWorld models → Latent dynamics models and model-based RL +1
  32. Phys4D: Fine-Grained Physics-Consistent 4D Modeling from Video DiffusionWorld models → Latent predictive world models +1
  33. Beyond Pixel Histories: World Models with Persistent 3D StateWorld models → Video-generation world models and simulators
  34. Minimax Optimal Strategy for Delayed Observations in Online Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  35. When Shallow Wins: Silent Failures and the Depth-Accuracy Paradox in Latent ReasoningLLM reasoning → Mathematical reasoning
  36. Biased Generalization in Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  37. Asymmetric Goal Drift in Coding Agents Under Value ConflictLLM agents and tool use → Software engineering coding agents
  38. [Re] FairDICE: A Fair Tradeoff in Multi-objective Offline RLOffline RL and imitation learning from data → Offline RL algorithms
  39. mHC-HSI: Clustering-Guided Hyper-Connection Mamba for Hyperspectral Image ClassificationState-space sequence models (S4, Mamba) → Hyperspectral image analysis with Mamba
  40. Parallel Test-Time Scaling with Multi-Sequence VerifiersLLM reasoning → Test-time compute and efficient thinking
  41. On Google's SynthID-Text LLM Watermarking System: Theoretical Analysis and Empirical ValidationLLM safety and security → Watermarking generated content and models
  42. Tracing Pharmacological Knowledge In Large Language ModelsMechanistic interpretability → Interpreting biomedical and science models
  43. Accelerating OpenPangu Inference on NPU via Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  44. LiteVLA-Edge: Quantized On-Device Multimodal Control for Embedded RoboticsVision-language-action models → Efficient VLA inference and adaptation
  45. MemSifter: Offloading LLM Memory Retrieval via Outcome-Driven Proxy ReasoningLLM reasoning → Reasoning for agents, planning and code
  46. CFG-Ctrl: Control-Based Classifier-Free Diffusion GuidanceDiffusion models → Diffusion foundations and sampling
  47. How to Peel with a Knife: Aligning Fine-Grained Manipulation with Human PreferenceLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  48. Beyond Language Modeling: An Exploration of Multimodal PretrainingMixture-of-experts → Multimodal MoE models
  49. Inherited Goal Drift: Contextual Pressure Can Undermine Agentic GoalsLLM agents and tool use → General LLM agent frameworks and benchmarks
  50. Speculative Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  51. Density-Guided Response Optimization: Community-Grounded Alignment via Implicit Acceptance SignalsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  52. COP-GEN: Latent Diffusion Transformer for Copernicus Earth Observation DataDiffusion models → Inverse problems and image restoration
  53. AI-for-Science Low-code Platform with Bayesian Adversarial Multi-Agent FrameworkLLM agents and tool use → General LLM agent frameworks and benchmarks
  54. Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool UseLLM reasoning → Reasoning for agents, planning and code +1
  55. Code2Math: Can Your Code Agent Effectively Evolve Math Problems Through Exploration?LLM agents and tool use → Educational agents and math problem solving
  56. Specificity-aware reinforcement learning for fine-grained open-world classificationDeep reinforcement learning methods → RL training of language and agent models
  57. Chain of World: World Model Thinking in Latent MotionWorld models → Embodied and robot world models +1
  58. BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?LLM agents and tool use → Software engineering coding agents
  59. MoD-DPO: Towards Mitigating Cross-modal Hallucinations in Omni LLMs using Modality Decoupled Preference OptimizationLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  60. Type-Aware Retrieval-Augmented Generation with Dependency Closure for Solver-Executable Industrial Optimization ModelingRetrieval-augmented generation → RAG pipeline design and evaluation
  61. FEAST: Retrieval-Augmented Multi-Hierarchical Food Classification for the FoodEx2 SystemRetrieval-augmented generation → Time series and agricultural RAG
  62. Saarthi for AGI: Towards Domain-Specific General Intelligence for Formal VerificationLLM agents and tool use → General LLM agent frameworks and benchmarks
  63. Less Noise, Same Certificate: Retain Sensitivity for UnlearningLLM safety and security → Machine unlearning
  64. Conditioned Activation Transport for T2I Safety SteeringMechanistic interpretability → Steering and probing for LLM safety
  65. Information Routing in Atomistic Foundation Models: How Task Alignment and Equivariance Shape Linear DisentanglementMechanistic interpretability → Interpreting biomedical and science models
  66. From Language to Action: Can LLM-Based Agents Be Used for Embodied Robot Cognition?LLM agents and tool use → Multimodal and embodied agents
  67. Agentic AI-based Coverage Closure for Formal VerificationLLM agents and tool use → Software engineering coding agents
  68. Edit in 2D, Verify in 3D: Reinforcement Learning for Multi-view Consistent Scene EditingDiffusion models → 3D, point cloud and scene generation +1
  69. APRES: An Agentic Paper Revision and Evaluation SystemLLM agents and tool use → Web, search, and research agents
  70. Deep Q-Learning-Based Gain Scheduling for Nonlinear Quadcopter DynamicsDeep reinforcement learning methods → RL for robot navigation and UAV control
  71. AWDiff: An a trous wavelet diffusion model for lung ultrasound image synthesisDiffusion models → Medical imaging and segmentation
