mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 1 Oct 2025

480 papers

  1. Conversational Agents for Building Energy Efficiency -- Advising Housing Cooperatives in Stockholm on Reducing Energy ConsumptionLLM agents and tool use → Financial trading and forecasting agents
  2. AI Agents with Decentralized Identifiers and Verifiable CredentialsLLM agents and tool use → Agent threats, guardrails and governance
  3. Constrained Diffusion for Protein Design with Hard Structural ConstraintsDiffusion models → Flow matching, time series and science
  4. LiRA: A Multi-Agent Framework for Reliable and Readable Literature Review GenerationLLM agents and tool use → Web, search, and research agents
  5. Demystifying deep search: a holistic evaluation with hint-free multi-hop questions and factorised metricsRetrieval-augmented generation → Agentic RAG, agents and memory +1
  6. Curiosity-Driven LLM-as-a-judge for Personalized Creative JudgmentLLM reasoning → Reasoning benchmarks and evaluation
  7. Structuring Reasoning for Complex Rules Beyond Flat RepresentationsLLM reasoning → Reasoning benchmarks and evaluation
  8. Characterizing Model Behavior Under Synthetic Data Training: An Empirical Study Across Scales and Mixing RatiosLLM reasoning → Reasoning benchmarks and evaluation +1
  9. Training Large Language Models To Reason In Parallel With Global Forking TokensLLM reasoning → Test-time compute and efficient thinking
  10. Constant in an Ever-Changing WorldDeep reinforcement learning methods → Deep RL algorithms and representations
  11. Enhancing Agentic Textual Graph Retrieval with Synthetic Stepwise SupervisionLLM agents and tool use → Web, search, and research agents
  12. Glaucoma Detection and Structured OCT Report Generation via a Fine-tuned Multimodal Large Language ModelMultimodal LLMs / vision-language models → Medical vision-language models
  13. KnowledgeSmith: Uncovering Knowledge Updating in LLMs with Model Editing and UnlearningLLM safety and security → Machine unlearning
  14. One More Question is Enough, Expert Question Decomposition (EQD) Model for Domain Quantitative ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  15. WALT: Web Agents that Learn ToolsLLM reasoning → Reasoning for agents, planning and code +1
  16. MetaSynth: Multi-Agent Metadata Generation from Implicit Feedback in Black-Box SystemsRetrieval-augmented generation → Agentic RAG, agents and memory +1
  17. Realistic CDSS Drug Dosing with End-to-end Recurrent Q-learning for Dual Vasopressor ControlDeep reinforcement learning methods → RL for clinical treatment and surgery
  18. Lateral Tree-of-Thoughts Surpasses ToT by Incorporating Logically-Consistent, Low-Utility CandidatesLLM reasoning → Test-time compute and efficient thinking
  19. Beyond Majority Voting: LLM Aggregation by Leveraging Higher-Order InformationLLM reasoning → Reasoning for agents, planning and code +1
  20. AortaDiff: A Unified Multitask Diffusion Framework For Contrast-Free AAA ImagingDiffusion models → Medical imaging and segmentation
  21. Understanding Adversarial Transfer: Why Representation-Space Attacks Fail Where Data-Space Attacks SucceedLLM safety and security → Vision-language and text-to-image safety
  22. Off-Policy Reinforcement Learning with Anytime Safety Guarantees via Robust Safe Gradient FlowDeep reinforcement learning methods → Safe and constrained RL
  23. Spatiotemporal Knowledge Graphs as Persistent Scene Memory for Embodied Question AnsweringMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  24. Density-Ratio Weighted Behavioral Cloning: Learning Control Policies from Corrupted DatasetsOffline RL and imitation learning from data → Imitation learning methods +1
  25. Purrception: Variational Flow Matching for Vector-Quantized Image GenerationDiffusion models → Flow matching, time series and science
  26. Comparative Field Deployment of Reinforcement Learning and Model Predictive Control for Residential HVACDeep reinforcement learning methods → RL for energy, networks and operations
  27. The Three Regimes of Offline-to-Online Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
  28. LSPO: Length-aware Dynamic Sampling for Policy Optimization in LLM ReasoningLLM reasoning → Reinforcement learning for reasoning
  29. How Well Can Preference Optimization Generalize Under Noisy Feedback?LLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  30. A Forensic Analysis of Synthetic Data in RL: Diagnosing and Solving Algorithmic Failures in Model-Based Policy OptimizationDeep reinforcement learning methods → Deep RL algorithms and representations
