mlsanityData to 14 Oct 2026

Papers

New on arXiv

Fri 15 May 2026

474 papers

  1. Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  2. AgentKVShift: Efficient KV Cache Reuse for Agentic Memory SystemsLLM agents and tool use → Software engineering coding agents +1
  3. CAMeR: Keyword-Gated Hybrid Activation for Adaptive Memory Retention in LLM AgentsLLM agents and tool use → Agent memory systems
  4. Probabilistic Concept-Aware Steering for Trustworthy LLM InferenceMechanistic interpretability → Activation steering methods
  5. S2T-RLHF: Hierarchical Credit Assignment for Stable Preference-Based RLHFLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  6. Accurate and Efficient Long-Term Memory for LLM AgentsLLM reasoning → Reasoning for agents, planning and code +1
  7. Optimization-as-a-Service via Multi-Agent Large Language Model for Radio Access NetworksLLM agents and tool use → Agentic AI for wireless networks
  8. An Agentic Retrieval Framework for Autonomous Context-Aware Data Quality AssessmentLLM agents and tool use → Web, search, and research agents
  9. Ligand-Conditioned Discrete Diffusion for Protein Sequence-Structure Co-DesignDiffusion models → Flow matching, time series and science
  10. Distributional Energy-Based Models for Uncertainty-Aware Structured LLM ReasoningLLM reasoning → Test-time compute and efficient thinking
  11. SAGE: Shaping Anchors for Guided Exploration in RLVR of LLMsLLM reasoning → Reinforcement learning for reasoning
  12. GeoWorld-VLM: Geometry from World Models for Vision-Language ModelsWorld models → World models for language agents +1
  13. Face inpainting with Identity Preserving Latent Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  14. EfficientTDMPC: Improved MPC Objectives for Sample-Efficient Continuous ControlDeep reinforcement learning methods → Deep RL algorithms and representations
  15. UB-SMoE: Universally Balanced Sparse Mixture-of-Experts for Resource-adaptive Federated Fine-tuning of Foundation ModelsMixture-of-experts → Federated mixture-of-experts
  16. Scalable Knowledge Editing for Mixture-of-Experts LLMs via Tensor-Structured UpdatesMixture-of-experts → MoE large language models
  17. LinAlg-Bench: A Forensic Benchmark Revealing Structural Failure Modes in LLM Mathematical ReasoningLLM reasoning → Mathematical reasoning
  18. Right Predictions, Misleading Explanations: On the Vulnerability of Vision-Language Model ExplanationsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  19. AtlasVid: Efficient Ultra-High-Resolution Long Video Generation via Decoupled Global-Local ModelingDiffusion models → Video generation
  20. Statistical Unlearning of Distributions: A Hypothesis Testing ApproachLLM safety and security → Machine unlearning
  21. TTE-Flash: Accelerating Reasoning-based Multimodal Representations via Think-Then-Embed TokensLLM reasoning → Multimodal reasoning
  22. HexAGenT: Efficient Agentic LLM Serving via Workflow- and Heterogeneity-Aware SchedulingEfficient LLM inference and serving → Efficient reasoning and agent inference
  23. Learning How to CubeLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  24. PrivScope: Task-scoped Disclosure Control for Hybrid Agentic SystemsLLM agents and tool use → Agent threats, guardrails and governance
  25. SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent MonitorsLLM agents and tool use → Agent threats, guardrails and governance
  26. R2V Agent: Teaching SLMs When to Ask for HelpLLM agents and tool use → General LLM agent frameworks and benchmarks
  27. Where Pretraining writes and Alignment reads: the asymmetry of Transformer weight spaceLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  28. GRASP: Graph Agentic Search over Propositions for Multi-hop Question AnsweringLLM agents and tool use → Web, search, and research agents
  29. Attend Locally, Remember Linearly: Linear Attention as Cross-Frame Memory for Autoregressive Video DiffusionDiffusion models → Video generation
  30. Wavelet Flow Matching for Multi-Scale Physics EmulationDiffusion models → Flow matching, time series and science
  31. Skim: Speculative Execution for Fast and Efficient Web AgentsLLM agents and tool use → Web, search, and research agents
  32. From Prompts to Protocols: An AI Agent for Laboratory AutomationLLM agents and tool use → Web, search, and research agents
  33. PQR: A Framework to Generate Diverse and Realistic User Queries that Elicit QA Agent FailuresLLM agents and tool use → General LLM agent frameworks and benchmarks
  34. World Model-Enabled Causal Digital Twins for Semantic Communications in Physical AI SystemsWorld models → World models for language agents +1
  35. RAPT: Retrieval-Augmented Post-hoc Thresholding for Multi-Label ClassificationRetrieval-augmented generation → Generation and context integration
  36. SWoMo: Neuro-Symbolic World Model for Cataract Surgery SimulationWorld models → Medical and surgical world models +1
  37. Multiscale Supervised Unbalanced Optimal Transport Flow MatchingDiffusion models → Flow matching, time series and science
  38. Global Convergence of Sampling-Based Nonconvex Optimization through Diffusion-Style SmoothingDiffusion models → Diffusion foundations and sampling
  39. The Scaling Laws of Skills in LLM Agent SystemsLLM agents and tool use → Agent skill learning and evolution
  40. Visual Agentic Memory: Enabling Online Long Video Understanding via Online Indexing, Hierarchical Memory, and Agentic RetrievalLLM agents and tool use → Multimodal and embodied agents
  41. Deep Learning for MRI Slice Interpolation: The Critical Role of Problem FormulationDiffusion models → Medical imaging and segmentation
  42. Dimension-Uniform Discretization Analysis of Preconditioned Annealed Langevin Dynamics for Multimodal Gaussian MixturesDiffusion models → Diffusion foundations and sampling
  43. From AI-Generated Content to Agentic Action: Security and Safety Threats in Generative AILLM agents and tool use → Agent threats, guardrails and governance
  44. Flow Matching with Optimized Subclass Priors for Medical Image AugmentationDiffusion models → Medical imaging and segmentation
  45. MHMamba: Multi-Head Mamba for 3D Brain Tumor SegmentationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  46. Asking Back: Interaction-Layer Antidistillation WatermarksKnowledge distillation → Federated, robust and private distillation
  47. REC-RL: Referring expression counting via Gaussian and range-based reward optimizationLLM reasoning → Multimodal reasoning +1
  48. Identifiable Token Correspondence for World ModelsWorld models → Latent dynamics models and model-based RL +1
  49. Membership Inference Attacks on Discrete Diffusion Language ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