  72. AI Space Physics: Constitutive boundary semantics for open AI institutionsLLM agents and tool use → Agent threats, guardrails and governance
  73. Beyond Task Completion: Revealing Corrupt Success in LLM Agents through Procedure-Aware EvaluationLLM agents and tool use → Software engineering coding agents
  74. MoECLIP: Patch-Specialized Experts for Zero-shot Anomaly DetectionMixture-of-experts → Vision mixture-of-experts
  75. TAO-Attack: Toward Advanced Optimization-Based Jailbreak Attacks for Large Language ModelsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  76. Beyond Factual Correctness: Mitigating Preference-Inconsistent Explanations in Explainable RecommendationLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
  77. RAPO: Expanding Exploration for LLM Agents via Retrieval-Augmented Policy OptimizationRetrieval-augmented generation → Agentic RAG, agents and memory +1
  78. TikZilla: Scaling Text-to-TikZ with High-Quality Data and Reinforcement LearningDeep reinforcement learning methods → RL with diffusion and flow models
  79. Reinforcement Learning with Symbolic Reward MachinesDeep reinforcement learning methods → Interpretable and logic-guided RL
  80. EduVQA: Towards Concept-Aware Assessment of Educational AI-Generated VideosMixture-of-experts → Vision mixture-of-experts
  81. V3DB: Audit-on-Demand Zero-Knowledge Proofs for Verifiable Vector Search over Committed SnapshotsRetrieval-augmented generation → Privacy and security of RAG
  82. PrivMedChat: End-to-End Differentially Private RLHF for Medical Dialogue SystemsLLM alignment / RLHF / preference optimisation → Medical LLM alignment
  83. Step-Level Sparse Autoencoder for Reasoning Process InterpretationLLM reasoning → Reasoning benchmarks and evaluation +1
  84. REGAL: A Registry-Driven Architecture for Deterministic Grounding of Agentic AI in Enterprise TelemetryLLM agents and tool use → Software engineering coding agents
  85. OrchMAS: Orchestrated Reasoning with Multi Collaborative Heterogeneous Scientific Expert Structured AgentsLLM reasoning → Reasoning for agents, planning and code +1
  86. SpatialText: A Pure-Text Cognitive Benchmark for Spatial Understanding in Large Language ModelsLLM reasoning → Spatial and embodied reasoning
  87. MaBERT:A Padding Safe Interleaved Transformer Mamba Hybrid Encoder for Efficient Extended Context Masked Language ModelingState-space sequence models (S4, Mamba) → Core SSM architectures for language
  88. Why Does RLAIF Work At All?LLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  89. Contextualized Privacy Defense for LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance
  90. DreamFlow: Local Navigation Beyond Observation via Conditional Flow Matching in the Latent SpaceDiffusion models → Diffusion and flow policies for robotics
  91. TagaVLM: Topology-Aware Global Action Reasoning for Vision-Language NavigationLLM reasoning → Spatial and embodied reasoning +1
  92. Architecting Trust in Artificial Epistemic AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  93. Semi-Supervised Few-Shot Adaptation of Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  94. Sparse autoencoders reveal organized biological knowledge but minimal regulatory logic in single-cell foundation models: a comparative atlas of Geneformer and scGPTMechanistic interpretability → Interpreting biomedical and science models
  95. TC-Pad'e: Trajectory-Consistent Pad'e Approximation for Diffusion AccelerationDiffusion models → Diffusion foundations and sampling
  96. ShipTraj-R1: Reinforcing Ship Trajectory Prediction in Large Language Models via Group Relative Policy OptimizationLLM reasoning → Reinforcement learning for reasoning
  97. Temporal Consistency Improves Generalization in Contextual Offline Meta Reinforcement LearningOffline RL and imitation learning from data → Decision transformers and sequence modeling
  98. On the Structural Limitations of Weight-Based Neural Adaptation and the Role of Reversible Behavioral LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  99. TRACE: Task-Adaptive Reasoning and Representation Learning for Universal Multimodal RetrievalLLM reasoning → Multimodal reasoning
  100. Interpretable Motion-Attentive Maps: Spatio-Temporally Localizing Concepts in Video Diffusion TransformersDiffusion models → Video generation
All 433
  1. Learning to Generate and Extract: A Multi-Agent Collaboration Framework For Zero-shot Document-level Event Arguments ExtractionLLM agents and tool use → General LLM agent frameworks and benchmarks
  2. SAE as a Crystal Ball: Interpretable Features Predict Cross-domain Transferability of LLMs without TrainingMechanistic interpretability → SAE features and their applications
  3. Intrinsic Geometry-Appearance Consistency Optimization for Sparse-View Gaussian SplattingDiffusion models → 3D, point cloud and scene generation
  4. LLandMark: A Multi-Agent Framework for Landmark-Aware Multimodal Interactive Video RetrievalLLM agents and tool use → Multimodal and embodied agents
  5. SemanticDialect: Semantic-Aware Mixed-Format Quantization for Video Diffusion TransformersDiffusion models → Diffusion foundations and sampling
  6. SIGMark: Scalable In-Generation Watermark with Blind Extraction for Video DiffusionDiffusion models → Robustness, privacy and adversarial aspects +1
  7. Think-as-You-See: Streaming Chain-of-Thought Reasoning for Large Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
