mlsanityData to 14 Oct 2026

Papers

New on arXiv

Mon 18 May 2026

611 papers

  1. Retrieval-Augmented Generation to Support Railways Engineering Tasks: A Case StudyRetrieval-augmented generation → RAG pipeline design and evaluation
  2. PathoSage: Towards Multi-Source Evidence Adjudication in Pathology via Experience-Aware Agentic WorkflowMultimodal LLMs / vision-language models → Medical vision-language models +1
  3. Subtle Injection for Ground-truth Inference of LLM Training DataLLM safety and security → Membership inference attacks
  4. From Human Videos to Robot Manipulation: A Survey on Scalable Vision-Language-Action Learning with Human-Centric DataVision-language-action models → Human-video and latent-action pretraining
  5. Mental Damage: Caption Poisoning Attacks on Retrieval-Augmented Text-to-Music GenerationRetrieval-augmented generation → Privacy and security of RAG
  6. Harnessing AtomisticSkills for Agentic Atomistic ResearchLLM agents and tool use → Medical and scientific domain agents
  7. Diff-Instruct with Diffused Reward: Towards Principled One-step Generator RLLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  8. IVR-R1: Refining Trajectories through Iterative Visual-Grounded Reasoning in Reinforcement LearningLLM reasoning → Multimodal reasoning +1
  9. Generation of Heterogeneous PET Images from Uniform Organ Activity Maps Using a Pretrained Domain-Adapted Diffusion ModelDiffusion models → Medical imaging and segmentation
  10. It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMsKnowledge distillation → On-policy and self-distillation for LLMs
  11. FBOS-RL: Feedback-Driven Bi-Objective Synergistic Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning +1
  12. Multi-Agent Reinforcement Learning for Safe Autonomous Driving Under Pedestrian Behavioral UncertaintyEnd-to-end autonomous driving → Cooperative and V2X driving
  13. ProcCtrlBench: Evaluating Process-Level Defects and Control Preservation in LLM Coding AgentsLLM agents and tool use → Software engineering coding agents
  14. CP-MoE: Consistency-Preserving Mixture-of-Experts for Continual LearningMixture-of-experts → Mixture of LoRA experts
  15. GROW: Aligning GRPO with State-Action Modeling for Open-World VLM AgentsLLM reasoning → Reinforcement learning for reasoning +2
  16. Lean Refactor: Multi-Objective Controllable Proof Optimization via Agentic Strategy SearchLLM agents and tool use → Educational agents and math problem solving
  17. Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents?LLM agents and tool use → Web, search, and research agents
  18. MMoA: An AI-Agent framework with recurrence for Memoried Mixure-of-AgentLLM agents and tool use → General LLM agent frameworks and benchmarks
  19. Sequential Consensus for Multi-Agent LLM Debates: A Wald-SPRT compute governor with calibration-based failure detectionLLM reasoning → Reasoning for agents, planning and code +1
  20. Hallucination as Exploit: Evidence-Carrying Multimodal AgentsLLM agents and tool use → Medical and scientific domain agents
  21. Going PLACES: Participatory Localized Red Teaming for Text-to-Image Safety in the Global SouthLLM safety and security → Safety alignment, refusal and guardrails
  22. Discoverable Agent Knowledge -- A Formal Framework for Agentic KG Affordances (Extended Version)LLM agents and tool use → General LLM agent frameworks and benchmarks
  23. Supporting System Testing with a Multi-Agent LLM-based Framework for Knowledge Graph Extraction: A Case Study with Ethernet Switch SystemsLLM agents and tool use → Software engineering coding agents
  24. Prompting language influences diagnostic reasoning and accuracy of large language modelsLLM reasoning → Clinical and biomedical applications
  25. Reducing Diffusion Model Memorization with Higher Order Langevin DynamicsDiffusion models → Diffusion foundations and sampling
  26. A Heuristic Approach for Performance Tuning in RL-based Quadrotor Control via Reward Design and Termination ConditionsDeep reinforcement learning methods → RL for robot navigation and UAV control
  27. On the Geometric Limits of Transformer Defenses against Obfuscation Attacks: Latent Embedding Collapse & Performance Robustness GapLLM safety and security → Prompt injection and agent security
  28. Progressive Autonomy as Preference Learning: A Formalization of Trust Calibration for Agentic Tool UseLLM agents and tool use → Reinforcement learning for LLM agents
  29. Be Kind, Rewrite: Benign Projections via Rewriting Defend Against LLM Data Poisoning AttacksLLM safety and security → Backdoor and data poisoning attacks
  30. Learning to Hand Off: Provably Convergent Workflow Learning under Interface ConstraintsLLM agents and tool use → Software engineering coding agents
  31. COBALT: Crowdsourcing Robot Learning via Cloud-Based Teleoperation with SmartphonesOffline RL and imitation learning from data → Robot manipulation imitation learning
  32. EgoBabyVLM: Benchmarking Cross-Modal Learning from Naturalistic Egocentric Video DataMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  33. POLAR-Bench: A Diagnostic Benchmark for Privacy-Utility Trade-offs in LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance
  34. DecisionBench: A Benchmark for Emergent Delegation in Long-Horizon Agentic WorkflowsLLM agents and tool use → General LLM agent frameworks and benchmarks
  35. ReacTOD: Bounded Neuro-Symbolic Agentic NLU for Zero-Shot Dialogue State TrackingLLM agents and tool use → General LLM agent frameworks and benchmarks
  36. Generative Pseudo-Force Fields for Molecular GenerationDiffusion models → Flow matching, time series and science
  37. KVBuffer: IO-aware Serving for Linear AttentionEfficient LLM inference and serving → KV cache optimization
  38. Interference-Aware Multi-Task UnlearningLLM safety and security → Machine unlearning
  39. Trustworthy Agent Network: Trust in Agent Networks Must Be Baked In, Not Bolted OnLLM agents and tool use → Agent threats, guardrails and governance
  40. AgentNLQ: A General-Purpose Agent for Natural Language to SQLLLM agents and tool use → Web, search, and research agents
  41. Distilling Linearized Behavior into Non-Linear Fine-Tuning for Effective Task ArithmeticLLM safety and security → Machine unlearning
  42. Surviving the Unseen: Predictive Defense for Novel Multi-Turn Multimodal AttacksLLM agents and tool use → Agent threats, guardrails and governance +1
  43. TabQL: In-Context Q-Learning with Tabular Foundation ModelsDeep reinforcement learning methods → Deep RL algorithms and representations
  44. MotionMERGE: A Multi-granular Framework for Human Motion Editing, Reasoning, Generation, and ExplanationLLM reasoning → Spatial and embodied reasoning
  45. OEP: Poisoning Self-Evolving LLM Agents via Locally Correct but Non-Transferable ExperiencesLLM agents and tool use → Agent threats, guardrails and governance +1
  46. ESLD (External Surrogate Latent Defense): A Latent-Space Architecture for Faster, Stronger Prompt-Injection DefenseLLM agents and tool use → Agent threats, guardrails and governance
  47. DMN: A Compositional Framework for Jailbreaking Multimodal LLMs with Multi-Image InputsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  48. Aurora: Unified Video Editing with a Tool-Using AgentDiffusion models → Video generation +1
  49. Code as Agent HarnessLLM agents and tool use → Software engineering coding agents
  50. SURGE: Approximation and Training Free Particle Filter for Diffusion SurrogateDiffusion models → Flow matching, time series and science
  51. WorldString: Actionable World RepresentationWorld models → Latent predictive world models
  52. Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-DistillationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  53. LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video GenerationDiffusion models → Video generation +1
  54. Spectral Progressive Diffusion for Efficient Image and Video GenerationDiffusion models → Diffusion foundations and sampling
  55. EgoExoMem: Cross-View Memory Reasoning over Synchronized Egocentric and Exocentric VideosLLM reasoning → Spatial and embodied reasoning
  56. Robo-Cortex: A Self-Evolving Embodied Agent via Dual-Grain Cognitive Memory and Autonomous Knowledge InductionLLM agents and tool use → Multimodal and embodied agents +1
  57. DexHoldem: Playing Texas Hold'em with Dexterous Embodied SystemLLM agents and tool use → Multimodal and embodied agents