  31. SCOPED: Score-Curvature Out-of-distribution Proximity Evaluator for DiffusionDiffusion models → Medical imaging and segmentation
  32. Data Selection for Fine-tuning Vision Language Models via Cross Modal Alignment TrajectoriesMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  33. Dual-Uncertainty Guided Policy Learning for Multimodal ReasoningLLM reasoning → Multimodal reasoning +1
  34. BioVERSE: Representation Alignment of Biomedical Modalities to LLMs for Multi-Modal ReasoningLLM reasoning → Clinical and biomedical applications
  35. How Well do Diffusion Policies Learn Kinematic Constraint Manifolds?Diffusion models → Diffusion and flow policies for robotics +1
  36. Automating Data-Driven Modeling and Analysis for Engineering Applications using Large Language Model AgentsLLM agents and tool use → Web, search, and research agents
  37. Optimal Stopping vs Best-of-N for Inference Time OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  38. TAG-EQA: Text-And-Graph for Event Question Answering via Structured Prompting StrategiesLLM reasoning → Prompting and chain-of-thought reasoning
  39. INSIGHT: INference-time Sequence Introspection for Generating Help Triggers in Vision-Language-Action ModelsVision-language-action models → VLA architectures and generalization
  40. VENTURA: Adapting Image Diffusion Models for Unified Task Conditioned NavigationDiffusion models → Diffusion and flow policies for robotics
  41. Fine-Tuning Masked Diffusion for Provable Self-CorrectionDiffusion models → Discrete and text diffusion
  42. Selective Underfitting in Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  43. Fine-tuning with RAG for Improving LLM Learning of New SkillsRetrieval-augmented generation → Agentic RAG, agents and memory
  44. Is It Thinking or Cheating? Detecting Implicit Reward Hacking by Measuring Reasoning EffortLLM reasoning → Prompting and chain-of-thought reasoning
  45. Retrieval-Augmented Framework for LLM-Based Clinical Decision SupportRetrieval-augmented generation → Medical and biomedical RAG
  46. Breaking the Code: Security Assessment of AI Code Agents Through Systematic Jailbreaking AttacksLLM agents and tool use → Agent threats, guardrails and governance +1
  47. WAInjectBench: Benchmarking Prompt Injection Detections for Web AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  48. MEMTRACK: Evaluating Long-Term Memory and State Tracking in Multi-Platform Dynamic Agent EnvironmentsLLM agents and tool use → Agent memory systems
  49. Fine-Tuning Jailbreaks under Highly Constrained Black-Box Settings: A Three-Pronged ApproachLLM safety and security → Jailbreaking
  50. LVTINO: LAtent Video consisTency INverse sOlver for High Definition Video RestorationDiffusion models → Inverse problems and image restoration
  51. HiSpec: Hierarchical Speculative Decoding for LLMsEfficient LLM inference and serving → Speculative decoding
  52. Continuously Augmented Discrete Diffusion model for Categorical Generative ModelingDiffusion models → Discrete and text diffusion
  53. Combining complex Langevin dynamics with score-based and energy-based diffusion modelsDiffusion models → Diffusion foundations and sampling
  54. Agentic Jigsaw Interaction Learning for Enhancing Visual Perception and Reasoning in Vision-Language ModelsLLM reasoning → Multimodal reasoning +2
  55. Domain-Specific Agents for Cherenkov Telescope Array Control Software and Gamma-Ray Data AnalysisLLM agents and tool use → Web, search, and research agents
  56. SimCity: Multi-Agent Urban Development Simulation with Rich InteractionsLLM agents and tool use → Social simulation and multi-agent debate
  57. The Social Laboratory: A Psychometric Framework for Multi-Agent LLM EvaluationLLM agents and tool use → Social simulation and multi-agent debate
  58. ThinKV: Thought-Adaptive KV Cache Compression for Efficient Reasoning ModelsLLM reasoning → Test-time compute and efficient thinking +1
  59. Dirichlet-Prior Shaping: Guiding Expert Specialization in Upcycled MoEsMixture-of-experts → Vision mixture-of-experts
  60. Temporal Score Rescaling for Temperature Sampling in Diffusion and Flow ModelsDiffusion models → Diffusion foundations and sampling
  61. EvoWorld: Evolving Panoramic World Generation with Explicit 3D MemoryWorld models → Video-generation world models and simulators
  62. BroRL: Scaling Reinforcement Learning via Broadened ExplorationLLM reasoning → Reinforcement learning for reasoning +1