  50. Real-time Speech Restoration using Data Prediction Mean FlowsDiffusion models → Audio, speech and music
  51. Offline Semantic Guidance for Efficient Vision-Language-Action Policy DistillationVision-language-action models → Generalist VLA models and benchmarks +1
  52. Dynamics-Level Watermarking of Flow Matching Models with Random CodesDiffusion models → Robustness, privacy and adversarial aspects +1
  53. FORGE: Self-Evolving Agent Memory With No Weight Updates via Population BroadcastLLM agents and tool use → Agent memory systems +1
  54. Argus: Evidence Assembly for Scalable Deep Research AgentsLLM agents and tool use → Web, search, and research agents
  55. Confirming Correct, Missing the Rest: LLM Tutoring Agents Struggle Where Feedback Matters MostLLM agents and tool use → Educational agents and math problem solving
  56. Context, Reasoning, and Hierarchy: A Cost-Performance Study of Compound LLM Agent Design in an Adversarial POMDPLLM reasoning → Reasoning for agents, planning and code +1
  57. paper.json: A Coordination Convention for LLM-Agent-Actionable PapersLLM agents and tool use → Web, search, and research agents
  58. MAgSeg: Segmentation of Agricultural Landscapes in High-Resolution Satellite Imagery using Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Agricultural vision-language models
  59. Imitation learning for clinical decision support in pediatric ECMOOffline RL and imitation learning from data → Safe offline RL
  60. BAPR: Bayesian amnesic piecewise-robust reinforcement learning for non-stationary continuous controlDeep reinforcement learning methods → RL theory and sample complexity
  61. Learn Where Outcomes Diverge: Efficient VLA RL via Probabilistic Chunk MaskingLLM reasoning → Reinforcement learning for reasoning +1
  62. Registers Matter for Pixel-Space Diffusion TransformersDiffusion models → Diffusion foundations and sampling
  63. Look Before You Leap: Autonomous Exploration for LLM AgentsLLM agents and tool use → Reinforcement learning for LLM agents
  64. GenShield: Unified Detection and Artifact Correction for AI-Generated ImagesDiffusion models → Image generation, text-to-image and editing
  65. Multi-Fidelity Flow Matching: Cascaded Refinement of PDE SolutionsDiffusion models → Flow matching, time series and science
  66. SGR: A Stepwise Reasoning Framework for LLMs with External Subgraph GenerationLLM reasoning → Knowledge- and tool-augmented reasoning
  67. ShopGym: An Integrated Framework for Realistic Simulation and Scalable Benchmarking of E-Commerce Web AgentsLLM agents and tool use → Social simulation and multi-agent debate
  68. DebiasRAG: A Tuning-Free Path to Fair Generation in Large Language Models through Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
  69. Sign-Separated Asymmetric Finite-Time Error Analysis of Q-LearningDeep reinforcement learning methods → RL theory and sample complexity
  70. PCDM: A Diffusion-Based Data Poisoning Attack Against Federated Learning SystemsLLM safety and security → Federated unlearning and poisoning
  71. A Cross-Modal Prompt Injection Attack against Large Vision-Language Models with Image-Only PerturbationMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  72. ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned RepresentationLLM reasoning → Multimodal reasoning
  73. VideoSeeker: Incentivizing Instance-level Video Understanding via Native Agentic Tool InvocationMultimodal LLMs / vision-language models → Video understanding with MLLMs +1
  74. Health-Conditioned Vision-Language-Action Models for Malfunction-Aware Robot ControlVision-language-action models → Generalist VLA models and benchmarks
  75. Ada-Diffuser: Latent-Aware Adaptive Diffusion for Decision-MakingDiffusion models → Diffusion and flow policies for robotics
  76. Reasoners or Translators? Contamination-aware Evaluation and Neuro-Symbolic Robustness in Tax LawLLM reasoning → Reasoning for agents, planning and code
  77. RecMem: Recurrence-based Memory Consolidation for Efficient and Effective Long-Running LLM AgentsLLM agents and tool use → Agent memory systems
  78. Mind Dreamer: Untethering Imagination via Active Causal Intervention on Latent ManifoldsDeep reinforcement learning methods → RL for robot locomotion and manipulation
  79. ScreenSearch: Uncertainty-Aware OS ExplorationLLM agents and tool use → GUI and mobile agents
  80. Adaptive Outer-Loop Control of Quadrotors via Reinforcement LearningDeep reinforcement learning methods → RL for robot navigation and UAV control
  81. Can Vision Language Models Be Adaptive in Mathematics Education? A Learner Model-based Rubric StudyMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  82. Echo-Forcing: A Scene Memory Framework for Interactive Long Video GenerationDiffusion models → Video generation
  83. Segmentation, Detection and Explanation: A Unified Framework for CT Appearance ReasoningLLM reasoning → Clinical and biomedical applications +1
  84. Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy OptimizationLLM reasoning → Reinforcement learning for reasoning +2
  85. Reference-Free Reinforcement Learning Fine-Tuning for MT: A Seq2Seq PerspectiveDeep reinforcement learning methods → RL training of language and agent models
  86. Learning Bilevel Policies over Symbolic World Models for Long-Horizon PlanningWorld models → Latent predictive world models +1
  87. OHP-RL: Online Human Preference as Guidance in Reinforcement Learning for Robot ManipulationDeep reinforcement learning methods → RL for robot locomotion and manipulation
  88. Deterministic Event-Graph Substrates as World Models for Counterfactual ReasoningWorld models → World models for language agents
  89. WorldVLN: Autoregressive World Action Model for Aerial Vision-Language NavigationWorld models → World models for navigation
  90. PAGER: Bridging the Semantic-Execution Gap in Point-Precise Geometric GUI ControlMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  91. Sparse Autoencoders enable Robust and Interpretable Fine-tuning of CLIP modelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP +1
  92. Imperfect World Models are ExploitableWorld models → Latent dynamics models and model-based RL +2
  93. From Failure to Feedback: Group Revision Unlocks Hard Cases in Object-Level GroundingMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  94. FocalPolicy: Frequency-Optimized Chunking and Locally Anchored Flow Matching for Coherent Visuomotor PolicyDiffusion models → Diffusion and flow policies for robotics
  95. Clock-state olfactory search in turbulent flows using Q-learning: The geometry of plume recoveryDeep reinforcement learning methods → RL for robot navigation and UAV control
  96. Towards Generalization of Block Attention via Automatic Segmentation and Block DistillationRetrieval-augmented generation → Multimodal RAG +1