  58. Dexora: Open-source VLA for High-DoF Bimanual DexterityVision-language-action models → Human-video and latent-action pretraining
  59. General Preference Reinforcement LearningLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
  60. SafeDiffusion-R1: Online Reward Steering for Safe Diffusion Post-TrainingDiffusion models → Robustness, privacy and adversarial aspects +1
  61. EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RLLLM agents and tool use → Tool learning and function calling
  62. Distilling Tabular Foundation Models for Structured Health DataKnowledge distillation → General knowledge distillation methods
  63. SkillGenBench: Benchmarking Skill Generation Pipelines for LLM AgentsLLM agents and tool use → Agent skill learning and evolution
  64. Reversa: A Reverse Documentation Engineering Framework for Converting Legacy Software into Operational Specifications for AI AgentsLLM agents and tool use → Software engineering coding agents
  65. COOPO: Cyclic Offline-Online Policy Optimization AlgorithmOffline RL and imitation learning from data → Offline RL algorithms +1
  66. Position: A Three-Layer Probabilistic Assume-Guarantee Architecture Is Structurally Required for Safe LLM Agent DeploymentLLM agents and tool use → Agent threats, guardrails and governance
  67. Pocket Foundation Models: Distilling TFMs into CPU-Ready Gradient-Boosted TreesKnowledge distillation → General knowledge distillation methods
  68. MementoGUI: Learning Agentic Multimodal Memory Control for Long-Horizon GUI AgentsLLM agents and tool use → GUI and mobile agents
  69. Language-Switching Triggers Take a Latent Detour Through Language ModelsLLM safety and security → Backdoor and data poisoning attacks
  70. Post-Trained MoE Can Skip Half Experts via Self-DistillationMixture-of-experts → MoE large language models +1
  71. Leveraging Latent Visual Reasoning in SilenceLLM reasoning → Multimodal reasoning
  72. Aligned Training: A Parameter-Free Method to Improve Feature Quality and Stability of Sparse Autoencoders (SAE)Mechanistic interpretability → Sparse autoencoder training and evaluation
  73. CrossView Suite: Harnessing Cross-view Spatial Intelligence of MLLMs with Dataset, Model and BenchmarkMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  74. Unified Walking, Running, and Recovery for Humanoids via State-Dependent Adversarial Motion PriorsDeep reinforcement learning methods → RL for robot locomotion and manipulation
  75. CATA: Continual Machine Unlearning via Conflict-Averse Task ArithmeticMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  76. Starve to Perceive: Taming Lazy Perception in VLMs with Constrained Visual BandwidthMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  77. Incantation: Natural Language as the Action Interface for Multi-Entity Video World ModelsWorld models → Video-generation world models and simulators
  78. Latent Action Reparameterization for Efficient Agent InferenceLLM agents and tool use → General LLM agent frameworks and benchmarks
  79. Not What You Asked For: Typographic Attacks in Household Robot ManipulationMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  80. AMARIS: A Memory-Augmented Rubric Improvement System for Rubric-Based Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  81. Randomized Advantage Transformation (RAT): Computing Natural Policy Gradients via Direct BackpropagationDeep reinforcement learning methods → RL theory and sample complexity
  82. Overeager Coding Agents: Measuring Out-of-Scope Actions on Benign TasksLLM agents and tool use → Agent threats, guardrails and governance
  83. MA2P: A Meta-Cognitive Autonomous Intelligent Agents Framework for Complex PersuasionLLM agents and tool use → Social simulation and multi-agent debate
  84. MINTEval: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent SystemsLLM agents and tool use → Agent memory systems
  85. Improving BM25 Code Retrieval Under Fixed Generic Tokenization: Adaptive q-Log Odds as a Drop-In BM25 FixRetrieval-augmented generation → RAG for code
  86. StableHand: Quality-Aware Flow Matching for World-Space Dual-Hand Motion Estimation from Egocentric VideoDiffusion models → Diffusion and flow policies for robotics
  87. Monitoring the Internal Monologue: Probe Trajectories Reveal Reasoning DynamicsLLM reasoning → Test-time compute and efficient thinking
  88. STT-Arena: A More Realistic Environment for Tool-Using with Spatio-Temporal DynamicsLLM agents and tool use → Tool learning and function calling
  89. Probing for Representation Manifolds in SuperpositionMechanistic interpretability → Sparse autoencoder training and evaluation
  90. Beyond Scaling: Agents Are Heading to the EdgeLLM agents and tool use → General LLM agent frameworks and benchmarks
  91. Continuous Diffusion Scales Competitively with Discrete Diffusion for LanguageDiffusion models → Discrete and text diffusion
  92. AMR-SD: Asymmetric Meta-Reflective Self-Distillation for Token-Level Credit AssignmentLLM reasoning → Reinforcement learning for reasoning +2
  93. DiPRL: Learning Discrete Programmatic Policies via Architecture Entropy RegularizationDeep reinforcement learning methods → RL theory and sample complexity
  94. Implicit Hierarchical GRPO: Decoupling Tool Invocation from Execution for Tool-Integrated Mathematical ReasoningLLM reasoning → Reasoning for agents, planning and code
  95. DBES: A Systematic Benchmark and Metric Suite for Evaluating Expert Specialization in Large-Scale MoEsMixture-of-experts → Expert routing strategies
  96. Single-Round Vector RAG vs an LLM-Compiled Wiki: A Preregistered Comparison on a Small Multi-Domain Research CorpusRetrieval-augmented generation → RAG pipeline design and evaluation
  97. PERL: Parameter Efficient Reasoning in CLIP Latent SpaceLLM reasoning → Multimodal reasoning +1
  98. Scheduling That Speaks: An Interpretable Programmatic Reinforcement Learning FrameworkDeep reinforcement learning methods → RL for energy, networks and operations
  99. Code-as-Room: Generating 3D Rooms from Top-Down View Images via Agentic Code SynthesisLLM agents and tool use → Multimodal and embodied agents
  100. Modelling Customer Trajectories with Reinforcement Learning for Practical Retail InsightsDeep reinforcement learning methods → RL for energy, networks and operations
All 611
  1. What's Holding Back Latent Visual Reasoning?LLM reasoning → Multimodal reasoning
  2. Heterogeneous Tasks Offloading in Vehicular Edge Computing: A Federated Meta Deep Reinforcement Learning ApproachDeep reinforcement learning methods → RL for energy, networks and operations
  3. Seeing Together: Multi-Robot Cooperative Egocentric Spatial Reasoning with Multimodal Large Language ModelsLLM reasoning → Spatial and embodied reasoning +1
  4. REBAR: Reference Ethical Benchmark for Autonomy ReadinessLLM safety and security → Prompt injection and agent security
  5. EvoMemBench: Benchmarking Agent Memory from a Self-Evolving PerspectiveLLM reasoning → Reasoning for agents, planning and code +2
  6. Geometry-Aware Uncertainty Coresets for Robust Visual In-Context Learning in HistopathologyMultimodal LLMs / vision-language models → Medical vision-language models
  7. SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to EvolutionLLM agents and tool use → Agent skill learning and evolution
  8. NEWTON: Agentic Planning for Physically Grounded Video GenerationLLM agents and tool use → Multimodal and embodied agents
  9. Diagnosing Korean-Language LLM Political Bias via Census-Grounded Agent SimulationLLM agents and tool use → Social simulation and multi-agent debate
  10. QSTRBench: a New Benchmark to Evaluate the Ability of Language Models to Reason with Qualitative Spatial and Temporal CalculiLLM reasoning → Spatial and embodied reasoning
  11. Beyond Inference-Time Search: Reinforcement Learning Synthesizes Reusable SolversDeep reinforcement learning methods → RL training of language and agent models
  12. GeoFlow: Enforcing Implicit Geometric Consistency in Video GenerationDiffusion models → 3D, point cloud and scene generation
  13. RAVE: Re-Allocating Visual Attention in Large Multimodal ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  14. Presupposition and Reasoning in Conditionals: A Theory-Based Study of Humans and LLMsLLM reasoning → Reasoning benchmarks and evaluation