  8. Nodes Are Early, Edges Are Late: Probing Diagram Representations in Large Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  9. Learning in Markov Decision Processes with Exogenous DynamicsDeep reinforcement learning methods → RL theory and sample complexity
  10. LLM-based Argument Mining meets Argumentation and Description Logics: a Unified Framework for Reasoning about DebatesLLM reasoning → Reasoning for agents, planning and code
  11. Toward Early Quality Assessment of Text-to-Image Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  12. Structure-Aware Text Recognition for Ancient Greek Critical EditionsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  13. Guideline-Grounded Evidence Accumulation for High-Stakes Agent VerificationLLM agents and tool use → Medical and scientific domain agents
  14. VSearcher: Long-Horizon Multimodal Search Agent via Reinforcement LearningLLM agents and tool use → Multimodal and embodied agents +1
  15. OCR or Not? Rethinking Document Information Extraction in the MLLMs Era with Real-World Large-Scale DatasetsLLM reasoning → Multimodal reasoning +1
  16. Agentified Assessment of Logical Reasoning AgentsLLM reasoning → Reasoning benchmarks and evaluation
  17. Rethinking Code Similarity for Automated Algorithm Design with LLMsLLM reasoning → Reasoning for agents, planning and code
  18. Generative adversarial imitation learning for robot swarms: Learning from human demonstrations and trained policiesOffline RL and imitation learning from data → Imitation learning methods
  19. Agentic Self-Evolutionary Replanning for Embodied NavigationLLM agents and tool use → Multimodal and embodied agents
  20. EvoSkill: Automated Skill Discovery for Multi-Agent SystemsLLM agents and tool use → Agent skill learning and evolution
  21. Next Embedding Prediction Makes World Models StrongerWorld models → Latent dynamics models and model-based RL +1
  22. Efficient Self-Evaluation for Diffusion Language Models via Sequence RegenerationDiffusion models → Discrete and text diffusion
  23. Seeing Clearly without Training: Mitigating Hallucinations in Multimodal LLMs for Remote SensingMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  24. MultiShadow: Multi-Object Shadow Generation for Image Compositing via Diffusion ModelDiffusion models → 3D, point cloud and scene generation
  25. Practical FP4 Training for Large-Scale MoE Models on Hopper GPUsMixture-of-experts → Efficient MoE training and inference systems
  26. From "What" to "How": Constrained Reasoning for Autoregressive Image GenerationLLM reasoning → Multimodal reasoning
  27. A Natural Language Agentic Approach to Study Affective PolarizationLLM agents and tool use → Social simulation and multi-agent debate
  28. MiM-DiT: MoE in MoE with Diffusion Transformers for All-in-One Image RestorationDiffusion models → Inverse problems and image restoration +1
  29. Graph-GRPO: Stabilizing Multi-Agent Topology Learning via Group Relative Policy OptimizationLLM reasoning → Reinforcement learning for reasoning +1
  30. ShareVerse: Multi-Agent Consistent Video Generation for Shared World ModelingWorld models → Video-generation world models and simulators
  31. ReCo-Diff: Residual-Conditioned Deterministic Sampling for Cold Diffusion in Sparse-View CTDiffusion models → Medical imaging and segmentation
  32. Retrieval-Augmented Robots via Retrieve-Reason-ActRetrieval-augmented generation → Agentic RAG, agents and memory
  33. VisionCreator: A Native Visual-Generation Agentic Model with Understanding, Thinking, Planning and CreationLLM agents and tool use → Multimodal and embodied agents
  34. ITLC at SemEval-2026 Task 11: Normalization and Deterministic Parsing for Formal Reasoning in LLMsLLM reasoning → Reasoning benchmarks and evaluation
  35. From Shallow to Deep: Pinning Semantic Intent via Causal GRPOLLM reasoning → Reasoning for agents, planning and code +1
  36. Evaluating Cross-Modal Reasoning Ability and Problem Characteristics with Multimodal Item Response TheoryLLM reasoning → Multimodal reasoning +1
  37. Real-Time Generation of Game Video Commentary with Multimodal LLMs: Pause-Aware Decoding ApproachesMultimodal LLMs / vision-language models → Video understanding with MLLMs
  38. Improving Diffusion Planners by Self-Supervised Action Gating with EnergiesOffline RL and imitation learning from data → Diffusion and flow policies for offline RL +1
  39. Compositional Visual Planning via Inference-Time Diffusion ScalingDiffusion models → Diffusion and flow policies for robotics
  40. StitchCUDA: An Automated Multi-Agents End-to-End GPU Programing Framework with Rubric-based Agentic Reinforcement LearningLLM agents and tool use → Software engineering coding agents
  41. SaFeR-ToolKit: Structured Reasoning via Virtual Tool Calling for Multimodal SafetyLLM reasoning → Reasoning for agents, planning and code +3
  42. Robust Heterogeneous Analog-Digital Computing for Mixture-of-Experts Models with Theoretical Generalization GuaranteesMixture-of-experts → MoE theory and gating functions
  43. Cross-Family Speculative Prefill: Training-Free Long-Context Compression with Small Draft ModelsLLM agents and tool use → Agent memory systems +1
  44. MASPOB: Bandit-Based Prompt Optimization for Multi-Agent Systems with Graph Neural NetworksLLM agents and tool use → General LLM agent frameworks and benchmarks
  45. See and Remember: A Multimodal Agent for Web TraversalLLM agents and tool use → Web, search, and research agents
  46. Uni-Skill: Building Self-Evolving Skill Repository for Generalizable Robotic ManipulationSynthetic data and self-improvement for LLMs → Self-evolving LLM agents