  97. FedEDAuth -- Federated Embedding Distribution Authentication for Counterfeit IC DetectionLLM safety and security → Federated unlearning and poisoning
  98. Unlocking Dense Metric Depth Estimation in VLMsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  99. Agentic Discovery of Neural Architectures: AIRA-Compose and AIRA-DesignLLM agents and tool use → General LLM agent frameworks and benchmarks
  100. Are VLMs Seeing or Just Saying? Uncovering the Illusion of Visual Re-examinationMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
All 474
  1. Do Less, Achieve More: Do We Need Every-Step Optimization for RL Fine-tuning of Diffusion Models?Diffusion models → Diffusion and flow policies for robotics
  2. GHOST: Geometry-Hierarchical Online Streaming Token Eviction for Efficient 3D ReconstructionEfficient LLM inference and serving → Token pruning and merging for ViTs
  3. Access Timing as Scaffolding: A Reinforcement Learning Approach to GenAI in EducationDeep reinforcement learning methods → RL training of language and agent models
  4. RoadmapBench: Evaluating Long-Horizon Agentic Software Development Across Version UpgradesLLM agents and tool use → Software engineering coding agents
  5. WorldAct: Activating Monolithic 3D Worlds into Interactive-Ready Object-Centric ScenesWorld models → Video-generation world models and simulators
  6. Intrinsic Wasserstein Rates for Score-Based Generative Models on Smooth ManifoldsDiffusion models → Diffusion foundations and sampling
  7. Toward Natural and Companionable Virtual Agents via Cross-Temporal Emotional ModelingLLM agents and tool use → Social simulation and multi-agent debate
  8. Embedding-perturbed Exploration Preference Optimization for Flow ModelsLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  9. Reversing the Flow: Generation-to-Understanding Synergy in Large Multimodal ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  10. Fairness-Aware Retrieval Optimization for Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
  11. SaaS-Bench: Can Computer-Use Agents Leverage Real-World SaaS to Solve Professional Workflows?LLM reasoning → Reasoning for agents, planning and code +1
  12. ALSO: Adversarial Online Strategy Optimization for Social AgentsLLM agents and tool use → Reinforcement learning for LLM agents
  13. GRASP: Learning to Ground Social Reasoning in Multi-Person Non-Verbal InteractionsLLM reasoning → Reasoning benchmarks and evaluation +1
  14. DimMem: Dimensional Structuring for Efficient Long-Term Agent MemoryLLM agents and tool use → Agent memory systems
  15. Attribute-Grounded Selective Reasoning for Artwork Emotion Understanding with Multimodal Large Language ModelsLLM reasoning → Audio-language model reasoning +1
  16. HyperDiT: Hyper-Connected Transformers for High-Fidelity Pixel-Space DiffusionDiffusion models → Diffusion foundations and sampling
  17. BARRIER: Bounded Activation Regions for Robust Information ErasureLLM safety and security → Machine unlearning
  18. Structure Abstraction and Generalization in a Hippocampal-Entorhinal Inspired World ModelWorld models → World models for navigation
  19. Nudging Beyond the Comfort Zone: Efficient Strategy-Guided Exploration for RLVRLLM reasoning → Reinforcement learning for reasoning
  20. DiLA: Disentangled Latent Action World ModelsWorld models → Embodied and robot world models
  21. EntropyScan: Towards Model-level Backdoor Detection in LVLMs via Visual Attention EntropyMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  22. 3D Segmentation Using Viewpoint-Dependent Spatial RelationshipsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  23. Differentiable Mixture-of-Agents Incentivizes Swarm Intelligence of Large Language ModelsLLM agents and tool use → General LLM agent frameworks and benchmarks
  24. Feedback World Model Enables Precise Guidance of Diffusion PolicyWorld models → Embodied and robot world models +1
  25. H-Mem: A Novel Memory Mechanism for Evolving and Retrieving Agent Memory via a Hybrid StructureLLM agents and tool use → Agent memory systems
  26. Distributed Zeroth-Order Policy Gradient for Networked Multi-agent Reinforcement Learning from Human FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  27. Tighter Regret Bounds for Contextual Action-Set Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  28. ASRU: Activation Steering Meets Reinforcement Unlearning for Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +2
  29. ElasticDiT: Efficient Diffusion Transformers via Elastic Architecture and Sparse Attention for High-Resolution Image Generation on Mobile DevicesDiffusion models → Diffusion foundations and sampling
  30. DreamSR: Towards Ultra-High-Resolution Image Super-Resolution via a Receptive-Field Enhanced Diffusion TransformerDiffusion models → Inverse problems and image restoration
  31. DealMaTe: Multi-Dimensional Material Transfer via Diffusion TransformerDiffusion models → 3D, point cloud and scene generation
  32. VCG-Bench: Towards A Unified Visual-Centric Benchmark for Structured Generation and EditingMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  33. Dynamic Chunking for Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  34. VLMs Trace Without Tracking: Diagnosing Failures in Visual Path FollowingMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  35. Rule2DRC: Benchmarking LLM Agents for DRC Script Synthesis with Execution-Guided Test GenerationLLM agents and tool use → Software engineering coding agents
  36. Viscosity-Informed Generative Actor-Critic for High-Dimensional Stochastic Optimal ControlDeep reinforcement learning methods → RL theory and sample complexity
  37. MaTe: Images Are All You Need for Material Transfer via Diffusion TransformerDiffusion models → 3D, point cloud and scene generation
  38. Sharp Spectral Thresholds for Logit Fixed PointsDeep reinforcement learning methods → RL theory and sample complexity
  39. ColPackAgent: Agent-Skill-Guided Hard-Particle Monte Carlo Workflows for Colloidal PackingLLM agents and tool use → Medical and scientific domain agents
  40. LRCP: Low-Rank Compressibility Guided Visual Token Pruning for Efficient LVLMsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  41. Latent Video Prediction Learns Better World ModelsWorld models → Video-generation world models and simulators
  42. Neutral-Reference Prompting for Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  43. TopoEvo: A Topology-Aware Self-Evolving Multi-Agent Framework for Root Cause Analysis in MicroservicesLLM agents and tool use → Software engineering coding agents +1
  44. PSD: Pushing the Pareto Frontier of Diffusion LLMs via Parallel Speculative DecodingEfficient LLM inference and serving → Diffusion LLM and MoE inference