  15. Focused Forcing: Content-Aware Per-Frame KV Selection for Efficient Autoregressive Video DiffusionDiffusion models → Video generation
  16. Same Signal, Different Semantics: A Cross-Framework Behavioral Analysis of Software Engineering AgentsLLM agents and tool use → Software engineering coding agents
  17. Mixture-of-Experts Diffusion Models for Adaptive Massive MIMO Channel Estimation via Variational Bayesian InferenceDiffusion models → Diffusion for compression and wireless
  18. ISEP: Implicit Support Expansion for Offline Reinforcement Learning via Stochastic Policy OptimizationOffline RL and imitation learning from data → Offline RL algorithms
  19. Wasserstein Equilibrium Decoding for Reliable Medical Visual Question AnsweringMultimodal LLMs / vision-language models → Medical vision-language models
  20. Alignment Dynamics in LLM Fine-TuningLLM alignment / RLHF / preference optimisation → LLM preference optimization methods +1
  21. PH-Dreamer: A Physics-Driven World Model via Port-Hamiltonian Generative DynamicsWorld models → Latent predictive world models
  22. SD-Search: On-Policy Hindsight Self-Distillation for Search-Augmented ReasoningKnowledge distillation → On-policy and self-distillation for LLMs
  23. StableVLA: Towards Robust Vision-Language-Action Models without Extra DataVision-language-action models → VLA architectures and generalization
  24. CommitDistill: A Lightweight Knowledge-Centric Memory Layer for Software RepositoriesLLM agents and tool use → Software engineering coding agents
  25. SRC-Flow: Compact Semantic Representations Enable Normalizing Flows for Image GenerationDiffusion models → Flow matching, time series and science
  26. Knowledge-to-Verification: Exploring RLVR for LLMs in Knowledge-Intensive DomainsLLM reasoning → Reinforcement learning for reasoning
  27. Machine Unlearning for Masked Diffusion Language ModelsDiffusion models → Discrete and text diffusion +1
  28. Privacy Preserving Reinforcement Learning with One-Sided FeedbackDeep reinforcement learning methods → RL for energy, networks and operations
  29. Multilingual jailbreaking of LLMs using low-resource languagesLLM safety and security → Jailbreaking
  30. Are Sparse Autoencoder Benchmarks Reliable?Mechanistic interpretability → SAE features and their applications
  31. SPATIOROUTE: Dynamic Prompt Routing for Zero-Shot Spatial ReasoningLLM reasoning → Spatial and embodied reasoning +1
  32. Forward-Learned Discrete Diffusion: Learning how to noise to denoise fasterDiffusion models → Diffusion foundations and sampling
  33. Concise and Logically Consistent Conformal Sets for Neuro-Symbolic Concept-Based ModelsLLM reasoning → Reasoning benchmarks and evaluation
  34. Beyond the Cartesian Illusion: Testing Two-Stage Multi-Modal Theory of Mind under Perceptual BottlenecksMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  35. Pairwise Preference Reward and Group-Based Diversity Enhancement for Superior Open-Ended GenerationLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  36. Dual-Rate Diffusion: Accelerating diffusion models with an interleaved heavy-light networkDiffusion models → Diffusion foundations and sampling
  37. MARS: Technical Report for the CASTLE Challenge at EgoVis 2026LLM agents and tool use → Multimodal and embodied agents
  38. Acoustic Interference: A New Paradigm Weaponizing Acoustic Latent Semantic for Universal Jailbreak against Large Audio Language ModelsLLM safety and security → Audio jailbreaks and speech backdoors
  39. Elastic-dLLM: Position Preserving Context Compression and Augmentation of Diffusion LLMsEfficient LLM inference and serving → Diffusion LLM and MoE inference
  40. Self-Evolving Spatial Reasoning in Vision Language Models via Geometric Logic ConsistencyLLM reasoning → Spatial and embodied reasoning +2
  41. Vision Inference Former: Sustaining Visual Consistency in Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  42. Three Heads Are Better Than One: A Multi-perspective Reasoning Framework for Enhanced Vulnerability DetectionLLM reasoning → Reasoning for agents, planning and code
  43. Whispers in the Noise: Surrogate-Guided Concept Awakening via a Multi-Agent FrameworkDiffusion models → Robustness, privacy and adversarial aspects
  44. Xiaomi Auto World Model: A Joint World Model Integrating Reconstruction and Generation for Autonomous DrivingWorld models → World models for autonomous driving +1
  45. An Empirical Study of Privacy Leakage Chains via Prompt Injection in Black-Box Chatbot EnvironmentsLLM safety and security → Prompt injection and agent security
  46. How Good LLMs Are at Answering Bangla Medical Visual Questions? Dataset and BenchmarkingMultimodal LLMs / vision-language models → Medical vision-language models
  47. Symmetry-Compatible Principle for Optimizer Design: Embeddings, LM Heads, SwiGLU MLPs, and MoE RoutersMixture-of-experts → MoE theory and gating functions
  48. Safety Geometry Collapse in Multimodal LLMs and Adaptive Drift CorrectionMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  49. SENSE: Satellite-based ENergy Synthesis for Sustainable EnvironmentDiffusion models → 3D, point cloud and scene generation
  50. A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAMDelta Integration into Upcycled MoEMixture-of-experts → MoE large language models
  51. The Expressive Power of Low Precision Softmax Transformers with (Summarized) Chain-of-ThoughtLLM reasoning → Prompting and chain-of-thought reasoning
  52. LLM-Guided Communication for Cooperative Multi-Agent Reinforcement LearningLLM agents and tool use → General LLM agent frameworks and benchmarks
  53. KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM InferenceEfficient LLM inference and serving → KV cache optimization
  54. Wasserstein bounds for denoising diffusion probabilistic models via the F"ollmer processDiffusion models → Diffusion foundations and sampling
  55. PPAI: Enabling Personalized LLM Agent Interoperability for Collaborative Edge IntelligenceLLM agents and tool use → General LLM agent frameworks and benchmarks
  56. Bench2Drive-Robust: Benchmarking Closed-Loop Autonomous Driving under Deployment PerturbationsEnd-to-end autonomous driving → End-to-end system architecture
  57. FLAG: Foundation model representation with Latent diffusion Alignment via Graph for spatial gene expression predictionDiffusion models → Medical imaging and segmentation
  58. Protection Is (Nearly) All You Need: Structural Protection Dominates Scoring in Globally Capped KV EvictionEfficient LLM inference and serving → KV cache optimization
  59. DocOS: Towards Proactive Document-Guided Actions in GUI AgentsLLM agents and tool use → GUI and mobile agents
  60. OmniSelect: Dynamic Modality-Aware Token Compression for Efficient Omni-modal Large Language ModelsEfficient LLM inference and serving → Audio and omni-modal token compression
  61. Connections between the F"ollmer process and the denoising diffusion probabilistic modelDiffusion models → Diffusion foundations and sampling
  62. PROTEA: Offline Evaluation and Iterative Refinement for Multi-Agent LLM WorkflowsLLM agents and tool use → Software engineering coding agents
  63. What Matters for Grocery Product Retrieval with Open Source Vision Language ModelsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  64. FedSDR: Federated Self-Distillation with RectificationKnowledge distillation → Federated, robust and private distillation
  65. Stable Audio 3Diffusion models → Audio, speech and music
  66. Predictive Prefetching for Retrieval-Augmented GenerationRetrieval-augmented generation → Generation and context integration
  67. LivePI: More Realistic Benchmarking of Agents Against Indirect Prompt InjectionLLM agents and tool use → Agent threats, guardrails and governance +1
  68. Learning to Balance: Decoupled Siamese Diffusion Transformer for Reference-Based Remote Sensing Image Super-ResolutionDiffusion models → Inverse problems and image restoration
  69. Babel: Jailbreaking Safety Attention via Obfuscation Distribution Optimized SamplingLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  70. Generation Navigator: A State-Aware Agentic Framework for Image GenerationLLM agents and tool use → Multimodal and embodied agents
  71. BLAgent: Agentic RAG for File-Level Bug LocalizationRetrieval-augmented generation → RAG for code +1