  47. Direct Reward Fine-Tuning on Poses for Single Image to 3D Human in the WildDiffusion models → 3D, point cloud and scene generation
  48. His2Trans: A Knowledge-Guided Agentic Framework for Project-Level C-to-Rust MigrationLLM agents and tool use → Software engineering coding agents
  49. Think, But Don't Overthink: Reproducing Recursive Language ModelsLLM reasoning → Test-time compute and efficient thinking
  50. Real-Time Generative Policy via Langevin-Guided Flow Matching for Autonomous DrivingDiffusion models → Diffusion and flow policies for robotics +2
  51. Heterogeneous Agent Collaborative Reinforcement LearningLLM agents and tool use → Reinforcement learning for LLM agents +1
  52. AgentAssay: Token-Efficient Regression Testing for Non-Deterministic AI Agent WorkflowsLLM agents and tool use → Software engineering coding agents
  53. SUN: Shared Use of Next-token Prediction for Efficient Multi-LLM Disaggregated ServingEfficient LLM inference and serving → Serving systems and request scheduling
  54. Extending the Formalism and Theoretical Foundations of Cryptography to AILLM agents and tool use → Agent threats, guardrails and governance
  55. ExpGuard: LLM Content Moderation in Specialized DomainsLLM safety and security → Safety alignment, refusal and guardrails
  56. LiveAgentBench: Comprehensive Benchmarking of Agentic Systems Across 104 Real-World ChallengesLLM agents and tool use → General LLM agent frameworks and benchmarks
  57. Towards Parameter-Free Temporal Difference LearningDeep reinforcement learning methods → RL theory and sample complexity
  58. Wasserstein Proximal Policy GradientDeep reinforcement learning methods → RL theory and sample complexity
  59. CAWM-Mamba: A unified model for infrared-visible image fusion and compound adverse weather restorationState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  60. CAPT: Confusion-Aware Prompt Tuning for Reducing Vision-Language MisalignmentMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  61. Through the Lens of Contrast: Self-Improving Visual Reasoning in VLMsLLM reasoning → Multimodal reasoning +1
  62. Generalizable Knowledge Distillation from Vision Foundation Models for Semantic SegmentationKnowledge distillation → Detection and dense prediction distillation
  63. CoDAR: Continuous Diffusion Language Models are More Powerful Than You ThinkLLM reasoning → Diffusion reasoning and test-time scaling +1
  64. On Discriminative vs. Generative classifiers: Rethinking MLLMs for Action UnderstandingLLM reasoning → Spatial and embodied reasoning +1
  65. Orality: A Semantic Canvas for Externalizing and Clarifying Thoughts with SpeechLLM reasoning → Audio-language model reasoning
  66. AnchorDrive: LLM Scenario Rollout with Anchor-Guided Diffusion Regeneration for Safety-Critical Scenario GenerationDiffusion models → Diffusion and flow policies for robotics
  67. Geometry-Aware Attention Guidance for Diffusion Models via Modern Hopfield DynamicsDiffusion models → Diffusion foundations and sampling
  68. LLM-MLFFN: Multi-Level Autonomous Driving Behavior Feature Fusion via Large Language ModelEnd-to-end autonomous driving → Large language models for driving
  69. Agentic Mixed-Source Multi-Modal Misinformation Detection with Adaptive Test-Time ScalingLLM reasoning → Multimodal reasoning +2
  70. Learning Object-Centric Spatial Reasoning for Sequential Manipulation in Cluttered EnvironmentsLLM reasoning → Spatial and embodied reasoning
  71. ParEVO: Synthesizing Code for Irregular Data: High-Performance Parallelism through Agentic EvolutionLLM agents and tool use → Software engineering coding agents
  72. NeuroProlog: Multi-Task Fine-Tuning for Neurosymbolic Mathematical Reasoning via the Cocktail EffectLLM reasoning → Reasoning benchmarks and evaluation
  73. What Capable Agents Must Know: Selection Theorems for Robust Decision-Making under UncertaintyWorld models → World models for language agents
  74. MUSE: A Run-Centric Platform for Multimodal Unified Safety Evaluation of Large Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  75. PRISM: Pushing the Frontier of Deep Think via Process Reward Model-Guided InferenceLLM reasoning → Reinforcement learning for reasoning +1
  76. Deep Interest Mining for Intent-Enriched Semantic IDs in Multimodal Generative Recommendation
  77. The Tool-Overuse Illusion: Why Does LLM Prefer External Tools over Internal Knowledge?
  78. Acoustic and Facial Markers of Perceived Conversational Success in Spontaneous Speech
  79. An Initial Exploration of Contrastive Prompt Tuning to Generate Energy-Efficient Code
  80. MERIT: Memory-Enhanced Retrieval for Interpretable Knowledge Tracing
  81. EEG-Based Brain-LLM Interface for Human Preference Aligned Generation
  82. EEG-SeeGraph: Interpreting functional connectivity disruptions in dementias via sparse-explanatory dynamic EEG-graph learning
  83. Tokenization Tradeoffs in Structured EHR Foundation Models
  84. Task Expansion and Cross Refinement for Open-World Conditional Modeling
  85. Suppressing Domain-Specific Hallucination in Construction LLMs: A Knowledge Graph Foundation for GraphRAG and QLoRA on River and Sediment Control Technical Standards
  86. Benchmarking Compact VLMs for Clip-Level Surveillance Anomaly Detection Under Weak Supervision
  87. Chart Deep Research in LVLMs via Parallel Relative Policy Optimization
  88. XAI and Few-shot-based Hybrid Classification Model for Plant Leaf Disease Prognosis
  89. GNN For Muon Particle Momentum estimation