  45. VSPO: Vector-Steered Policy Optimization for Behavioral ControlMechanistic interpretability → Activation steering methods
  46. Offline Reinforcement Learning with Universal Horizon ModelsOffline RL and imitation learning from data → Offline RL algorithms
  47. Pretraining Objective Matters in Extreme Low-Data FGVC: A Backbone-Controlled StudyMechanistic interpretability → Sparse autoencoder training and evaluation
  48. Compositional Jailbreaking: An Empirical Analysis of Mutator Chain Interactions in Aligned LLMsLLM safety and security → Jailbreaking
  49. AGC: Adaptive Geodesic Correction for Adversarial Robustness on Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  50. Unsupervised 3D Human Pose Estimation via Conditional Multi-view Ancestral SamplingDiffusion models → 3D, point cloud and scene generation
  51. STAR: A Stage-attributed Triage and Repair framework for RCA Agents in MicroservicesLLM agents and tool use → Software engineering coding agents
  52. MI-CXR: A Benchmark for Longitudinal Reasoning over Multi-Interval Chest X-raysLLM reasoning → Clinical and biomedical applications
  53. Response-Conditioned Parallel-to-Sequential Orchestration for Multi-Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  54. Measuring Maximum Activations in Open Large Language ModelsMixture-of-experts → MoE large language models
  55. Detecting Privilege Escalation in Polyglot Microservices via Agentic Program AnalysisLLM agents and tool use → Agent threats, guardrails and governance
  56. AstraFlow: Dataflow-Oriented Reinforcement Learning for Agentic LLMsLLM agents and tool use → Reinforcement learning for LLM agents
  57. RoiMAM: Region-of-Interest Medical Attention Model for Efficient Vision-Language UnderstandingMultimodal LLMs / vision-language models → Medical vision-language models
  58. NavRL++: A System-Level Framework for Improving Sim-to-Real Transfer in Reinforcement Learning-Based Robot NavigationDeep reinforcement learning methods → RL for robot navigation and UAV control
  59. TopoClaw: A Human-Centric and Topology-Aware Agent Operating SystemLLM agents and tool use → General LLM agent frameworks and benchmarks
  60. 3DTMDet: A Dual-Path Synergy Network of Transformer and SSM for 3D Object Detection in Point CloudsState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  61. DRS-GUI: Dynamic Region Search for Training-Free GUI GroundingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  62. RTL-BenchMT: Dynamic Maintenance of RTL Generation Benchmark Through Agent-Assisted Analysis and RevisionLLM agents and tool use → Software engineering coding agents
  63. SkiP: When to Skip and When to Refine for Efficient Robot ManipulationOffline RL and imitation learning from data → Robot manipulation imitation learning
  64. DeltaPrompts: Escaping the Zero-Delta Trap in Multimodal DistillationLLM reasoning → Multimodal reasoning +2
  65. Process Rewards with Learned ReliabilityLLM reasoning → Reinforcement learning for reasoning +1
  66. Task-Semantic Graph-Driven Distributed Agent Networking for Underwater Target TrackingDeep reinforcement learning methods → RL for robot navigation and UAV control
  67. Self-Prompting Diffusion Transformer for Open-Vocabulary Scene Text Editing via In-Context LearningDiffusion models → Image generation, text-to-image and editing
  68. Terrain Consistent Reference-Guided RL for Humanoid Navigation AutonomyDeep reinforcement learning methods → RL for robot locomotion and manipulation
  69. CAPS: Cascaded Adaptive Pairwise Selection for Efficient Parallel ReasoningLLM reasoning → Test-time compute and efficient thinking
  70. parallelcbf: A composable safety-filter and auditability framework for tensor-parallel reinforcement learningDeep reinforcement learning methods → Safe and constrained RL
  71. uGen: An Agentic Framework for Generating Microarchitectural Attack PoCsLLM agents and tool use → Agent threats, guardrails and governance
  72. FLASH: Efficient Visuomotor Policy via Sparse SamplingDiffusion models → Diffusion and flow policies for robotics
  73. Learning Normalized Energy Models for Linear Inverse ProblemsDiffusion models → Inverse problems and image restoration
  74. When Does Sparse MoE Help in Vision? The Role of Backbone Compute Leverage in Sparse RoutingMixture-of-experts → Vision mixture-of-experts
  75. The Unwritten Benchmark: A New Challenge for Multimodal Machine Learning in Abstract Perceptual Reasoning
  76. Large-Scale ChatBot Validation Through Customer Digital Twin Simulations
  77. MioFFAn: an Annotation Software for Formula Formalization with LLM Automation Capabilities
  78. Analyzing Middle School Students' Dialogue and Behaviors during Collaborative AI Chatbot Development Using Ordered Network Analysis
  79. Can Valence Reflect Morality in Natural Language? A Preliminary Annotation Study
  80. Instruct-FD: Can Your Full-Duplex Speech System Follow Turn-Taking Instructions?
  81. THOR: A Theta-Gamma Hierarchical Oscillatory Reasoning Framework for Multi-hop QA
  82. AI Companions as Hyper Attachment and Caregiving Targets
  83. AInterviewer: A Platform for Designing and Conducting AI-led Qualitative Interviews
  84. Marginal Alignment Does Not Guarantee Joint-Distribution Fidelity: An Official-Reference Audit of Nemotron-Personas-Korea with Cross-Locale Replication
  85. Will AI Agents Free Us From Meaningless Work? A Human-Centered Analysis
  86. XOResNet: Exclusive-OR Meta-Residuals Facilitate Deep Spiking Neural Networks Learning
  87. Parameter Efficient Multi-Class Intelligent Scheduling for Multimodal Online Distributed Industrial Anomaly Detection
  88. Uncertainty-aware neural emulation reveals climate-resilient maize traits at scale
  89. Harnesses for Inference-Time Alignment over Execution Trajectories
  90. Predicting Performance of Symbolic and Prompt Programs with Examples
  91. Conditional Entropy of Heat Diffusion on Temporal Networks
  92. GenAI-FDIA: Physics-Informed Generative Models for False Data Injection Attacks
  93. EUPHORIA: Efficient Universal Planning via Hybrid Optimization for Robust Industrial Robotic Assembly
  94. Multi-Headed Transformer Architectures as Time-dependent Wasserstein Gradient Flows
  95. MO-CAPO: Multi-Objective Cost-Aware Prompt Optimization
  96. DarkLLM: Learning Language-Driven Adversarial Attacks with Large Language Models
  97. EVA-0: Test-Time Model Evolution with Only Two Forward Passes per Sample
  98. FLUIDSPLAT: Reconstructing Physical Fields from Sparse Sensors via Gaussian Primitives
  99. From Sparsity to Simplicity: Enabling Simpler Sequential Replacements via Sparse Attention Distillation
  100. Towards Family-Grouped Hierarchical Federated Learning on Sub-5KB Models: A Feasibility Study of Privacy-Preserving ECG Monitoring for Ultra-Resource-Constrained Wearables