  72. From Detection to Response: A Deep Learning and Retrieval-Augmented Generation Framework for Network Intrusion MitigationRetrieval-augmented generation → Privacy and security of RAG
  73. Enhancing the Code Reasoning Capabilities of LLMs via Consistency-based Reinforcement LearningLLM reasoning → Reasoning for agents, planning and code
  74. A More Word-like Image Tokenization for MLLMsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  75. SkyNative: A Native Multimodal Architecture for Remote Sensing Vision-Language UnderstandingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  76. SVFSearch: A Multimodal Knowledge-Intensive Benchmark for Short-Video Frame Search in the Gaming Vertical DomainMultimodal LLMs / vision-language models → Video understanding with MLLMs
  77. Training data attribution in diffusion models via mirrored unlearning and noise-consistent skewDiffusion models → Diffusion foundations and sampling +1
  78. AtlasVA: Self-Evolving Visual Skill Memory for Teacher-Free VLM AgentsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +2
  79. Prompt Compression in Diffusion Large Language Models: Evaluating LLMLingua-2 on LLaDAEfficient LLM inference and serving → Prompt and context compression
  80. AdaptiveLoad: Towards Efficient Video Diffusion Transformer TrainingWorld models → Video-generation world models and simulators +1
  81. PanoWorld: A Generative Spatial World Model for Consistent Whole-House Panorama SynthesisWorld models → Video-generation world models and simulators
  82. WorldArena 2.0: Extending Embodied World Model Benchmarking on Modality, Functionality and PlatformWorld models → World models for navigation
  83. Ethical Hyper-Velocity (EHV): A Hardware-Rooted Zero-Trust Runtime Enforcement Architecture for Agentic AI SystemsLLM agents and tool use → Agent threats, guardrails and governance
  84. Agentic Chunking and Bayesian De-chunking of AI Generated Fuzzy Cognitive Maps: A Model of the Thucydides TrapLLM agents and tool use → Medical and scientific domain agents
  85. Evaluating Cognitive Age Alignment in Interactive AI AgentsLLM reasoning → Reasoning benchmarks and evaluation +2
  86. CoX-MoE: Coalesced Expert Execution for High-Throughput MoE Inference with AMX-Enabled CPU-GPU Co-ExecutionMixture-of-experts → Efficient MoE training and inference systems
  87. Multi-agent AI systems outperform human teams in creativityLLM agents and tool use → General LLM agent frameworks and benchmarks
  88. PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent OptimizationLLM reasoning → Reinforcement learning for reasoning +2
  89. HINT-SD: Targeted Hindsight Self-Distillation for Long-Horizon AgentsLLM agents and tool use → Reinforcement learning for LLM agents +1
  90. DAD4TS: Data-Augmentation-Oriented Diffusion Model for Time-Series Forecasting with Small-Scale DataDiffusion models → Flow matching, time series and science +1
  91. boldsymbolf-OPD: Stabilizing Long-Horizon On-Policy Distillation with Freshness-Aware ControlKnowledge distillation → On-policy and self-distillation for LLMs
  92. KISS - Knowledge Infrastructure for Scientific Simulation: A Scaffolding for Agentic Earth ScienceLLM agents and tool use → Multimodal and embodied agents
  93. Simple Approximation and Derivative Free Inference-Time Scaling for Diffusion Models via Sequential Monte Carlo on Path MeasuresLLM reasoning → Diffusion reasoning and test-time scaling +2
  94. Balancing Knowledge Distillation for Imbalance Learning with Bilevel OptimizationKnowledge distillation → General knowledge distillation methods
  95. Temporal Aware Pruning for Efficient Diffusion-based Video GenerationDiffusion models → Video generation +1
  96. Stabilizing, Scaling & Enhancing MeanFlow for Large-scale Diffusion DistillationDiffusion models → Diffusion foundations and sampling
  97. Agentic Cost-Aware Query Planning with Knowledge Distillation for Big Data AnalyticsLLM agents and tool use → Web, search, and research agents +1
  98. Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  99. CounterCount: A Diagnostic Framework for Counting Bias in Vision Language ModelsLLM reasoning → Multimodal reasoning +1
  100. Why We Look Where We Look: Emergent Human-like Fixations of a Foveated Visual Language Model Maximizing Scene UnderstandingMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  101. STRIDE: A Self-Reflective Agent Framework for Reliable Automatic Equation DiscoveryLLM agents and tool use → Web, search, and research agents
  102. Self-Distillation is Optimal Among Spectral Shrinkage Estimators in Spiked Covariance ModelsKnowledge distillation → General knowledge distillation methods
  103. Internalizing Tool Knowledge in Small Language Models via QLoRA Fine-TuningLLM agents and tool use → Tool learning and function calling
  104. Entropy-Gradient Inversion: Moving Toward Internal Mechanism of Large Reasoning ModelsLLM reasoning → Reinforcement learning for reasoning
  105. LatentUMM: Dual Latent Alignment for Unified Multimodal ModelsLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  106. FrequencyBooster: Full-Frequency Modeling for High-Fidelity Pixel DiffusionDiffusion models → Diffusion foundations and sampling
  107. Memisis: Orchestrating and Evaluating Synthetic Data for Tabular Health DatasetsSynthetic data and self-improvement for LLMs → Medical synthetic data and agents
  108. OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache QuantizationEfficient LLM inference and serving → KV cache quantization
  109. MoASE++: Mixture of Activation Sparsity Experts with Domain-Adaptive On-policy Distillation for Continual Test Time AdaptationKnowledge distillation → Multimodal distillation
  110. Harnessing LLM Agents with Skill ProgramsLLM agents and tool use → Agent skill learning and evolution
  111. Divergence-Suppressing Couplings for Rectified FlowDiffusion models → Flow matching, time series and science
  112. EXG: Self-Evolving Agents with Experience GraphsLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  113. Patch-MoE Mamba: A Patch-Ordered Mixture-of-Experts State Space Architecture for Medical Image SegmentationMixture-of-experts → Medical and biomedical MoE +1
  114. Sometin Beta Pass Notin: Improving Multilingual ASR for Nigerian Languages via Knowledge DistillationKnowledge distillation → Speech and audio distillation
  115. Auditing Bias and Safety in Voice AI Customer Care
  116. Digital Harf: A Clinically Integrated Multimodal AI System for Pervasive Arabic Speech and Language Therapy
  117. Same Question, Different Answers: Evaluating LLM Reliability Beyond Accuracy
  118. From Obligation to Specification: A Survey on Validating EU AI Act Requirements in RE
  119. Stochastic Sampling is Epistemically Shallow: The Dimensionality Gap Between Temperature Variation and Model Diversity in LLMs
  120. ClickGuard: Detecting and Spoiling Clickbait News with Informativeness Measures and Large Language Models
  121. HAAS Studio: A Tool for Simulating, Benchmarking, and Governing Human-AI Work Allocation
  122. Generativism: Toward a Learning Theory for the Age of Generative Artificial Intelligence
  123. Position: Generative Engine Optimization Creates Underexamined Risks, Governance Must Target Concentration, Disclosure, and Academic Blind Spots
  124. Physics-Informed Neural Networks for Radial Consolidation of Combined Electroosmotic, Vacuum and Surcharge Preloading Considering Smear Effects
  125. Reinterpreting Safety Thresholds as Neuron Spiking Thresholds
  126. Quantum Machine Learning-based 6G edge Network: Enabling Adaptive Communication and Model Aggregation
  127. Can Quantum Federated Learning Withstand Circuit-Level Backdoors?
  128. Rapid online deep artifact suppression for real-time spiral bSSFP CMR with blipped-CAIPI simultaneous multi-slice imaging at 1.5 T
  129. Toxicity in Twitch Chats: An LLM-Based Analysis Across Gaming Communities
  130. Brain-to-Image Retrieval and Reconstruction via Multimodal EEG Alignment
  131. Task-Aligned Self-Supervised Learning for Medical Image Analysis: A Task-Oriented Review with Practical Design Guidelines
  132. Topological Signal Processing: An Application-Oriented Tutorial
  133. Expressive Power of Deep Homomorphism Networks over Relational Databases
  134. Neural Acceleration for Graph Partitioning
  135. Multi-Head Attention as Ensemble Nadaraya-Watson Estimation: Variance Reduction, Decorrelation, and Optimal Head Diversity