  90. AutoFigure-Edit: Generating Editable Scientific Illustration
  91. Unmixing ATR-μFTIR spectroscopic images of cross-sections of historical oil paintings
  92. ERP-RiskBench: Leakage-Safe Ensemble Learning for Financial Risk
  93. calibfusion: Transformer-Based Differentiable Calibration for Radar-Camera Fusion Detection in Water-Surface Environments
  94. MAD-SmaAt-GNet: A Multimodal Advection-Guided Neural Network for Precipitation Nowcasting
  95. VSPrefill: Vertical-Slash Sparse Attention with Lightweight Indexing for Long-Context Prefilling
  96. Learning Unified Distance Metric for Heterogeneous Attribute Data Clustering
  97. Capability Thresholds and Manufacturing Topology: How Embodied Intelligence Triggers Phase Transitions in Economic Geography
  98. SENTINEL: Stagewise Integrity Verification for Pipeline Parallel Decentralized Training
  99. Controllable Generative Sandbox for Causal Inference
  100. Belief-Sim: Towards Belief-Driven Simulation of Demographic Misinformation Susceptibility
  101. Hazard-Aware Traffic Scene Graph Generation
  102. ByteFlow: Language Modeling through Adaptive Byte Compression without a Tokenizer
  103. An Effective Data Augmentation Method by Asking Questions about Scene Text Images
  104. Spectrum Shortage for Radio Sensing? Leveraging Ambient 5G Signals for Human Activity Detection
  105. Transport Clustering: Solving Low-Rank Optimal Transport via Clustering
  106. From Local Matches to Global Masks: Template-Guided Instance Detection and Segmentation in Open-World Scenes
  107. Confidence-aware Monocular Depth Estimation for Minimally Invasive Surgery
  108. Modeling Cross-vision Synergy for Unified Large Vision Model
  109. Real-time tightly coupled GNSS and IMU integration via Factor Graph Optimization
  110. Real-time loosely coupled GNSS and IMU integration via Factor Graph Optimization
  111. Tucano 2 Cool: Better Open Source LLMs for Portuguese
  112. Trade-offs in Ensembling, Merging and Routing Among Parameter-Efficient Experts
  113. Role-Aware Conditional Inference for Spatiotemporal Ecosystem Carbon Flux Prediction
  114. Directional Neural Collapse Explains Few-Shot Transfer in Self-Supervised Learning
  115. mlx-snn: Spiking Neural Networks on Apple Silicon via MLX
  116. Multi-Agent Influence Diagrams to Hybrid Threat Modeling
  117. Test-Time Meta-Adaptation with Self-Synthesis
  118. MMAI Gym for Science: Training Liquid Foundation Models for Drug Discovery
  119. Baseline Performance of AI Tools in Classifying Cognitive Demand of Mathematical Tasks
  120. Orbital Transformers for Predicting Wavefunctions in Time-Dependent Density Functional Theory
  121. A theoretical model of dynamical grammatical gender shifting based on set-valued set function
  122. Raising Bars, Not Parameters: LilMoo Compact Language Model for Hindi
  123. Solving adversarial examples requires solving exponential misalignment
  124. PhyPrompt: RL-based Prompt Refinement for Physically Plausible Text-to-Video Generation
  125. Geographically-Weighted Weakly Supervised Bayesian High-Resolution Transformer for 200m Resolution Pan-Arctic Sea Ice Concentration Mapping and Uncertainty Estimation using Sentinel-1, RCM, and AMSR2 Data
  126. Quantifying Ranking Instability Across Evaluation Protocol Axes in Gene Regulatory Network Benchmarking
  127. When Small Variations Become Big Failures: Reliability Challenges in Compute-in-Memory Neural Accelerators
  128. Optimal trajectory-guided stochastic co-optimization for e-fuel system design and real-time operation
  129. Graph Hopfield Networks: Energy-Based Node Classification with Associative Memory
  130. Half the Nonlinearity Is Wasted: Measuring and Reallocating the Transformer's MLP Budget
  131. Impact of Localization Errors on Label Quality for Online HD Map Construction
  132. Proact-VL: A Proactive VideoLLM for Real-Time AI Companions
  133. Beyond Accuracy: Evaluating Visual Grounding In Multimodal Medical Reasoning
  134. Farther the Shift, Sparser the Representation: Analyzing OOD Mechanisms in LLMs
  135. PRIVATEEDIT: A Privacy-Preserving Pipeline for Face-Centric Generative Image Editing
  136. Scalable Contrastive Causal Discovery under Unknown Soft Interventions
  137. A Short Note on a Variant of the Squint Algorithm
  138. Surprisal-R'enyi Free Energy
  139. Heterogeneous Time Constants Improve Stability in Equilibrium Propagation
  140. Beyond Cross-Validation: Adaptive Parameter Selection for Kernel-Based Gradient Descents
  141. Zero-Knowledge Federated Learning with Lattice-Based Hybrid Encryption for Quantum-Resilient Medical AI
  142. Multi-Agent-Based Simulation of Archaeological Mobility in Uneven Landscapes
  143. Towards Improved Sentence Representations using Token Graphs
  144. RADAR: Learning to Route with Asymmetry-aware DistAnce Representations
  145. Learning Order Forest for Qualitative-Attribute Data Clustering
  146. AOI: Turning Failed Trajectories into Training Signals for Autonomous Cloud Diagnosis
  147. Utonia: Toward One Encoder for All Point Clouds
  148. MIBURI: Towards Expressive Interactive Gesture Synthesis
  149. ULTRA: Unified Multimodal Control for Autonomous Humanoid Whole-Body Loco-Manipulation
  150. Tether: Autonomous Functional Play with Correspondence-Driven Trajectory Warping
  151. Learning Demographic-Conditioned Mobility Trajectories with Aggregate Supervision
  152. Gravity Falls: A Comparative Analysis of Domain-Generation Algorithm (DGA) Detection Methods for Mobile Device Spearphishing