  101. GRID: Graph Representation of Intelligence Data for Security Text Knowledge Graph Construction
  102. Recall Isn't Enough: Bounding Commitments in Personalized Language Systems
  103. Isolating Nonlinear Independent Sources in fMRI with β-TCVAE Models
  104. On-Device Interpretable Tsetlin Machine-Based Intrusion Detection for Secure IoMT
  105. Convex Dataset Valuation for Post-Training
  106. Your SaaS Is an Insurance Product: A Modeling Framework
  107. Identify then Realize: Contrastive Learning of Latent Port-Hamiltonian Dynamics from Partial Observations
  108. CHI-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?
  109. Enhancing Metacognitive AI: Knowledge-Graph Population with Graph-Theoretic LLM Enrichment
  110. Multi-Object Tracking Consistently Improves Wildlife Inference
  111. Sustainable Intelligence for the Wild: Democratizing Ecological Monitoring via Knowledge-Adaptive Edge Expert Agents
  112. GraViti: Graph-Level Variational Autoencoders with Relaxed Permutation Invariance
  113. In-context learning enables continental-scale subsurface temperature prediction from sparse local observations
  114. A Scalable Tool for Measuring Manner and Result Verbs in Developmental Language Research
  115. SKG-Eval: Stateful Evaluation of Multi-Turn Dialogue via Incremental Semantic Knowledge Graphs
  116. Public-Decay Homomorphic State Space Models for Private Sequence Inference
  117. The Score Kalman Filter
  118. Provably Shorter Scratchpads in Hybrid DeltaNet-Attention Decoders
  119. MedMIX: Modality-Internal Expert Fusion for Multimodal Medical Diagnosis
  120. SCARED-C: Corrected Camera Poses for Endoscopic Depth Estimation
  121. To Trust or Not to Trust: Authors' Response to AI-based Reviews
  122. Does Weight Decay Enhance Training Stability?
  123. SCOUT: Cyclic Causal Discovery Under Soft Interventions with Unknown Targets
  124. MLReplicate: Benchmarking Autonomous Research Systems for Machine Learning Reproducibility
  125. Learning What Evaluators Value: A Reliable Approach to Modeling Evaluator Preferences
  126. Beyond Sentiment Classification: A Generative Framework for Emotion Intensity Evaluation in Text
  127. PRISMat: Policy-Driven, Permutation-Invariant Autoregressive Material Generation
  128. Tensor Cookbook: Mastering Tensors through Diagrams
  129. To MRL or not to MRL: Text Embeddings are Robust to Truncation Without Matryoshka Learning, Except In Heavy Truncation Scenarios
  130. PromptDecipher: Supporting AI Tutor Authoring Through Editable Simulated Interactions
  131. Controlla: Learning Controllability via Graph-Constrained Latent Geometry
  132. Why Modeling Human Haptic Material Perception with AI Is Difficult
  133. fPINN-DeepONet: A Physics-Informed Operator Learning Framework for Multi-term Time-fractional Mixed Diffusion-wave Equations
  134. Policy Learning with Observational Data: The Case of Hepatitis C Treatment for HIV/HCV Co-Infected Patients
  135. How Few-Shot Examples Add Up: A Causal Decomposition of Function Vectors in In-Context Learning
  136. ArtMesh: Part-Aware Articulated Mesh Fields with Motion-Consistent Dynamics
  137. Structure-Aware Masking for Protein Representation Learning
  138. Voice "Cloning" is Style Transfer
  139. Counterparty Modeling is Not Strategy: The Limits of LLM Negotiators
  140. TriALS: Triphasic-Aided Liver Lesion Segmentation Benchmark in Non-Contrast CT
  141. Isotonic Survival Regression: Calibrated Survival Distributions from Deep Cox Models
  142. A Cubing Strategy for Identifying Stable Hyperparameter Regions for Uncertainty Quantification in Spatial Deep Learning
  143. Scalable Uncertainty Reasoning in Knowledge Graphs
  144. Automatic Unsupervised Ensemble Outlier Model Selection--Extended Version
  145. Scaling Accessible Mathematics on arXiv: HTML Conversion and MathML 4
  146. Attention-Aware Transformer-Based Aggregation Network for Video Periocular Recognition
  147. Symphony for Speech-to-Text: Supporting Real-Time Medical Voice Interfaces
  148. LLMs in Qualitative Research: Opportunities, Limitations, and Practical Considerations
  149. Boundedly Rational Meta-Learning in Sequential Consumer Choice
  150. Inventorship in AI-Assisted Inventions: Designing an Experiment to Shape Case Law
  151. Hypergraph Pattern Machine: Compositional Tokenization for Higher-Order Interactions
  152. Toward Template-Free Explainability for Monte Carlo Tree Search
  153. DepthPolyp: Pseudo-Depth Guided Lightweight Segmentation for Real-Time Colonoscopy
  154. Alignment Drift in Long-Term Human-LLM Interaction: A Mechanism-Oriented Framework
  155. SeamCam: Quantifying Seamless Camouflage via Multi-Cue Visual Detectability
  156. No Plan, Yet Human: A Reactive Robotics Model Predicts Human Planning Failures on a Clinical Task
  157. StAD: Stein Amortized Divergence for Fast Likelihoods with Diffusion and Flow
  158. MoleCode unlocks structural intelligence in large language models
  159. Policy-Grounded Dynamic Facet Suggestions for Job Search
  160. Seeking the Unfamiliar but Memorable: Conceptual Creativity as Meta-Learning
  161. Generative Artificial Intelligence for Literature Reviews
  162. LERA: LLM-Enhanced RAG for Ad Auction in Generative Chatbots
  163. Strategic Over-Parameterization for Generalizable Low-Rank Adaptation
  164. Mechanistically Interpretable Neural Encoding Reveals Fine-Grained Functional Selectivity in Human Visual Cortex
  165. Conservative AI for Safety-Sensitive Medical Image Restoration: Residual-Bounded CT-CTA Enhancement for Intracranial Aneurysm-Relevant Signal Recovery
  166. Multi-hop Relational Contrastive Learning: Extending Spatial Contrastive Pre-training Beyond Pairwise Relations
  167. Peak-Detector: Explainable Peak Detection via Instruction-Tuned Large Language Models in Physiological Sign
  168. Physics-Guided Geometric Diffusion for Macro Placement Generation
  169. PESD-TSF: A Period-Aware and Explicit Structured Decomposition Framework for Long-Term Time Series Forecasting
  170. Nested Spatio-Temporal Time Series Forecasting