  136. Conformal Selective Acting: Anytime-Valid Risk Control for RLVR-Trained LLMs
  137. Catching a Moving Subspace: Low-Rank Bandits Beyond Stationarity
  138. Chronicle: A Multimodal Foundation Model for Joint Language and Time Series Understanding
  139. Residual Paving: Diagnosing the Routing Bottleneck in Selective Refusal Editing
  140. Instance Discrimination for Link Prediction
  141. Efficient Table QA via TableGrid Navigation and Progressive Inference Prompting
  142. Physics-informed convolutional neural networks for fluid flow through porous media
  143. Automated Kernel Discovery Towards Understanding High-dimensional Bayesian Optimization
  144. Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification
  145. Prism: Structural Symmetry Scanning via Duality-Constrained Laplacian Projection
  146. LEAP: A closed-loop framework for perovskite precursor additive discovery
  147. Geometry-Lite: Interpretable Safety Probing via Layer-Wise Margin Geometry
  148. The Thermodynamic Costs of Simple Linear Regression
  149. Planner-Admissible Graph-PDE Value Extensions for Sparse Goal-Conditioned Planning
  150. A Cloud-Based Tool for Meteorite Recovery Using Drones and Machine Learning
  151. Activation Functions, Statistics and Learning of Higher-Order Interactions in Restricted Boltzmann Machines
  152. Bridge: Retrieval-Augmented Spatiotemporal Modeling for Urban Delivery Demand
  153. How Far Are We From True Auto-Research?
  154. Efficient coding along the visual hierarchy
  155. Information Processing Capacity of Stationary Physical Systems: Theory, Data-efficient Estimation Methods, and Photonic Demonstration
  156. Flash PD-SSM: Memory-Optimized Structured Sparse State-Space Models
  157. Agent Meltdowns: The Road to Hell Is Paved with Helpful Agents
  158. PMF-CL: Pareto-Minimal-Forgetting Continual Learner for Conflicting Tasks
  159. GRASP: Deterministic argument ranking in interaction graphs
  160. Towards Data-Efficient Video Pre-training with Frozen Image Foundation Models
  161. Identifiable Multimodal Causal Representation Learning under Partial Latent Sharing
  162. Knowing When Not to Predict: Self Supervised Learning and Abstention for Safer DR Screening
  163. CLIC: Contextual Language-Informed Cardiac Pathology Classification
  164. Atomistic Modeling of Chemical Disorder in Materials: Bridging Conventional Methods and AI-Assisted Approaches
  165. Dual-Channel Tensor Neural Networks: Finite-Sample Theory and Conformal Structure Selection
  166. GOAL: Graph-based Objective-Aligned Diffusion Solvers for Dynamic Multi-Objective Optimization
  167. Learning Interpretable Point-Based Clinical Risk Scores via Direct Optimization
  168. FAGER: Factually Grounded Evaluation and Refinement of Text-to-Image Models
  169. Performance Monitoring of Proton Exchange Membrane Water Electrolyzer by Transformers-Based Machine Learning Model
  170. Neural Operators for Design-Space Surrogate Modeling of Tendon-Actuated Continuum Robots
  171. Heterogeneity-Aware Dataset Scheduling for Efficient Audio Large Language Model Training
  172. ScheduleFree+: Scaling Learning-Rate-Free & Schedule-Free Learning to Large Language Models
  173. Embedding by Elicitation: Dynamic Representations for Bayesian Optimization of System Prompts
  174. Counterfactual Likelihood Tests for Indirect Influence in Private Reasoning Channels
  175. Chessformer: A Unified Architecture for Chess Modeling
  176. MANGO: Meta-Adaptive Network Gradient Optimization for Online Continual Learning
  177. The impact of observation density on Bayesian inversion of latent dynamics in shock-dominated flows
  178. CRAFT: Critic-Refined Adaptive Key-Frame Targeting for Multimodal Video Question Answering
  179. Learning Long-Term Temporal Dependencies in Photovoltaic Power Output Prediction Through Multi-Horizon Forecasting
  180. Riemannian Networks over Full-Rank Correlation Matrices
  181. Benchmarking Commercial ASR Systems on Code-Switching Speech: Arabic, Persian, and German
  182. The Annotation Scarcity Paradox in Low-Resource NLP Evaluation: A Decade of Acceleration and Emerging Constraints
  183. Toward an AI-Powered Computational Testbed for Workforce Policy
  184. Mapping Uncharted Symmetries: Machine Discovery in Combinatorics
  185. LiFT: Lifted Inter-slice Feature Trajectories for 3D Image Generation from 2D Generators
  186. Provably Data-driven Lagrangian Relaxation for Mixed Integer Linear Programming
  187. Automated Grading of Handwritten Mathematics Using Vision-Capable LLMs
  188. Guiding Neuro-Symbolic Scenario Generation with Spatio-Temporal Logic
  189. RLFTSim: Realistic and Controllable Multi-Agent Traffic Simulation via Reinforcement Learning Fine-Tuning
  190. Personalized Face Privacy Protection From a Single Image
  191. KAN-MLP-Mixer: A comprehensive investigation of the usage of Kolmogorov-Arnold Networks (KANs) for improving IMU-based Human Activity Recognition
  192. Learning When to Adapt
  193. MedFM-Robust: Benchmarking Robustness of Medical Foundation Models
  194. Conformal Prediction via Transported Beta Laws
  195. Deep Neural Sheaf Diffusion
  196. A Systematic Failure Analysis of Vision Foundation Models for Open Set Iris Presentation Attack Detection
  197. LoRA vs. Full Fine-Tuning: A Theoretical Perspective
  198. SAGA: A Sequence-Adaptive Generative Architecture for Multi-Horizon Probabilistic Forecasting with Adaptive Temporal Conformal Prediction
  199. Learn-by-Wire Training Control Governance: Bounded Autonomous Training Under Stress for Stability and Efficiency
  200. Causal Inference with Categorical Unobserved Confounder via Mixture Learning
  201. EgoTraj: Real-World Egocentric Human Trajectory Dataset for Multimodal Prediction
  202. Distance-Aware Muon: Adaptive Step Scaling for Normalized Optimization
  203. Agent Security is a Systems Problem
  204. Artifact-Bench: Evaluating MLLMs on Detecting and Assessing the Artifacts of AI-Generated Videos
  205. Harnessing Self-Supervised Features for Art Classification
  206. Shaping the Prior: How Synthetic Task Distributions Determine Tabular Foundation Model Quality
  207. Hyrax: An Extensible Framework for Rapid ML Experimentation and Unsupervised Discovery in the Era of Rubin, Roman, and Euclid
  208. Evaluating the Utility of Personal Health Records in Personalized Health AI
  209. FedMental: Evaluating Federated Learning for Mental Health Detection from Social Media Data
  210. A Geometric Analysis of Sign-Magnitude Asymmetry in a ReLU + RMSNorm Block under Ternary Quantization
  211. HypergraphFormer: Learning Hypergraphs from LLMs for Editable Floor Plan Generation
  212. Markov Chain Decoders Overcome the Heavy-Tail Limitations of Lipschitz Generative Models
  213. Bayesian Latent Space Models for Graphs Are Misspecified: Toward Robust Inference via Generalized Posteriors
  214. From Division to Decision: Leveraging Temporal Cell-Stage Segmentation for Embryo Transferability Prediction
  215. SynGR: Unleashing the Potential of Cross-Modal Synergy for Generative Recommendation
  216. MoCo-EA: Exploiting Adversarial Mode Connectivity for Efficient Evolutionary Attacks
  217. CounterFlow: A Two-Phase Inference-Time Sampling for Counterfactual Video Foley Generation
  218. Can These Views Be One Scene? Evaluating Multiview 3D Consistency when 3D Foundation Models Hallucinate
  219. DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention
  220. A Readiness-Driven Runtime for Pipeline-Parallel Training under Runtime Variability
  221. WavFlow: Audio Generation in Waveform Space
  222. ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop
  223. What Does the AI Doctor Value? Auditing Pluralism in the Clinical Ethics of Language Models
  224. PIXLRelight: Controllable Relighting via Intrinsic Conditioning
  225. Advancing Narrative Long Video Generation via Training-Free Identity-Aware Memory
  226. Predictable Confabulations: Factual Recall by LLMs Scales with Model Size and Topic Frequency
  227. Semantic Generative Tuning for Unified Multimodal Models
  228. Learned Memory Attenuation in Sage-Husa Kalman Filters for Robust UAV State Estimation
  229. Learning Normal Representations for Blood Biomarkers
  230. A Large-Scale Study on the Accuracy vs Cost Trade-offs of Training and Evaluation Settings in Fine-Grained Image Recognition