  63. TOUCAN: Synthesizing 1.5M Tool-Agentic Data from Real-World MCP EnvironmentsLLM agents and tool use → Tool learning and function calling
  64. Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable RewardsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  65. GRAD: Generative Retrieval-Aligned Demonstration Sampler for Efficient Few-Shot ReasoningLLM reasoning → Reasoning benchmarks and evaluation +1
  66. Social Welfare Function Leaderboard: When LLM Agents Allocate Social WelfareLLM agents and tool use → Social simulation and multi-agent debate
  67. Prosperity before Collapse: How Far Can Off-Policy RL Reach with Stale Data on LLMs?LLM reasoning → Reinforcement learning for reasoning
  68. Multi-Marginal Flow Matching with Adversarially Learnt InterpolantsDiffusion models → Flow matching, time series and science
  69. Where Do Backdoors Live? A Component-Level Analysis of Backdoor Propagation in Speech Language ModelsLLM safety and security → Backdoor and data poisoning attacks
  70. ModernVBERT: Towards Smaller Visual Document RetrieversRetrieval-augmented generation → Multimodal RAG
  71. mR3: Multilingual Rubric-Agnostic Reward Reasoning ModelsLLM reasoning → Reinforcement learning for reasoning +1
  72. Apriel-1.5-15b-ThinkerLLM reasoning → Multimodal reasoning
  73. A Practitioner's Guide to Multi-turn Agentic Reinforcement LearningLLM agents and tool use → Reinforcement learning for LLM agents
  74. Strategic Fusion of Vision Language Models: Shapley-Credited Context-Aware Dawid-Skene for Multi-Label Tasks in Autonomous DrivingMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
  75. Rethinking Thinking Tokens: LLMs as Improvement OperatorsLLM reasoning → Test-time compute and efficient thinking
  76. Eliciting Chain-of-Thought Reasoning for Time Series Analysis using Reinforcement LearningLLM reasoning → Time series reasoning
  77. Exploring Network-Knowledge Graph Duality: A Case Study in Agentic Supply Chain Risk AnalysisLLM agents and tool use → Financial trading and forecasting agents
  78. Safety Instincts: LLMs Learn to Trust Their Internal Compass for Self-DefenseLLM safety and security → Safety alignment, refusal and guardrails
  79. Multi-Actor Multi-Critic Deep Deterministic Reinforcement Learning with a Novel Q-Ensemble MethodDeep reinforcement learning methods → RL theory and sample complexity
  80. Research on the Integration of Embodied Intelligence and Reinforcement Learning in Textual DomainsDeep reinforcement learning methods → RL for robot locomotion and manipulation
  81. Eliciting Secret Knowledge from Language ModelsMechanistic interpretability → Probing deception, bias and beliefs
  82. Typed Chain-of-Thought: A Curry-Howard Framework for Verifying LLM ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  83. Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level CompositionVision-language-action models → Reinforcement learning and post-training +1
  84. GEM: A Gym for Agentic LLMsLLM agents and tool use → Reinforcement learning for LLM agents
  85. Interpreting Language Models Through Concept Descriptions: A SurveyMechanistic interpretability → Knowledge and representations inside LLMs
  86. In-Situ Tweedie Discrete Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  87. CurES: From Gradient Analysis to Efficient Curriculum Learning for Reasoning LLMsLLM reasoning → Reinforcement learning for reasoning
  88. Meaningless Tokens, Meaningful Gains: How Activation Shifts Enhance LLM ReasoningLLM reasoning → Test-time compute and efficient thinking
  89. Secure and reversible face anonymization with diffusion modelsDiffusion models → Robustness, privacy and adversarial aspects
  90. Syntax-Guided Diffusion Language Models with User-Integrated PersonalizationDiffusion models → Discrete and text diffusion
  91. ImageDoctor: Diagnosing Text-to-Image Generation via Grounded Image ReasoningLLM reasoning → Multimodal reasoning
  92. POVQA: Preference-Optimized Video Question Answering with Rationales for Data EfficiencyMultimodal LLMs / vision-language models → Video understanding with MLLMs +1
  93. Riemannian Consistency ModelDiffusion models → Flow matching, time series and science
  94. Spiralformer: Low Latency Encoder for Streaming Speech Recognition with Circular Layer Skipping and Early ExitingEfficient LLM inference and serving → Audio and omni-modal token compression