  171. Avoiding Structural Failure Modes in Tabular Fair SSL: Online Primal-Dual Allocation under Confidence Gating
  172. Diffusion Attention Expert Model for Predicting and Semi-automatic Localizing STAS in Lung Cancer Histopathological Images
  173. Two-Valued Symmetric Circulant Matrices: Applications in Deep Learning
  174. Hierarchical Two-Stage Framework for Environment-Aware Long-Horizon Vessel Trajectory Prediction
  175. DeepArrhythmia: Segment-Contextualized ECG Arrhythmia Classification via Selective Evidence Acquisition
  176. Semantic Smoothing via Novel View Synthesis for Robust SAR Image Classification
  177. IVGT: Implicit Visual Geometry Transformer for Neural Scene Representation
  178. Designing Datacenter Power Delivery Hierarchies for the AI Era
  179. A Generative AI Framework for Intelligent Utility Billing CO 2 Analytics and Sustainable Resource Optimisation
  180. FRESH: Information-Geometric Calibration of Patient-Level Models to Aggregate Evidence
  181. AI-Mediated Communication Can Steer Collective Opinion
  182. Prospective multi-pathogen disease forecasting using autonomous LLM-guided tree search
  183. No Free Swap: Protocol-Dependent Layer Redundancy in Transformers
  184. A Unified Generative-AI Framework for Smart Energy Infrastructure: Intelligent Gas Distribution, Utility Billing, Carbon Analytics, and Quantum-Inspired Optimisation
  185. Universal Magnetic Structure Prediction from Atomic Coordinates with Near-Experimental Accuracy
  186. Learning from Totally Unpaired Data via Minimum Conditional Entropy Coupling
  187. Evaluating Design Video Generation: Metrics for Compositional Fidelity
  188. Artificial Aphasias in Lesioned Language Models
  189. The Privacy Price of Tail-Risk Learning: Effective Tail Sample Size in Differentially Private CVaR Optimization
  190. Fully Open Meditron: An Auditable Pipeline for Clinical LLMs
  191. Hypothesis-driven construction of mesoscopic dynamics
  192. A Scalable Nonparametric Continuous-Time Survival Model through Numerical Quadrature
  193. Formal Methods Meet LLMs: Auditing, Monitoring, and Intervention for Compliance of Advanced AI Systems
  194. Improving Cross-Cultural Survey Simulation with Calibrated Value Personas
  195. Optimized Three-Dimensional Photovoltaic Structures with LLM guided Tree Search
  196. Runtime-Orchestrated Second-Order Optimization for Scalable LLM Training
  197. Res2CLIP: Few-Shot Generalist Anomaly Detection with Residual-to-Residual Alignment
  198. Second-Order Multi-Level Variance Correction for Modality Competition in Multimodal Models
  199. Entropic Auto-Encoding via Implicit Free-Energy Minimization
  200. SwAIther-Precip: Lead-Time-Aware Bias Correction Enables Kilometer-Scale Downscaling of Global AI Precipitation Forecasts over Switzerland
  201. An Algebraic Exposition of the Theory of Dyadic Morality
  202. Skew-adaptive conformal prediction
  203. Property-Guided LLM Program Synthesis for Planning
  204. SNAC-Pack 2.0: Scaled-Out Surrogate Neural Architecture Codesign
  205. STABLE: Simulation-Ready Tabletop Layout Generation via a Semantics-Physics Dual System
  206. Navigating Potholes with Geometry-Aware Sharpness Minimization
  207. WeatherOcc3D: VLM-Assisted Adverse Weather Aware 3D Semantic Occupancy Prediction
  208. Entropy Across the Bridge: Conditional-Marginal Discretization for Flow and Schr"odinger Samplers
  209. Scalable neuromorphic computing from autonomous spiking dynamics in a clockless reconfigurable chip
  210. Attention Dispersion in Dynamic Graph Transformers: Diagnosis and a Transferable Fix
  211. Multi-Level Contextual Token Relation Modeling for Machine-Generated Text Detection
  212. Federated Imputation under Heterogeneous Feature Spaces
  213. GeoGS-CE: Learning Delay--Beam Channel Priors with 3D Gaussians for High-Mobility Scenarios
  214. Centralized vs Decentralized Federated Learning: A trade-off performance analysis
  215. Multi-level Self-supervised Pretraining on Compositional Hierarchical Graph for Molecular Property Prediction
  216. Towards Trustworthy and Explainable AI for Perception Models: From Concept to Prototype Vehicle Deployment
  217. Towards Foundation Models for Relational Databases with Language Models and Graph Neural Networks
  218. MIND: Decoupling Model-Induced Label Noise via Latent Manifold Disentanglement
  219. A numerical study into neural network surrogate model performance for uncertainty propagation
  220. Can Large Language Models Imitate Human Speech for Clinical Assessment? LLM-Driven Data Augmentation for Cognitive Score Prediction
  221. AgriMind: An Ensemble Deep Learning Framework for Multi-Class Plant Disease Classification
  222. ITGPT: Generative Pretraining on Irregular Timeseries
  223. SAFE Quantum Machine Learning with Variational Quantum Classifiers
  224. Robust Prior-Guided Segmentation for Editable 3D Gaussian Splatting
  225. Misspecified Estimate-then-Optimize Leads to Supra-Competitive Prices
  226. Reshape and Recur: Improving SSMs with Input Reshaping and Depth Recurrence
  227. XSearch: Explainable Code Search via Concept-to-Code Alignment
  228. Learning Sim-Grounded Policies for Bimanual Rope Manipulation from Human Teleoperation Data
  229. Explainable AI Isn't Enough! Rethinking Algorithmic Contestability
  230. Who Owns This Agent? Tracing AI Agents Back to Their Owners
  231. Conditioned in Training, Dispensable at Inference: Typological Conditioning for Multilingual Speech Translation
  232. Judge Circuits Explain Format-Induced Inconsistency in LLM-as-a-Judge
  233. EndoGSim: Physics-Aware 4D Dynamic Endoscopic Scene Simulations via MLLM-Guided Gaussian Splatting
  234. Variational Autoregressive Networks with probability priors
  235. Accelerated Gradient Descent for Faster Convergence with Minimal Overhead
  236. End-to-end plaque counting and virus titration from laboratory plate images with deep learning
  237. CitePrism: Human-in-the-Loop AI for Citation Auditing and Editorial Integrity
  238. Testing properties of trees in graphical models with covariance queries