  231. PopPy: Opportunistically Exploiting Parallelism in Python Agentic Workflows
  232. Ensembling Tabular Foundation Models - A Diversity Ceiling And A Calibration Trap
  233. Can Adaptive Gradient Methods Converge under Heavy-Tailed Noise? A Case Study of AdaGrad
  234. Democratizing Large-Scale Re-Optimization with LLM-Guided Model Patches
  235. Can machine learning for quantum-gas experiments be explainable?
  236. Learning Quantifiable Visual Explanations Without Ground-Truth
  237. CMAG: Concept-Scaffolded Retrieval for Marketplace Avatar Generation
  238. Lance: Unified Multimodal Modeling by Multi-Task Synergy
  239. Efficient Lookahead Encoding and Abstracted Width for Learning General Policies in Classical Planning
  240. Generative AI Advertising as a Problem of Trustworthy Commercial Intervention
  241. Better Together: Evaluating the Complementarity of Earth Embedding Models
  242. A No-Defense Defense Against Gradient-Based Adversarial Attacks on ML-NIDS: Is Less More?
  243. GIM: Evaluating models via tasks that integrate multiple cognitive domains
  244. Efficient and Noise-Tolerant PAC Learning of Multiclass Linear Classifiers
  245. AI for Auto-Research: Roadmap & User Guide
  246. KairosHope: A Next-Generation Time-Series Foundation Model for Specialized Classification via Dual-Memory Architecture
  247. Statistical Limits and Efficient Algorithms for Differentially Private Federated Learning
  248. An Assessment of Human vs. Model Uncertainty in Soft-Label Learning and Calibration
  249. Articulation in Prime: Primitive-Based Articulated Object Understanding from a Single Casual Video
  250. SPIKE: An Adaptive Dual Controller Framework for Cost-Efficient Long-Horizon Game Agents
  251. Data Presentation Over Architecture: Resampling Strategies for Credit Risk Prediction with Tabular Foundation Models
  252. Stable Causal Discovery via Directed Acyclic Graph Aggregation
  253. Position: Weight Space Should Be a First-Class Generative AI Modality
  254. SCICONVBENCH: Benchmarking LLMs on Multi-Turn Clarification for Task Formulation in Computational Science
  255. Learning Lifted Action Models from Traces with Minimal Information About Actions and States
  256. Learning to Look Benign: Targeted Evasion of Malware Detectors via API Import Injection
  257. An Approximation Algorithm for Graph Label Selection
  258. Stochastic Penalty-Barrier Method for Constrained Machine Learning
  259. ManiSoft: Towards Vision-Language Manipulation for Soft Continuum Robotics
  260. SAME: A Semantically-Aligned Music Autoencoder
  261. Perfect Parallelization in Mini-Batch SGD with Classical Momentum Acceleration
  262. Dance Across Shifts: Forward-Facilitation Continual Test-Time Adaptation through Dynamic Style Bridging
  263. Forecasting Downstream Performance of LLMs With Proxy Metrics
  264. PACE-FNO: Physics-Aligned Canonical Equivariance for Fourier Neural Operators
  265. Resolving Representation Ambiguity in Feedforward Novel View Synthesis Transformer via Semantic-Spatial Decoupling
  266. Pointwise Generalization in Deep Neural Networks
  267. PACE: Geometry-Aware Bridge Transport for Single-Cell Trajectory Inference
  268. When Outcome Looks Right But Discipline Fails: Trace-Based Evaluation Under Hidden Competitor State
  269. S2Aligner: Pair-Efficient and Transferable Pre-Training for Sparse Text-Attributed Graphs
  270. OmniPro: A Comprehensive Benchmark for Omni-Proactive Streaming Video Understanding
  271. scHelix: Asymmetric Dual-Stream Integration via Explicit Gene-Level Disentanglement
  272. Query-Conditioned Knowledge Alignment for Reliable Cross-System Medical Reasoning
  273. GUT-IS: A Data-Driven Approach to Integrating Constructs and Their Relations in Information Systems
  274. Readers make targeted regressions to plausible errors in reanalysis of "noisy-channel garden-path" sentences
  275. Estimating Item Difficulty with Large Language Models as Experts
  276. Self-supervised local learning rules learn the hidden hierarchical structure of high-dimensional data
  277. Key-Gram: Extensible World Knowledge for Embodied Manipulation
  278. Federated Martingale Posterior Samping
  279. Protein Fold Classification at Scale: Benchmarking and Pretraining
  280. VISAFF: Speaker-Centered Visual Affective Feature Learning for Emotion Recognition in Conversation
  281. LESSViT: Robust Hyperspectral Representation Learning under Spectral Configuration Shift
  282. XCTFormer: Leveraging Cross-Channel and Cross-Time Dependencies for Enhanced Time-Series Analysis
  283. Tight Complexity of Muon under Heavy-Tailed Noise
  284. Beyond Morphology: Quantifying the Diagnostic Power of Color Features in Cancer Classification
  285. Easier to Judge than to Find: Predicting In-Context Learning Success for Demonstration Selection
  286. A Practical Noise2Noise Denoising Pipeline for High-Throughput Raman Spectroscopy
  287. Offline Contextual Bandits in the Presence of New Actions
  288. Weakly Supervised Cross-Modal Learning for 4D Radar Scene Flow Estimation
  289. Ancient Greek to Modern Greek Machine Translation: A Novel Benchmark and Fine-Tuning Experiments on LLMs and NMT Models
  290. Benchmarking transferability of SSL pretraining to same and different modality segmentation tasks
  291. Modality vs. Morphology: A Framework for Time Series Classification for Biological Signals
  292. OCCAM: Open-set Causal Concept explAnation and Ontology induction for black-box vision Models
  293. AI4BayesCode: From Natural Language Descriptions to Validated Modular Stateful Bayesian Samplers
  294. GAMMA: Global Bit Allocation for Mixed-Precision Models under Arbitrary Budgets
  295. Prompt2Fingerprint: Plug-and-Play LLM Fingerprinting via Text-to-Weight Generation
  296. Flowing with Confidence
  297. Shallow ReLUs Networks in Lp-Type and Sobolev Spaces: Approximation and Path-Norm Controlled Generalization
  298. InstructAV2AV: Instruction-Guided Audio-Video Joint Editing
  299. Speech-Guided Multimodal Learning for Vocal Tract Segmentation in Real-Time MRI
  300. From BERT to T5: A Study of Named Entity Recognition
  301. When Fireflies Cluster; Enhancing Automatic Clustering via Centroid-Guided Firefly Optimization
  302. Adaptive Experimentation for Censored Survival Outcomes
  303. NeRF-based Spacecraft Reconstruction from Monocular Imagery Under Illumination Variability and Pose Uncertainty
  304. Building Reliable Arithmetic Multipliers Under NBTI Aging and Process Variations
  305. A Dataset for the Recognition of Historical and Handwritten Music Scores in Western Notation
  306. TIGER-FG: Text-Guided Implicit Fine-Grained Grounding for E-commerce Retrieval
  307. Text2CAD-Bench: A Benchmark for LLM-based Text-to-Parametric CAD Generation
  308. Generative Adversarial Learning from Deterministic Processes
  309. Generalized Functional ANOVA: A Complete Theoretical Framework
  310. Prompts Don't Protect: Architectural Enforcement via MCP Proxy for LLM Tool Access Control
  311. Cracks in the Foundation: A Civil Infrastructure Dataset to Challenge Vision Foundation Models
  312. Historical Knowledge Graphs for Global Maritime Estimated Time of Arrival
  313. Qumus: Realization of An Embodied AI Quantum Material Experimentalist
  314. Computational aspects of the Volterra Signature
  315. Generalize cross-ratios in n-dimensional Plane-Based Geometric Algebra
  316. Vision Foundation Models as Generalist Tokenizers for Image Generation
  317. Spherical Harmonic Optimal Transport: Application to Climate Models Comparisons
  318. Graph Hierarchical Recurrence for Long-Range Generalization
  319. Towards Ubiquitous Mapping and Localization for Dynamic Indoor Environments
  320. TabH2O: A Unified Foundation Model for Tabular Prediction
  321. Probing SMEFT Operators through tbarttbart Production with Hyper-Graph Neural Networks at the LHC
  322. Generating Physically Consistent Molecules with Energy-Based Models