  153. LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory
  154. DuoMo: Dual Motion Diffusion for World-Space Human Reconstruction
  155. Physics-informed post-processing of stabilized finite element solutions for transient convection-dominated problems
  156. Valet: A Standardized Testbed of Traditional Imperfect-Information Card Games
  157. Using Learning Progressions to Guide AI Feedback for Science Learning
  158. UniG2U-Bench: Do Unified Models Advance Multimodal Understanding?
  159. On Geometry Regularization in Autoencoder Reduced-Order Models with Latent Neural ODE Dynamics
  160. The elbow statistic: Multiscale clustering statistical significance
  161. Guiding Sparse Neural Networks with Neurobiological Principles to Elicit Biologically Plausible Representations
  162. SynthCharge: An Electric Vehicle Routing Instance Generator with Feasibility Screening to Enable Learning-Based Optimization and Benchmarking
  163. Inverse Reconstruction of Shock Time Series from Shock Response Spectrum Curves using Machine Learning
  164. Coalgebras for categorical deep learning: Representability and universal approximation
  165. Adaptive Methods Are Preferable in High Privacy Settings: An SDE Perspective
  166. Stabilized Adaptive Loss and Residual-Based Collocation for Physics-Informed Neural Networks
  167. NeuroSkill(tm): Proactive Real-Time Agentic System Capable of Modeling Human State of Mind
  168. Shape Derivative-Informed Neural Operators with Application to Risk-Averse Shape Optimization
  169. I-CAM-UV: Integrating Causal Graphs over Non-Identical Variable Sets Using Causal Additive Models with Unobserved Variables
  170. Understanding and Mitigating Dataset Corruption in LLM Steering
  171. No Memorization, No Detection: Output Distribution-Based Contamination Detection in Small Language Models
  172. ACE-Brain-0: Spatial Intelligence as a Shared Scaffold for Universal Embodiments
  173. Infinite dimensional generative sensing
  174. A Covering Framework for Offline POMDPs Learning using Belief Space Metric
  175. Expectation and Acoustic Neural Network Representations Enhance Music Identification from Brain Activity
  176. Scalable Posterior Uncertainty for Flexible Density-Based Clustering
  177. ProSMA-UNet: Decoder Conditioning for Proximal-Sparse Skip Feature Selection
  178. Neuro-Symbolic Artificial Intelligence: A Task-Directed Survey in the Black-Box Models Era
  179. Kling-MotionControl Technical Report
  180. An Investigation Into Various Approaches For Bengali Long-Form Speech Transcription and Bengali Speaker Diarization
  181. Channel-Adaptive Edge AI: Maximizing Inference Throughput by Adapting Computational Complexity to Channel States
  182. How to Model AI Agents as Personas?: Applying the Persona Ecosystem Playground to 41,300 Posts on Moltbook for Behavioral Insights
  183. Torus embeddings
  184. UniSkill: A Dataset for Matching University Curricula to Professional Competencies
  185. Joint Training Across Multiple Activation Sparsity Regimes
  186. From Complex Dynamics to DynFormer: Rethinking Transformers for PDEs
  187. Evaluating Performance Drift from Model Switching in Multi-Turn LLM Systems
  188. Multi-Scale Adaptive Neighborhood Awareness Transformer For Graph Fraud Detection
  189. Why Adam Can Beat SGD: Second-Moment Normalization Yields Sharper Tails
  190. Odin: Multi-Signal Graph Intelligence for Autonomous Discovery in Knowledge Graphs
  191. Interpreting Speaker Characteristics in the Dimensions of Self-Supervised Speech Features
  192. Compact Prompting in Instruction-tuned LLMs for Joint Argumentative Component Detection
  193. Proactive Guiding Strategy for Item-side Fairness in Interactive Recommendation
  194. On the Expressive Power of Transformers for Maxout Networks and Continuous Piecewise Linear Functions
  195. Safe and Robust Domains of Attraction for Discrete-Time Systems: A Set-Based Characterization and Certifiable Neural Network Estimation
  196. TinyIceNet: Low-Power SAR Sea Ice Segmentation for On-Board FPGA Inference
  197. Design Generative AI for Practitioners: Exploring Interaction Approaches Aligned with Creative Practice
  198. From Reachability to Learnability: Geometric Design Principles for Quantum Neural Networks
  199. Incremental Graph Construction Enables Robust Spectral Clustering of Texts
  200. TrustMH-Bench: A Comprehensive Benchmark for Evaluating the Trustworthiness of Large Language Models in Mental Health
  201. QFlowNet: Fast, Diverse, and Efficient Unitary Synthesis with Generative Flow Networks
  202. IoUCert: Robustness Verification for Anchor-based Object Detectors
  203. cPNN: Continuous Progressive Neural Networks for Evolving Streaming Time Series
  204. Generalized Bayes for Causal Inference
  205. BRIGHT: A Collaborative Generalist-Specialist Foundation Model for Breast Pathology
  206. Any Resolution Any Geometry: From Multi-View To Multi-Patch
  207. MA-CoNav: A Master-Slave Multi-Agent Framework with Hierarchical Collaboration and Dual-Level Reflection for Long-Horizon Embodied VLN
  208. SEHFS: Structural Entropy-Guided High-Order Correlation Learning for Multi-View Multi-Label Feature Selection
  209. Breaking the Prototype Bias Loop: Confidence-Aware Federated Contrastive Learning for Highly Imbalanced Clients
  210. VIRGi: View-dependent Instant Recoloring of 3D Gaussians Splats
  211. The Dresden Dataset for 4D Reconstruction of Non-Rigid Abdominal Surgical Scenes
  212. Variance reduction in lattice QCD observables via normalizing flows
  213. Spatial Autoregressive Modeling of DINOv3 Embeddings for Unsupervised Anomaly Detection
  214. On the Topology of Neural Network Superlevel Sets
  215. LAGO: A Local-Global Optimization Framework Combining Trust Region Methods and Bayesian Optimization
  216. Integrating Homomorphic Encryption and Synthetic Data in FL for Privacy and Learning Quality