  239. Constrained latent state modeling: A unifying perspective on representation learning under competing constraints
  240. Defining Cultural Capabilities for AI Evaluation: A Taxonomy Grounded in Intercultural Communication Theory
  241. Beyond Content: A Comprehensive Speech Toxicity Dataset and Detection Framework Incorporating Paralinguistic Cues
  242. Petri Net Induced Heuristic Search for Resource Constrained Scheduling
  243. Ontology for Policing: Conceptual Knowledge Learning for Semantic Understanding and Reasoning in Law Enforcement Reports
  244. Entropy-Based Characterisation of the Polarised Regime in Latent Variable Models
  245. When and Why Adversarial Training Improves PINNs: A Neural Tangent Kernel Perspective
  246. Topological Kalman Filtering on Cell Complexes
  247. Node-private community estimation in stochastic block models: Tractable algorithms and lower bounds
  248. Decomposed Vision-Language Alignment for Fine-Grained Open-Vocabulary Segmentation
  249. A Retrieval-Enhanced Transformer for Multi-Step Port-of-Call Sequence Prediction in Global Liner Shipping
  250. Invaria: Learning Scale and Density Invariance in Point Clouds via Next-Resolution Prediction
  251. AdaEraser: Training-Free Object Removal via Adaptive Attention Suppression
  252. Unsupervised Domain Shift Detection with Interpretable Subspace Attribution
  253. LoCO: Low-rank Compositional Rotation Fine-tuning
  254. SLIP & ETHICS: Graduated Intervention for AI Emotional Companions
  255. RaPD: Resolution-Agnostic Pixel Diffusion via Semantics-Enriched Implicit Representations
  256. A Causally Grounded Taxonomy for Image Degradation Robustness Evaluation
  257. Generative Long-term User Interest Modeling for Click-Through Rate Prediction
  258. Context-aware Entity-Relation Extraction for Threat Intelligence Knowledge Graphs
  259. From Layers to Networks: Comparing Neural Representations via Diffusion Geometry
  260. Layer Selection in Feature-Based Losses Affects Image Quality and Microstructural Consistency in Deep Learning Super-Resolution of Brain Diffusion MRI
  261. Uncertainty-Aware Wildfire Smoke Density Classification from Satellite Imagery via CBAM-Augmented EfficientNet with Evidential Deep Learning
  262. A Multi-Layer Cloud-IDS Pipeline with LLM and Adaptive Q-Learning Calibration
  263. CHoE: Cross-Domain Heterogeneous Graph Prompt Learning via Structure-Conditioned Experts
  264. Practical Validity Conditions for Byzantine-Tolerant Federated Learning
  265. Linked Multi-Modal Data on Russian Domestic and Foreign Policy Speeches
  266. Symplectic Neural Operators for Learning Infinite Dimensional Hamiltonian Systems
  267. Shapley Neuron Values for Continual Learning: Which Neurons Matter Most?
  268. Ti-iLSTM: A TinyDL Approach for Logic-Level Anomaly Detection in Industrial Water Treatment Systems
  269. SOLAR: Self-supervised Joint Learning for Symmetric Multimodal Retrieval
  270. From Observed Viability to Internal Predictive Approximation: A Single-Subject Latent-Space Analysis of Gait Dynamics Under Occlusal Constraint
  271. On RGB-TIR Stereo Calibration under Extreme Resolution Asymmetry
  272. Complexity of Non-Log-Concave Sampling in Fisher Information
  273. Conversations in Space: Non-Linear LLM Interaction in Everyday Use
  274. GAP: Geometric Anchor Pre-training for Data-Efficient Visuomotor Learning of Manipulation Tasks
  275. Community-aware evaluation and threshold calibration for open-set plankton image recognition
  276. Heuristic-Based Merging of HPC Traces to Extend Hardware Counter Coverage
  277. Modeling Music as a Time-Frequency Image: A 2D Tokenizer for Music Generation
  278. Not All Tasks Quantize Equally: Fisher-Guided Quantization for Visual Geometry Transformer
  279. FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization
  280. StippleDiffusion: Capacity-Constrained Stippling using Controlled Diffusion
  281. BootstrapAgent: Distilling Repository Setup into Reusable Agent Knowledge
  282. Martingale Neural Operators: Learning Stochastic Marginals via Doob-Meyer Factorization
  283. Cross-Modal Registration Between 3D and 2D Fingerprints via Pose-Aware Unwrapping and Point-Cloud Fusion
  284. ForMaT: Dataset for Visually-Grounded Multilingual PDF Translation
  285. AOT-POT: Adaptive Operator Transformation for Large-Scale PDE Pre-training
  286. Learning Context-conditioned Gaussian Overbounds for Convolution-Based Uncertainty Propagation
  287. ADAPT: A Self-Calibrating Proactive Autoscaler for Container Orchestration
  288. Grokking as Structural Inference: Transformers Need Bayesian Lottery Tickets
  289. A Topology-Aware Spatiotemporal Handover Framework for Continuous Multi-UAV Tracking
  290. Continual Learning of Domain-Invariant Representations
  291. Lamarckian Inheritance in Dynamic Environments: How Key Variables Affect Evolutionary Dynamics
  292. CompactQE: Interpretable Translation Quality Estimation via Small Open-Weight LLMs
  293. A Unified Perturbation Framework for Analyzing Leaderboard Stability and Manipulation
  294. Learn2Splat: Extending the Horizon of Learned 3DGS Optimization
  295. Hierarchical and Holistic Open-Vocabulary Functional 3D Scene Graphs for Indoor Spaces
  296. BiomedAP: A Vision-Informed Dual-Anchor Framework with Gated Cross-Modal Fusion for Robust Medical Vision-Language Adaptation
  297. UAM: A Dual-Stream Perspective on Forgetting in VLA Training
  298. Can We Trust AI-Inferred User States. A Psychometric Framework for Validating the Reliability of Users States Classification by LLMs in Operational Environments
  299. DecomPose: Disentangling Cross-Category Optimization Contention for Category-Level 6D Object Pose Estimation
  300. GOMA: Toward Structure-Driven Multimodal Alignment from a Graph Signal Smoothing Perspective
  301. Bidirectional Fusion Guided by Cardiac Patterns for Semi-Supervised ECG Segmentation
  302. Contexting as Recommendation: Evolutionary Collaborative Filtering for Context Engineering
  303. Semi-MedRef: Semi-Supervised Medical Referring Image Segmentation with Cross-Modal Alignment