  323. Beyond Square Roots: A Memory-Efficient Explicit Factorization for Multi-Epoch Private Learning
  324. Dynamic robotic cloth folding with efficient Koopman operator-based model predictive control
  325. The Hidden Cost of Contextual Sycophancy: an AI Literacy Intervention in Human-AI Collaboration
  326. On Stability and Decomposition of Sample Quantiles under Heavy-Tailed Distributions
  327. Proximal basin hopping: global optimization with guarantees
  328. Decoupled Conformal Optimisation: Efficient Prediction Sets via Independent Tuning and Calibration
  329. Optimising CSRNet with parameter-free attention mechanisms for crowd counting in public transport
  330. Hybrid Quantum-Classical Neural Architecture Search
  331. Robust Player-Conditional Champion Ranking for League of Legends: Style Similarity, Mastery Priors, and Archetype-Constrained Discovery
  332. Infini-News: Efficiently Queryable Access to 1.3 Billion Processed Common Crawl News Articles
  333. 3D Skew Gaussian Splatting with Any Camera Trajectory Visualization Engine
  334. QLIF-CAST: Quantum Leaky-Integrate-and-Fire for Time-Series Weather Forecasting
  335. Prune, Update and Trim: Robust Structured Pruning for Large Language Models
  336. Lost in the Folds: When Cross-Validation Is Not a Deep Ensemble for Uncertainty Estimation
  337. CineMatte: Background Matting for Virtual Production and Beyond
  338. Causely: A Causal Intelligence Layer for Enterprise AI A Benchmark Study on SRE and Reliability Workflows
  339. Improved Baselines with Representation Autoencoders
  340. The Symmetries of Three-Layer ReLU Networks
  341. Dynamic Elliptical Graph Factor Models via Riemannian Optimization with Geodesic Temporal Regularization
  342. Attention-based PCA
  343. DARE-EEG: A Foundation Model for Mining Dual-Aligned Representation of EEG
  344. Collision-Resistant Single-Pass Method for Unsupervised Fine-Grained Image Hashing
  345. Temporal Task Diversity: Inductive Biases Under Non-Stationarity in Synthetic Sequence Modelling
  346. Geometric Dictionary Learning of Dynamical Systems with Optimal Transport
  347. From Volume to Value: Preference-Aligned Memory Construction for On-Device RAG
  348. RT-Splatting: Joint Reflection-Transmission Modeling with Gaussian Splatting
  349. CodeBind: Decoupled Representation Learning for Multimodal Alignment with Unified Compositional Codebook
  350. GaussianZoom: Progressive Zoom-in Generative 3D Gaussian Splatting with Geometric and Semantic Guidance
  351. Subject-Specific Analysis of Self-Initiated Attention Shifts from EEG with Controlled Internal and External Attention Conditions
  352. A Unified Framework for Structured Flow Modeling: From Representation to Verification and Model Discovery
  353. Non-Colliding Biometric Identities for Digital Entities: Geometry, Capacity, and Million-Scale Virtual Identity Provisioning
  354. Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos
  355. SomaliWeb v1: A Quality-Filtered Somali Web Corpus with a Matched Tokenizer and a Public Language-Identification Benchmark
  356. Attacking the First-Principle: A Black-Box, Query-Free Targeted Mimicry Attack on Binary Function Classifiers
  357. Context Memorization for Efficient Long Context Generation
  358. RST: certifying and constructing prescribed information in variational autoencoders
  359. SIREM: Speech-Informed MRI Reconstruction with Learned Sampling
  360. EgoInteract: Synthetic Egocentric Videos Generation for Interaction Understanding and Anticipation
  361. Leveraging Graph Structure in Seq2Seq Models for Knowledge Graph Link Prediction
  362. PIPER: Content-Based Table Search via profiling and LLM-Generated Pseudoqueries
  363. RGB-only Active 3D Scene Graph Generation for Indoor Mobile Robots
  364. Best Segmentation Buddies for Image-Shape Correspondence
  365. View-Aware Semantic Alignment for Aerial-Ground Person Re-Identification
  366. UTOPYA: A Multimodal Deep Learning Framework for Physics-Informed Anomaly Detection and Time-Series Prediction
  367. Fixed External Cameras as Common Prior Maps for Active 3D Scene Graph Generation
  368. Scalable Environments Drive Generalizable Agents
  369. Canonical Regularisation of Wide Feature-Learning Neural Networks
  370. Token-Space Mask Prediction for Efficient Vision Transformer Segmentation
  371. Ringmaster LMO: Asynchronous Linear Minimization Oracle Momentum Method
  372. Do You Need Text Rectification? Soft Attention Mask Embedding for Rectification-Free Scene Text Spotting
  373. Visualizing the Invisible: Generative Visual Grounding Empowers Universal EEG Understanding in MLLMs
  374. Buffer-Parameterized Machine Learning Surrogate Models for Cross-Technology Signal Integrity Analysis and Optimization
  375. TRACE: Trajectory Correction from Cross-layer Evidence for Hallucination Reduction
  376. Semi-LAR: Semi-supervised Contrastive Learning with Linear Attention for Removal of Nighttime Flares
  377. FOL2NS: Generating Natural Sentences from First-Order Logic
  378. Foundation Models for Credit Risk Prediction: A Game Changer?
  379. Evidence-Grounded Frontier Mapping and Agentic Hypothesis Generation in Nanomedicine
  380. Generative AI and the Productivity Divide: Human-AI Complementarities in Education
  381. Who Generated This 3D Asset? Learning Source Attribution for Generative 3D Models
  382. Rad-VLSM: A Cross-Modal Framework with Semantics-Assisted Prompting for Medical Segmentation and Diagnosis
  383. POST: Prior-Observation Adversarial Learning of Spatio-Temporal Associations for Multivariate Time Series Anomaly Detection
  384. WinTok: A Win-Win Hybrid Tokenizer via Decomposing Visual Understanding and Generation with Transferable Tokens
  385. iPOE: Interpretable Prompt Optimization via Explanations
  386. TaskGround: Structured Executable Task Inference for Full-Scene Household Reasoning
  387. How Loud Rumbles Hit Newsstands: A Data Analysis of Coverage and Spatial Bias in German News about Landslides Around the World
  388. DanceHMR: Hand-Aware Whole-Body Human Mesh Recovery from Monocular Videos
  389. Learning to Solve Compositional Geometry Routing Problems
  390. pyforce-1.0.0: Python Framework for data-driven model Order Reduction of multi-physiCs problEms
  391. Parameterized 4-Qubit EWL Quantum Game Circuits with Dirac-Solow-Swan Hamiltonian Integration for Quadruple Helix Disruptive Innovation Recommender Systems
  392. Equilibrium Selection in Multi-Agent Policy Gradients via Opponent-Aware Basin Entry
  393. A-ProS: Towards Reliable Autonomous Programming Through Multi-Model Feedback
  394. Teger: Spatiotemporal Covariance for Probabilistic Traffic Forecasting
  395. The MixCount Dataset: Bridging the Data Gap for Open-Vocabulary Object Counting
  396. Embedded ConvNet Ensembles: A Lightweight Approach to Recognize Arabic Handwritten Characters
  397. Threats to Arabic Handwriting Recognition: Investigating Black-Box Adversarial Attacks on embedded ConvNet models
  398. CATRF: Codec-Adaptive TriPlane Radiance Fields for Volumetric Content Delivery
  399. Efficient 3D Content Reconstruction and Generation
  400. Confidence-Gated Robot Autonomy: When Does Uncertainty Actually Help?
  401. On efficient robust regression with subquadratic samples
  402. SGSoft: Learning Fused Semantic-Geometric Features for 3D Shape Correspondence via Template-Guided Soft Signals
  403. Patch Ensembles for Robust Salmon Re-Identification with Weak Trajectory Labels
  404. Exploring Trust Calibration in XAI - The Impact of Exposing Model Limitations to Lay Users
  405. New Insight of Variance reduce in Zero-Order Hard-Thresholding: Mitigating Gradient Error and Expansivity Contradictions
  406. Real-time Multi-instrument Autonomous Discovery of Novel Phase-change Memory Materials
  407. Quantum Sidecar Architectures for Hybrid AI Training and Inference: Stateful Protected Registers, Stateless Reset-and-Reprepare Circuits and Quantum Weight-State Outlook