  95. It Takes Two: Your GRPO Is Secretly DPOLLM reasoning → Reinforcement learning for reasoning +1
  96. QUASAR: Quantum Assembly Code Generation Using Tool-Augmented LLMs via Agentic RLLLM agents and tool use → Medical and scientific domain agents
  97. Analyzing Dialectical Biases in LLMs for Knowledge and Reasoning BenchmarksLLM reasoning → Reasoning benchmarks and evaluation
  98. Large Reasoning Models Learn Better Alignment from Flawed ThinkingLLM reasoning → Reasoning for agents, planning and code +2
  99. Digital Twins: McKean-Pontryagin Control for Partially Observed Physical TwinsDeep reinforcement learning methods → RL theory and sample complexity
  100. On Discovering Algorithms for Adversarial Imitation LearningOffline RL and imitation learning from data → Imitation learning methods
All 480
  1. Benchmarking Foundation Models with Retrieval-Augmented Generation in Olympic-Level Physics Problem SolvingRetrieval-augmented generation → Agentic RAG, agents and memory
  2. Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect VerifiersDeep reinforcement learning methods → RL training of language and agent models
  3. RiskPO: Risk-based Policy Optimization via Verifiable Reward for LLM Post-TrainingLLM reasoning → Reinforcement learning for reasoning
  4. TubeDAgger: Reducing the Number of Expert Interventions with Stochastic Reach-TubesOffline RL and imitation learning from data → Imitation learning methods
  5. Rectifying Regression in Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  6. Advancing Automated Ethical Profiling in SE: a Zero-Shot Evaluation of LLM ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  7. HalluGuard: Evidence-Grounded Small Reasoning Models to Mitigate Hallucinations in Retrieval-Augmented GenerationLLM reasoning → Hallucination detection and mitigation +1
  8. Gather-Scatter Mamba: Accelerating Propagation with Efficient State Space ModelState-space sequence models (S4, Mamba) → Vision Mamba backbones
  9. Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMsLLM reasoning → Knowledge- and tool-augmented reasoning
  10. Can World Models Benefit VLMs for World Dynamics?World models → Video-generation world models and simulators
  11. Mechanistic Interpretability as Statistical Estimation: A Variance AnalysisMechanistic interpretability → Circuits and mechanistic analysis
  12. Learning Compact Representations of LLM Abilities via Item Response TheoryMixture-of-experts → MoE large language models
  13. Towards Verifiable Federated Unlearning: Framework, Challenges, and The Road AheadLLM safety and security → Federated unlearning and poisoning
  14. Exposing the Cracks: Vulnerabilities of Retrieval-Augmented LLM-based Machine TranslationRetrieval-augmented generation → Generation and context integration
  15. NSARM: Next-Scale Autoregressive Modeling for Robust Real-World Image Super-ResolutionDiffusion models → Inverse problems and image restoration
  16. Stabilizing Policy Gradients for Sample-Efficient Reinforcement Learning in LLM ReasoningLLM reasoning → Reinforcement learning for reasoning
  17. Learn to Guide Your Diffusion ModelDiffusion models → Diffusion foundations and sampling
  18. Guiding Evolutionary Molecular Design: Adding Reinforcement Learning for Mutation SelectionDeep reinforcement learning methods → RL for energy, networks and operations
  19. Fast, Secure, and High-Capacity Image Watermarking with Autoencoded Text VectorsLLM safety and security → Watermarking generated content and models
  20. Benchmarking Agentic Systems in Automated Scientific Information Extraction with ChemXLLM agents and tool use → Medical and scientific domain agents
  21. DIA: The Adversarial Exposure of Deterministic Inversion in Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
  22. UniverSR: Unified and Versatile Audio Super-Resolution via Vocoder-Free Flow MatchingDiffusion models → Audio, speech and music
  23. Are Large Vision-Language Models Ready to Guide Blind and Low-Vision Individuals?Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  24. Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM UnlearningLLM safety and security → Machine unlearning
  25. From Scores to Preferences: Redefining MOS Benchmarking for Speech Quality Reward ModelingLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
  26. TD-JEPA: Latent-predictive Representations for Zero-Shot Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  27. CroSTAta: Cross-State Transition Attention Transformer for Robotic ManipulationOffline RL and imitation learning from data → Robot manipulation imitation learning