  217. Improving Anomaly Detection with Foundation-Model Synthesis and Wavelet-Domain Attention
  218. Delegation and Verification Under AI
  219. Layer-wise QUBO-Based Training of CNN Classifiers for Quantum Annealing
  220. Leveraging Label Proportion Prior for Class-Imbalanced Semi-Supervised Learning
  221. CGL: Advancing Continual GUI Learning via Reinforcement Fine-Tuning
  222. Path Dependence under Adaptive AI Delegation
  223. SEALing the Gap: A Reference Framework for LLM Inference Carbon Estimation via Multi-Benchmark Driven Embodiment
  224. Enhancing Physics-Informed Neural Networks with Domain-aware Fourier Features: Towards Improved Performance and Interpretable Results
  225. ACE-Merging: Data-Free Model Merging with Adaptive Covariance Estimation
  226. Beyond One-Size-Fits-All: Adaptive Subgraph Denoising for Zero-Shot Graph Learning with Large Language Models
  227. Bias and Fairness in Self-Supervised Acoustic Representations for Cognitive Impairment Detection
  228. GloPath: An Entity-Centric Foundation Model for Glomerular Lesion Assessment and Clinicopathological Insights
  229. HDINO: A Concise and Efficient Open-Vocabulary Detector
  230. Eliciting Numerical Predictive Distributions of LLMs Without Autoregression
  231. Articulation in Motion: Prior-free Part Mobility Analysis for Articulated Objects By Dynamic-Static Disentanglement
  232. Harmonic Beltrami Signature Network: a Shape Prior Module in Deep Learning Framework
  233. Towards Accurate and Interpretable Time-series Forecasting: A Polynomial Learning Approach
  234. Distributed Dynamic Invariant Causal Prediction in Environmental Time Series
  235. Embedding interpretable ℓ1-regression into neural networks for uncovering temporal structure in cell imaging
  236. ProGIC: Progressive and Lightweight Generative Image Compression with Residual Vector Quantization
  237. 3D-DRES: Detailed 3D Referring Expression Segmentation
  238. Generalized non-exponential Gaussian splatting
  239. StegaFFD: Privacy-Preserving Face Forgery Detection via Fine-Grained Steganographic Domain Lifting
  240. Eval4Sim: An Evaluation Framework for Persona Simulation
  241. Retrievit: In-context Retrieval Capabilities of Transformers, State Space Models, and Hybrid Architectures
  242. .tmu: A Low-Entropy Tree-Structured Representation for LLM-Assisted Scientific Writing
  243. Multimodal-Prior-Guided Importance Sampling for Hierarchical Gaussian Splatting in Sparse-View Novel View Synthesis
  244. The Distribution of Phoneme Frequencies across the World's Languages: Macroscopic and Microscopic Information-Theoretic Models
  245. CoFL: Continuous Flow Fields for Language-Conditioned Navigation
  246. Learning Memory-Enhanced Improvement Heuristics for Flexible Job Shop Scheduling
  247. SPARC: Spatial-Aware Path Planning via Attentive Agent Communication
  248. Scale-invariant Gaussian derivative residual networks
  249. A Browser-based Open Source Assistant for Multimodal Content Verification
  250. Adapting Time Series Foundation Models through Data Mixtures
  251. Faster, Cheaper, More Accurate: Specialised Knowledge Tracing Models Outperform LLMs
  252. BrandFusion: A Multi-Agent Framework for Seamless Brand Integration in Text-to-Video Generation
  253. ChemFlow:A Hierarchical Neural Network for Multiscale Representation Learning in Chemical Mixtures
  254. Lattice-based Deep Neural Networks: Regularity and Tailored Regularization
  255. The Price of Robustness: Stable Classifiers Need Overparameterization
  256. ScribeTokens: Fixed-Vocabulary Tokenization of Digital Ink
  257. NOVA: Sparse Control, Dense Synthesis for Pair-Free Video Editing
  258. R3GW: Relightable 3D Gaussians for Outdoor Scenes in the Wild
  259. An Interpretable, Controllable Time-Varying IIR Denoiser for On-Device Assistive Hearing
  260. From Heuristic Selection to Automated Algorithm Design: LLMs Benefit from Strong Priors
  261. Designing UNICORN: a Unified Benchmark for Imaging in Computational Pathology, Radiology, and Natural Language
  262. HiLoRA: Hierarchical Low-Rank Adaptation for Personalized Federated Learning
  263. Scores Know Bobs Voice: Speaker Impersonation Attack
  264. From Solver to Tutor: Evaluating the Pedagogical Intelligence of LLMs with KMP-Bench
  265. ITO: Multi-View Alignment and Training-Time Fusion for Image-Text Pretraining
  266. Rethinking Time Series Domain Generalization via Structure-Stratified Calibration
  267. Deep learning-guided evolutionary optimization for protein design
  268. iGVLM: Dynamic Instruction-Guided Vision Encoding for Question-Aware Multimodal Understanding
  269. Enhancing User Throughput in Multi-panel mmWave Radio Access Networks for Beam-based MU-MIMO Using a DRL Method
  270. The power of small initialization in noisy low-tubal-rank tensor recovery
  271. Gated Differential Linear Attention: A Linear-Time Decoder for High-Fidelity Medical Segmentation
  272. Cross-view geo-localization, Image retrieval, Multiscale geometric modeling, Frequency domain enhancement
  273. Single Microphone Own Voice Detection based on Simulated Transfer Functions for Hearing Aids
  274. Tensor Decomposition Structure Search Framework from an Interaction Perspective
  275. An Empirical Analysis of Calibration and Selective Prediction in Multimodal Clinical Condition Classification
  276. Sensory-Aware Sequential Recommendation via Review-Distilled Representations
  277. Intelligent Pathological Diagnosis of Gestational Trophoblastic Diseases via Visual-Language Deep Learning Model
  278. FinTexTS: Financial Text-Paired Time-Series Dataset via Semantic-Based and Multi-Level Pairing
  279. Neural quantum support vector data description for one-class classification
  280. Addressing Missing and Noisy Modalities in One Solution: Unified Modality-Quality Framework for Low-quality Multimodal Data