  408. TeleCom-Bench: How Far Are Large Language Models from Industrial Telecommunication Applications?
  409. Interaction-Breaking Adversarial Learning Framework for Robust Multi-Agent Reinforcement Learning
  410. DSAA: Dual-Stage Attribute Activation for Fine-grained Open Vocabulary Detection
  411. Unveiling Memorization-Generalization Coexistence: A Case Study on Arithmetic Tasks with Label Noise
  412. Federated Learning by Utility-Constrained Stochastic Aggregation for Improving Rational Participation
  413. A data-driven Fourier-mixture neural-network method for density estimation
  414. See What I Mean: Aligning Vision and Language Representations for Video Fine-grained Object Understanding
  415. LogRouter: Adaptive Two-Level LLM Routing for Log Question Answering in Big Data Systems
  416. TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model
  417. SAS: Semantic-aware Sampling for Generative Dataset Distillation
  418. Functionalization via Structure Completion and Motion Rectification
  419. Uncertainty Reliability Under Domain Shift: An Investigation for Data-Driven Blood Pressure Estimation in Photoplethysmography
  420. Semantic Reranking at Inference Time for Hard Examples in Rhetorical Role Labeling
  421. Inter-LPCM: Learning-based Inter-Frame Predictive Coding for LiDAR Point Cloud Compression
  422. Scalable Decision-Focused Learning through Cost-Sensitive Regression
  423. RL4RLA: Teaching ML to Discover Randomized Linear Algebra Algorithms Through Curriculum Design and Graph-Based Search
  424. Spiker-LL: An Energy-Efficient FPGA Accelerator Enabling Adaptive Local Learning in Spiking Neural Networks
  425. Bridging the Gap: Converting Read Text to Conversational Dialogue
  426. Shared Backbone PPO for Multi-UAV Communication Coverage with Connection Preservation
  427. Verify-Gated Completion as Admission Control in a Governed Multi-Agent Runtime: A Bounded Architecture Case Study
  428. MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization
  429. Towards Sustainable Growth: A Multi-Value-Aware Retrieval Framework for E-Commerce Search
  430. Low Latency Gaze Tracking via Latent Optical Sensing
  431. SAFE-SVD: Sensitivity-Aware Fidelity-Enforcing SVD for Physics Foundation Models
  432. See Silhouettes in Motion with Neuromorphic Vision
  433. AutoVecCoder: Teaching LLMs to Generate Explicitly Vectorized Code
  434. Unleashing LLMs in Bayesian Optimization: Preference-Guided Framework for Scientific Discovery
  435. Function graph transformers universally approximate operators between function spaces
  436. Reconciling Contradictory Views on the Effectiveness of SFT in LLMs: An Interaction Perspective
  437. Wasserstein Saddle-Free Newton: Saddle Escape and Local Spectral Convergence
  438. Counting Machine Parts
  439. UAVFF3D: A Geometry-Aware Benchmark for Feed-Forward UAV 3D Reconstruction
  440. BacktestBench: Benchmarking Large Language Models for Automated Quantitative Strategy Backtesting
  441. Universal Adversarial Triggers
  442. Conditional Predictive Inference for General Structured Data with Group Symmetries
  443. InfoFlow: A Framework for Multi-Layer Transformer Analysis
  444. Transfer Learning for Customized Car Racing Environments
  445. An Efficient Streaming Video Understanding Framework with Agentic Control
  446. Domain Transfer Becomes Identifiable via a Single Alignment
  447. SurgLQA: Scalable Long-Horizon Surgical Video Question Answering
  448. A Pilot Benchmark for NL-to-FOL Translation in Planetary Exploration
  449. One Model to Translate Them All: Universal Any-to-Any Translation for Heterogeneous Collaborative Perception
  450. Beyond Euclidean Prototypes: Spectral Disentanglement and Geodesic Matching for Few-Shot Medical Image Segmentation
  451. LAST-RAG: Literature-Anchored Stochastic Trajectory Retrieval-Augmented Generation for Knowledge-Conditioned Degradation Model Selection
  452. DuIVRS-2: An LLM-based Interactive Voice Response System for Large-scale POI Attribute Acquisition
  453. DCFold: Efficient Protein Structure Generation with Single Forward Pass
  454. Lightweight Gaussian Process Inference in C++ on Metal and CUDA
  455. Long-horizon prediction of three-dimensional wall-bounded turbulence with CTA-Swin-UNet and resolvent analysis
  456. Attention Sinks and Outliers in Attention Residuals
  457. Guard: Scalable Straggler Detection and Node Health Management for Large-Scale Training
  458. HexagonalWarriorMamba: Superior Threshold-Dependent Multi-label Classification of 12-Lead ECG Cardiac Abnormalities
  459. PySIFT: GPU-Resident Deterministic SIFT for Deep Learning Vision Pipelines
  460. Imaging Hidden Objects with Consumer LiDAR via Motion Induced Sampling
  461. PAREDA: A Multi-Accent Speech Dataset of Natural Language Processing Research Discussions
  462. Multi-site PPG: An In-the-Wild Physiological Dataset from Emerging Multi-site Wearables
  463. Learning over Positive and Negative Edges with Contrastive Message Passing
  464. Generating Pretraining Tokens from Organic Data for Data-Bound Scaling
  465. SNLP: Layer-Parallel Inference via Structured Newton Corrections
  466. Efficient Bilevel Optimization for Meta Label Correction in Noisy Label Learning
  467. Interactive Evaluation Requires a Design Science
  468. Content-Style Identification via Differential Independence
  469. Unleashing the Representational Power of Fourier Shapes for Attacking Infrared Object Detection
  470. TierCheck: Tiered Checkpointing for Fault Tolerance in Large Language Model Training
  471. Evidence-Guided Unknown Rejection for High-Confidence Near-Known Unknowns
  472. Virtues of Ordered Chaos: Planning with Topple Actions in Tabletop Stack Rearrangement
  473. Going Headless? On the Boundaries of Vertical AI Firms
  474. One Model, Two Roles: Emergent Specialization in a Shared Recurrent Transformer
  475. Accelerating AI-Powered Research: The PuppyChatter Framework for Usable and Flexible Tooling
  476. A Unified Framework for Data-Free One-Step Sampling via Wasserstein Gradient Flows
  477. Curriculum Group Policy Optimization: Adaptive Sampling for Unleashing the Potential of Text-to-Image Generation
  478. AMO: Operator-level Adaptive Muon Orthogonalization
  479. GenTS: A Comprehensive Benchmark Library for Generative Time Series Models
  480. Optimal Knock-Pick Planning for Tightly Packed Tabletop Blocks With Parallel Grippers
  481. Is Complex Training Necessary for Long-Tailed OOD Detection? A Re-think from Feature Geometry
  482. When Accuracy Is Not Enough: Uncertainty Collapse between Noisy Label Learning and Out-of-Distribution Detection
  483. HydroAgent: Closing the Gap Between Frontier LLMs and Human Experts in Hydrologic Model Calibration via Simulator-Grounded RL
  484. SocialMemBench: Are AI Memory Systems Ready for Social Group Settings?
  485. Uncertainty-Calibrated Recommendations for Low-Active Users
  486. Revisiting the Adam-SGD Gap in LLM Pre-Training: The Role of Large Effective Learning Rates
  487. Network Knowledge Prior Guided Learning for Data-Efficient Surface Defect Detection
  488. Learning Variable-Length Tokenization for Generative Recommendation
  489. Efficient Sparse-to-Dense Visual Localization via Compact Gaussian Scene Representation and Accelerated Dense Pose Estimation
  490. Systematic Evaluation of the Quality of Synthetic Clinical Notes Rephrased by LLMs at Million-Note Scale
  491. PlantPose: Universal Plant Skeleton Estimation via Tree-constrained Graph Generation
  492. Towards Universal Physical Adversarial Attacks via a Joint Multi-Objective and Multi-Model Optimization Framework
  493. Feature Learning in Linear-Width Two-Layer Networks: Two vs. One Step of Gradient Descent
  494. AURORA: Contextual Orthogonalization for Geometric Representation Learning in Healthcare Foundation Models
  495. Comparing Two Categorical Gini Correlations with Applications to Classification Problems
  496. Surface-Form Neural Sparse Retrieval: Robust Fuzzy Matching for Industrial Music Search
  497. MV-Gate: Insider Threat Detection via Multi-View Behavioral Statistics and Semantic Modeling
  498. Bridging the Version Gap: Multi-version Training Improves ICD Code Prediction, Especially for Rare Codes
  499. Testable and Actionable Calibration for Full Swap Regret
  500. Unleashing Vision Transformer Potential In Image Quality Assessment via Global-Local Adaptive Interaction
  501. Agents for Experiments, Experiments for Agents: A Design Grammar for AI-Enabled Experimental Science
  502. StatQAT: Statistical Quantizer Optimization for Deep Networks
  503. UST-Hand: An Uncertainty-aware Spatiotemporal Point Cloud Interaction Network for 3D Self-supervised Hand Pose Estimation
  504. L-Drive: Beyond a Single Mapping-Latent Context Drives Time Series Forecasting
  505. Domain Incremental Learning for Pandemic-Resilient Chest X-Ray Analysis
  506. GraSP-VL: Length as a Semantic Granularity Interface for Vision-Language Representations
  507. Sequential Structure in Intraday Futures Data: LSTM vs Gradient Boosting on MNQ
  508. How does feature learning reshape the function space?
  509. From Documents to Segments: A Contextual Reformulation for Topic Assignment
  510. Online Conformal Prediction for Non-Exchangeable Panel Data
  511. Toy Combinatorial Interpretability Models Reveal Lottery Tickets in Early Feature Space