  28. Training-free Uncertainty Guidance for Complex Visual Tasks with MLLMsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  29. Graph Integrated Multimodal Concept Bottleneck ModelMixture-of-experts → MoE large language models
  30. HAMLET: Switch your Vision-Language-Action Model into a History-Aware PolicyVision-language-action models → Reasoning and chain-of-thought in VLA
  31. ALARB: An Arabic Legal Argument Reasoning BenchmarkLLM reasoning → Reasoning for agents, planning and code
  32. ACPO: Adaptive Curriculum Policy Optimization for Aligning Vision-Language Models in Complex ReasoningLLM reasoning → Multimodal reasoning +1
  33. Stochastic Self-Organization in Multi-Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  34. Adaptive Event Stream Slicing for Open-Vocabulary Event-Based Object Detection via Vision-Language Knowledge DistillationKnowledge distillation → Detection and dense prediction distillation
  35. A Geometric Unification of Generative AI with Manifold-Probabilistic Projection ModelsDiffusion models → Diffusion foundations and sampling
  36. Align Your Tangent: Training Better Consistency Models via Manifold-Aligned TangentsDiffusion models → Flow matching, time series and science
  37. MCM-DPO: Multifaceted Cross-Modal Direct Preference Optimization for Alt-text GenerationLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  38. Expected Attention: KV Cache Compression by Estimating Attention from Future Queries DistributionEfficient LLM inference and serving → KV cache optimization
  39. Erased, But Not Forgotten: Erased Rectified Flow Transformers Still Remain Unsafe Under Concept AttackDiffusion models → Robustness, privacy and adversarial aspects
  40. Collaborative-Distilled Diffusion Models (CDDM) for Accelerated and Lightweight Trajectory PredictionDiffusion models → Diffusion and flow policies for robotics
  41. When Silence Matters: The Impact of Irrelevant Audio on Text Reasoning in Large Audio-Language ModelsLLM reasoning → Audio-language model reasoning
  42. UCD: Unconditional Discriminator Promotes Nash Equilibrium in GANsDiffusion models → Diffusion foundations and sampling
  43. FAME: Adaptive Functional Attention with Expert Routing for Function-on-Function RegressionMixture-of-experts → MoE theory and gating functions
  44. ACON: Optimizing Context Compression for Long-horizon LLM AgentsLLM agents and tool use → Agent memory systems +1
  45. LVLMs as inspectors: an agentic framework for category-level structural defect annotationLLM agents and tool use → Multimodal and embodied agents
  46. Hybrid Training for Vision-Language-Action ModelsVision-language-action models → Reasoning and chain-of-thought in VLA
  47. Eyes-on-Me: Scalable RAG Poisoning through Transferable Attention-Steering AttractorsRetrieval-augmented generation → Privacy and security of RAG +1
  48. CoT Vectors: Transferring and Probing the Reasoning Mechanisms of LLMsLLM reasoning → Prompting and chain-of-thought reasoning
  49. GRITS: A Spillage-Aware Guided Diffusion Policy for Robot Food Scooping TasksDiffusion models → Diffusion and flow policies for robotics
  50. Adaptive Shared Experts with LoRA-Based Mixture of Experts for Multi-Task LearningMixture-of-experts → Mixture of LoRA experts
  51. ReSeek: A Self-Correcting Framework for Search Agents with Instructive RewardsLLM agents and tool use → Web, search, and research agents
  52. Toward Safer Diffusion Language Models: Discovery and Mitigation of Priming VulnerabilityDiffusion models → Robustness, privacy and adversarial aspects +1
  53. On Predictability of Reinforcement Learning Dynamics for Large Language ModelsLLM reasoning → Reinforcement learning for reasoning
  54. Data Quality Challenges in Retrieval-Augmented GenerationRetrieval-augmented generation → RAG pipeline design and evaluation
  55. ThinkBrake: Efficient Reasoning via Log-Probability Margin Guided DecodingLLM reasoning → Test-time compute and efficient thinking
  56. GUI-KV: Efficient GUI Agents via KV Cache with Spatio-Temporal AwarenessMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +2
  57. Cascaded Diffusion Framework for Probabilistic Coarse-to-Fine Hand Pose EstimationDiffusion models → Diffusion and flow policies for robotics