  281. FiDeSR: High-Fidelity and Detail-Preserving One-Step Diffusion Super-Resolution
  282. HateMirage: An Explainable Multi-Dimensional Dataset for Decoding Faux Hate and Subtle Online Abuse
  283. LLMs for High-Frequency Decision-Making: Normalized Action Reward-Guided Consistency Policy Optimization
  284. Causal Discovery Should Embrace the Wisdom of the Crowd
  285. Exact Functional ANOVA Decomposition for Categorical Inputs Models
  286. SorryDB: Can AI Provers Complete Real-World Lean Theorems?
  287. Unifying Contrastive and Generative Objectives for Visual Understanding and Text-to-Image Generation
  288. OmniFashion: Towards Generalist Fashion Intelligence via Multi-Task Vision-Language Learning
  289. AlphaFree: Recommendation Free from Users, IDs, and GNNs
  290. HomeAdam: Adam and AdamW Algorithms Sometimes Go Home to Obtain Better Provable Generalization
  291. SEP-YOLO: Fourier-Domain Feature Representation for Transparent Object Instance Segmentation
  292. Credibility Governance: A Social Mechanism for Collective Self-Correction under Weak Truth Signals
  293. Convex and Non-convex Federated Learning with Stale Stochastic Gradients: Diminishing Step Size is All You Need
  294. The Vienna 4G/5G Drive-Test Dataset
  295. Towards an Incremental Unified Multimodal Anomaly Detection: Augmenting Multimodal Denoising From an Information Bottleneck Perspective
  296. Post Hoc Extraction of Pareto Fronts for Continuous Control
  297. Implicit Bias in Deep Linear Discriminant Analysis
  298. Same Error, Different Function: The Optimizer as an Implicit Prior in Financial Time Series
  299. Mind the Way You Select Negative Texts: Pursuing the Distance Consistency in OOD Detection with VLMs
  300. Detecting Structural Heart Disease from Electrocardiograms via a Generalized Additive Model of Interpretable Foundation-Model Predictors
  301. VLMFusionOcc3D: VLM Assisted Multi-Modal 3D Semantic Occupancy Prediction
  302. Combinatorial Sparse PCA Beyond the Spiked Identity Model
  303. Synthetic-Child: An AIGC-Based Synthetic Data Pipeline for Privacy-Preserving Child Posture Estimation
  304. GPUTOK: GPU Accelerated Byte Level BPE Tokenization
  305. Low-Degree Method Fails to Predict Robust Subspace Recovery
  306. Maximizing Generalization: The Effect of Different Augmentation Techniques on Lightweight Vision Transformer for Bengali Character Classification
  307. Neural Electromagnetic Fields for High-Resolution Material Parameter Reconstruction
  308. ATD: Improved Transformer with Adaptive Token Dictionary for Image Restoration
  309. Joint Optimization of Model Partitioning and Resource Allocation for Anti-Jamming Collaborative Inference Systems
  310. How Controllable Are Large Language Models? A Unified Evaluation across Behavioral Granularities
  311. Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels
  312. FlashEvaluator: Expanding Search Space with Parallel Sequence-Level Evaluation
  313. EdgeFLow: Serverless Federated Learning via Sequential Model Migration in Edge Networks
  314. SOLAR: SVD-Optimized Lifelong Attention for Recommendation
  315. Give me scissors: Collision-Free Dual-Arm Surgical Assistive Robot for Instrument Delivery
  316. SemGS: Feed-Forward Semantic 3D Gaussian Splatting from Sparse Views for Generalizable Scene Understanding
  317. ForestPersons: A Large-Scale Dataset for Under-Canopy Missing Person Detection
  318. A Neuropsychologically Grounded Evaluation of LLM Cognitive Abilities
  319. Functional Properties of the Focal-Entropy
  320. EIMC: Efficient Instance-aware Multi-modal Collaborative Perception
  321. Thermodynamic Regulation of Finite-Time Gibbs Training in Energy-Based Models: A Restricted Boltzmann Machine Study
  322. NeighborMAE: Exploiting Spatial Dependencies between Neighboring Earth Observation Images in Masked Autoencoders Pretraining
  323. Beyond Anatomy: Explainable ASD Classification from rs-fMRI via Functional Parcellation and Graph Attention Networks
  324. Human-Certified Module Repositories for the AI Age
  325. SGMA: Semantic-Guided Modality-Aware Segmentation for Remote Sensing with Incomplete Multimodal Data
  326. Biomechanically Accurate Gait Analysis: A 3d Human Reconstruction Framework for Markerless Estimation of Gait Parameters
  327. WTHaar-Net: a Hybrid Quantum-Classical Approach
  328. Revealing Positive and Negative Role Models to Help People Make Good Decisions
  329. Learning-Augmented Moment Estimation on Time-Decay Models
  330. Geometric structures and deviations on James' symmetric positive-definite matrix bicone domain
  331. ModalPatch: A Plug-and-Play Module for Robust Multi-Modal 3D Object Detection under Modality Drop
  332. Optimizing Orbital Parameters of Satellites for a Global Quantum Network
  333. E2E-GNet: An End-to-End Skeleton-based Geometric Deep Neural Network for Human Motion Recognition