  304. Position: Early-Stage Quality Assurance in Annotation Pipelines Is More Cost-Effective Than Late-Stage Validation
  305. Learning Dynamic Pick-and-Place for a Legged Manipulator
  306. SMMBench: A Benchmark for Source-Distributed Multimodal Agent Memory
  307. Evaluation of Anatomical Shape Priors in Deep Learning-Based Cardiac Multi-Compartment Segmentation
  308. AGOP-IxG: A Gradient Covariance Filter for Local Feature Attribution on Tabular Data, with a Controlled Benchmark
  309. Going Beyond the Edge: Distributed Inference of Transformer Models on Ultra-Low-Power Wireless Devices
  310. SEED: Targeted Data Selection by Weighted Independent Set
  311. FRWKV+: Periodic-Aware Adaptive Gating for Frequency-Space Linear Time Series Forecasting
  312. How to Choose Your Teacher for Fine Grained Image Recognition
  313. α-TCAV: A Unified Framework for Testing with Concept Activation Vectors
  314. Few-Shot Large Language Models for Actionable Triage Categorization of Online Patient Inquiries
  315. Interaction-Aware Influence Functions for Group Attribution
  316. Highly Detailed and Generalizable Broadleaf Tree Crown Instance Segmentation from UAV Imagery
  317. Degradation-Aware Blur-Segmentation of Brain Tumor
  318. ChronoEarth-492K: A Large Scale and Long Horizon Spatiotemporal Hyperspectral Earth Observation Dataset and Benchmark
  319. PRISM: Prompt Reliability via Iterative Simulation and Monitoring for Enterprise Conversational AI
  320. On the Power of Adaptivity for varepsilon-Best Arm Identification in Linear Bandits
  321. VAGS: Velocity Adaptive Guidance Scale for Image Editing and Generation
  322. TFZ-Tree: An Ultra-Lightweight Waveform Classification Framework for Resource-Constrained Devices
  323. Bridging Silicon and the Hippocampus: Algebro-Deterministic Memory "VaCoAl" as a Substrate for Vector-HaSH and TEM
  324. Towards Code-Oriented LM Embeddings for Surrogate-Assisted Neural Architecture Search
  325. Perforated Neural Networks for Keyword Spotting
  326. Learning Disentangled Representations for Generalized Multi-view Clustering
  327. Leveraging heterogeneity for identifiability: Bayesian order-based learning of multiple DAGs
  328. Evaluating Chinese Ambiguity Understanding in Large Language Models
  329. Reweighting free energy profiles between universal machine learning interatomic potentials for fast consensus building
  330. IO-SVD: Input-Output Whitened SVD for Adaptive-Rank LLM Compression
  331. Position: Zeroth-Order Optimization in Deep Learning Is Underexplored, Not Underpowered
  332. Pessimistic Risk-Aware Policy Learning in Contextual Bandits
  333. A Few GPUs, A Whole Lotta Scale: Faithful LLM Training Emulation with PrismLLM
  334. Toward LLMs Beyond English-Centric Development
  335. Transformer-like Inference from Optimal Control
  336. Syntax Without Semantics: Teaching Large Language Models to Code in an Unseen Language
  337. CM-EVS: Sparse Panoramic RGB-D-Pose Data for Complete Scene Coverage
  338. Efficient Image Synthesis with Sphere Latent Encoder
  339. MHGraphBench: Knowledge Graph-Grounded Benchmarking of Mental Health Knowledge in Large Language Models
  340. Calibrating LLMs with Semantic-level Reward
  341. Embracing Biased Transition Matrices for Complementary-Label Learning with Many Classes
  342. See Before You Code: Learning Visual Priors for Spatially Aware Educational Animation Generation
  343. LDGuid: A Framework for Robust Change Detection via Latent Difference Guidance
  344. TVRN: Invertible Neural Networks for Compression-Aware Temporal Video Rescaling
  345. Gaussian Relational Graph Transformer
  346. MaxSketch: Robust Distinct Counting in Streams via Random Projections
  347. Position: Artificial Intelligence Needs Meta Intelligence -- the Case for Metacognitive AI
  348. CrystalBoltz: End-to-End Protein Structure Determination via Experiment-Guided Diffusion for X-Ray Crystallography
  349. GiLT: Augmenting Transformer Language Models with Dependency Graphs
  350. Text-RSIR: A Text-Guided Framework for Efficient Remote Sensing Image Transmission and Reconstruction
  351. When Latent Geometry Is Not Enough: Draft-Conditioned Latent Refinement for Non-Autoregressive Text Generation
  352. Operator-Controlled 6G: From Connectivity Infrastructure to Guaranteed Digital Services
  353. Characterizing Learning in Deep Neural Networks using Tractable Algorithmic Complexity Analysis
  354. CTF4Nuclear: Common Task Framework for Nuclear Fission and Fusion Models
  355. Domain-Independent Game Abstraction using Word Embedding Techniques
  356. Learning Spatially Adaptive Structural Coordination for Underwater Salient Object Detection
  357. Tuning-free Instruction-based Video Editing Via Structural Noise Initialization and Guidance
  358. Rethinking Neural Network Learning Rates: A Stackelberg Perspective
  359. Neural Point-Forms
  360. Stochastic Non-Smooth Convex Optimization with Unbounded Gradients
  361. On the Fragility of Data Attribution When Learning Is Distributed
  362. DiffVAS: Diffusion-Guided Visual Active Search in Partially Observable Environments
  363. DetectRL-X: Towards Reliable Multilingual and Real-World LLM-Generated Text Detection
  364. RoPE Distinguishes Neither Positions Nor Tokens in Long Contexts, Provably
  365. OgBench: A Framework for Evaluating Graph Neural Networks on Omics Data
  366. STS: Efficient Sparse Attention with Speculative Token Sparsity
  367. PrismQuant: Rate-Distortion-Optimal Vector Quantization for Gaussian-Mixture Sources
  368. X-SYNTH: Beyond Retrieval -- Enterprise Context Synthesis from Observed Digital Human Attention
  369. Learning with Conflicts of Interest
  370. AnyAct: Towards Human Reenactment of Character Motion From Video
  371. LAPS: Improving Incremental LiDAR Mapping using Active Pooling and Sampling for Neural Distance Fields
  372. Ghosted Layers: Unconstrained Activation Alignment for Recovering Layer-Pruned LLMs
  373. SurvivalPFN: Amortizing Survival Prediction via In-Context Bayesian Inference
  374. Hybrid LLM-based Intelligent Framework for Robot Task Scheduling