  58. VIRTUE: Visual-Interactive Text-Image Universal EmbedderMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  59. Efficient Multi-modal Large Language Models via Progressive Consistency DistillationMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  60. Copy-Paste to Mitigate Large Language Model HallucinationsRetrieval-augmented generation → Hallucination detection in RAG
  61. Graph2Eval: Automatic Multimodal Task Generation for Agents via Knowledge GraphsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  62. Affordance-Guided Diffusion Prior for 3D Hand ReconstructionDiffusion models → Diffusion and flow policies for robotics
  63. Diffusion Alignment as Variational Expectation-MaximizationDiffusion models → Diffusion foundations and sampling
  64. CodeChemist: Test-Time Scaling for Low-Resource Code Generation via Functional Knowledge TransferLLM reasoning → Reasoning for agents, planning and code
  65. Exploring System 1 and 2 communication for latent reasoning in LLMsLLM reasoning → Test-time compute and efficient thinking
  66. Rethinking Reward Models for Multi-Domain Test-Time ScalingLLM reasoning → Reinforcement learning for reasoning +1
  67. MathSticks: A Benchmark for Visual Symbolic Compositional Reasoning with Matchstick PuzzlesLLM reasoning → Multimodal reasoning
  68. Agent Fine-tuning through Distillation for Domain-specific LLMs in MicrodomainsLLM agents and tool use → General LLM agent frameworks and benchmarks
  69. Vicinity-Guided Discriminative Latent Diffusion for Privacy-Preserving Domain AdaptationDiffusion models → Diffusion foundations and sampling
  70. Integrating Offline Pre-Training with Online Fine-Tuning: A Reinforcement Learning Approach for Robot Social NavigationOffline RL and imitation learning from data → Social robot navigation +1
  71. A Call to Action for a Secure-by-Design Generative AI ParadigmLLM safety and security → Prompt injection and agent security
  72. BindWeave: Subject-Consistent Video Generation via Cross-Modal IntegrationDiffusion models → Video generation
  73. PromptLoop: Plug-and-Play Prompt Refinement via Latent Feedback for Diffusion Model AlignmentDiffusion models → Diffusion and flow policies for robotics +1
  74. Towards Self-Evolving Benchmarks: Synthesizing Agent Trajectories via Test-Time Exploration under Validate-by-Reproduce ParadigmLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  75. RELATE-Sim: Leveraging Turning Point Theory and LLM Agents to Predict and Understand Long-Term Relationship Dynamics through Interactive Narrative SimulationsLLM agents and tool use → Social simulation and multi-agent debate
  76. PAL-UI: Planning with Active Look-back for Vision-Based GUI AgentsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  77. VLA-RFT: Vision-Language-Action Reinforcement Fine-tuning with Verified Rewards in World SimulatorsWorld models → Embodied and robot world models +2
  78. AbsTopK: Rethinking Sparse Autoencoders For Bidirectional FeaturesLLM reasoning → Reasoning benchmarks and evaluation +1
  79. How Can Mamba Learn In Context with Outliers and Generalize Provably?State-space sequence models (S4, Mamba) → Core SSM architectures for language
  80. Discrete Wavelet Transform as a Facilitator for Expressive Latent Space Representation in Variational Autoencoders in Satellite ImageryDiffusion models → Inverse problems and image restoration
  81. Causally-Informed Reinforcement Learning for Adaptive Emotion-Aware Social Media Recommendation
  82. Social and Physical Attributes-Defined Trust Evaluation for Effective Collaborator Selection in Human-Device Coexistence Systems
  83. Analyse comparative d'algorithmes de restauration en architecture d'epli'ee pour des signaux chromatographiques parcimonieux
  84. Speak to a Protein: An Interactive Multimodal Co-Scientist
  85. Carbon-Aware Orchestration of Integrated Satellite Aerial Terrestrial Networks via Digital Twin
  86. Articulation-Informed ASR: Integrating Articulatory Features into ASR via Auxiliary Speech Inversion and Cross-Attention Fusion
  87. Neu-RadBERT for Enhanced Diagnosis of Brain Injuries and Conditions
  88. CML-Bench: A Framework for Evaluating and Enhancing LLM-Powered Movie Scripts Generation
  89. SynCED-EnDe 2025: A Synthetic and Curated English - German Dataset for Critical Error Detection in Machine Translation
  90. Reliable End-to-End Material Information Extraction from the Literature with Source-Tracked Multi-Stage Large Language Models
  91. To model human linguistic prediction, make LLMs less superhuman
  92. Auditing Algorithmic Bias in Transformer-Based Trading
  93. NLD-LLM: A systematic framework for evaluating small language transformer models on natural language description
  94. Linguistic Characteristics of AI-Generated Text: A Survey
  95. Rationale-Augmented Retrieval with Constrained LLM Re-Ranking for Task Discovery
  96. Intelligent Healthcare Ecosystems: Optimizing the Iron Triangle of Healthcare (Access, Cost, Quality)
  97. DECOR: Deep Embedding Clustering with Orientation Robustness
  98. NS-Pep: De novo Peptide Design with Non-Standard Amino Acids
  99. Fast frequency reconstruction using Deep Learning for event recognition in ring laser data
  100. Attack logics, not outputs: Towards efficient robustification of deep neural networks by falsifying concept-based properties
  101. SVDefense: Effective Defense against Gradient Inversion Attacks via Singular Value Decomposition
  102. Advances in Medical Image Segmentation: A Comprehensive Survey with a Focus on Lumbar Spine Applications
  103. Photorealistic Inpainting for Perturbation-based Explanations in Ecological Monitoring
  104. The View From Space: Navigating Instrumentation Differences with EOFMs
  105. Decomposing Attention To Find Context-Sensitive Neurons
  106. Linear RNNs for autoregressive generation of long music samples
  107. Retrieval and Augmentation of Domain Knowledge for Text-to-SQL Semantic Parsing
  108. Round-trip Reinforcement Learning: Self-Consistent Training for Better Chemical LLMs
  109. On Integer Programming for the Binarized Neural Network Verification Problem
  110. CarbonX: An Open-Source Tool for Computational Decarbonization Using Time Series Foundation Models
  111. Predictive Modeling and Explainable AI for Veterinary Safety Profiles, Residue Assessment, and Health Outcomes Using Real-World Data and Physicochemical Properties
  112. From Videos to Indexed Knowledge Graphs -- Framework to Marry Methods for Multimodal Content Analysis and Understanding
  113. Flock: A Knowledge Graph Foundation Model via Learning on Random Walks
  114. Behavioral Geometric Supervision Aligns Video Foundation Models with Human Social Perception
  115. Pharmacophore-Guided Generative Design of Novel Drug-Like Molecules
  116. AIReg-Bench: Benchmarking Language Models That Assess AI Regulation Compliance
  117. From keywords to semantics: Perceptions of large language models in data discovery
  118. LLM-NAS: LLM-driven Hardware-Aware Neural Architecture Search
  119. Fine-tuning LLMs with variational Bayesian last layer for high-dimensional Bayesian optimization
  120. Extracting O*NET Features from the NLx Corpus to Build Public Use Aggregate Labor Market Data
  121. A-VERT: Agnostic Verification with Embedding Ranking Targets
  122. RealClass: A Framework for Classroom Speech Simulation with Public Datasets and Game Engines
  123. The Command Line GUIde: Graphical Interfaces from Man Pages via AI
  124. Financial Stability Implications of Generative AI: Taming the Animal Spirits
  125. Local Linear Attention: An Optimal Interpolation of Linear and Softmax Attention For Test-Time Regression
  126. GeoSURGE: Geo-localization using Semantic Fusion with Hierarchy of Geographic Embeddings
  127. SoftAdaClip: A Smooth Clipping Strategy for Fair and Private Model Training
  128. Edge Artificial Intelligence: A Systematic Review of Evolution, Taxonomic Frameworks, and Future Horizons
  129. AFFORD2ACT: Affordance-Guided Automatic Keypoint Selection for Generalizable and Lightweight Robotic Manipulation
  130. On the Role of Domain Experts in Creating Effective Tutoring Systems
  131. A Tale of LLMs and Induced Small Proxies: Scalable Small Language Models for Knowledge Mining
  132. DiffKnock: Diffusion-based Knockoff Statistics for Neural Networks Inference
  133. Risk Phase Transitions in Spiked Regression: Alignment Driven Benign and Catastrophic Overfitting
  134. OntoLogX: Ontology-Guided Knowledge Graph Extraction from Cybersecurity Logs with Large Language Models
  135. Ultra-Efficient Decoding for End-to-End Neural Compression and Reconstruction
  136. Resolving the Identity Crisis in Text-to-Image Generation
  137. Neural Network Surrogates for Free Energy Computation of Complex Chemical Systems
  138. Sycophantic AI Decreases Prosocial Intentions and Promotes Dependence
  139. Learning to Play Multi-Follower Bayesian Stackelberg Games
  140. DeMuon: A Decentralized Muon for Matrix Optimization over Graphs
  141. SPUS: A Lightweight and Parameter-Efficient Foundation Model for PDEs
  142. RheOFormer: A generative transformer model for simulation of complex fluids and flows
  143. EvoStruggle: A Dataset Capturing the Evolution of Struggle across Activities and Skill Levels
  144. An Efficient Quality Metric for Video Frame Interpolation Based on Motion-Field Divergence
  145. A theoretical framework for M-posteriors: frequentist guarantees and robustness properties
  146. To Augment or Not to Augment? Diagnosing Distributional Symmetry Breaking
  147. Image Generation Based on Image Style Extraction
  148. Aristotle: IMO-level Automated Theorem Proving
  149. Self-Supervised Representation Learning as Mutual Information Maximization
  150. On the Identifiability of Latent Action Policies
  151. HomID : Benchmarking Intrinsic Dimension Estimators on Homogenous Manifolds with Anisotropic Embeddings
  152. Low Rank Gradients and Where to Find Them
  153. Hybrid Predictive Modeling of Malaria Incidence in the Amhara Region, Ethiopia: Integrating Multi-Output Regression and Time-Series Forecasting
  154. MorphGen: Controllable and Morphologically Plausible Generative Cell-Imaging
  155. From 2D to 3D, Deep Learning-based Shape Reconstruction in Magnetic Resonance Imaging: A Review
  156. Cyber Academia-Chemical Engineering (CA-ChemE): A Living Digital Town for Self-Directed Research Evolution and Emergent Scientific Discovery
  157. Network-Level Vehicle Delay Estimation at Heterogeneous Signalized Intersections
  158. Private Realizable-to-Agnostic Transformation with Near-Optimal Sample Complexity
  159. Microsaccade-Inspired Probing: Positional Encoding Perturbations Reveal LLM Misbehaviours
  160. Evaluating New AI Cell Foundation Models on Challenging Kidney Pathology Cases Unaddressed by Previous Foundation Models
  161. ASTRA: Let Arbitrary Subjects Transform in Video Editing
  162. COM-BOM: Bayesian Exemplar Search for Efficiently Exploring the Accuracy-Calibration Pareto Frontier
  163. Audio Driven Real-Time Facial Animation for Social Telepresence
  164. On the Benefits of Weight Normalization for Overparameterized Matrix Sensing
  165. Code2Video: A Code-centric Paradigm for Educational Video Generation
  166. EditTrack: Detecting and Attributing AI-assisted Image Editing
  167. Energy-Regularized Sequential Model Editing on Hyperspheres
  168. Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity
  169. Fiaingen: A financial time series generative method matching real-world data quality
  170. A first-order method for constrained nonconvex-nonconcave minimax optimization
  171. How Does the Pretraining Distribution Shape In-Context Learning? A Fundamental Trade-Off
  172. MASH: Modeling Abstention via Selective Help-Seeking
  173. Automatic Speech Recognition (ASR) for African Low-Resource Languages: A Systematic Literature Review
  174. Generalized Parallel Scaling with Interdependent Generations
  175. Re-examining Low Rank adaptation for private LLM fine-tuning
  176. TabINR: An Implicit Neural Representation Framework for Tabular Data Imputation
  177. Prompt Curriculum Learning for Efficient LLM Post-Training
  178. Instant4D: 4D Gaussian Splatting in Minutes
  179. Breaking the Euclidean Barrier: Hyperboloid-Based Biological Sequence Analysis
  180. PRISM-Consult: A Panel-of-Experts Architecture for Clinician-Aligned Diagnosis
  181. Privacy Preserved Federated Learning with Attention-Based Aggregation for Biometric Recognition
  182. The causal structure of galactic astrophysics
  183. TsLLM: Augmenting LLMs for General Time Series Understanding and Prediction
  184. Geometric Analysis of Neural Regression Collapse via Intrinsic Dimension
  185. Theory of Scaling Laws for In-Context Regression: Depth, Width, Context and Time
  186. Optimizing Fairness in Production Planning: A Human-Centric Approach to Machine and Workforce Allocation
  187. Optimal placement of wind farms via quantile constraint learning
  188. Double projection for reconstructing dynamical systems: between stochastic and deterministic regimes
  189. CodeGenLink: A Tool to Find the Likely Origin and License of Automatically Generated Code
  190. Predicting Diabetic Retinopathy Using a Two-Level Ensemble Model
  191. ReSWD: ReSTIR'd, not shaken. Combining Reservoir Sampling and Sliced Wasserstein Distance for Variance Reduction
  192. Hybrid Dialogue State Tracking for Persian Chatbots: A Language Model-Based Approach
  193. KeySG: Hierarchical Keyframe-Based 3D Scene Graphs
  194. Gated X-TFC: Soft Domain Decomposition for Forward and Inverse Problems in Sharp-Gradient PDEs
  195. Activation-Deactivation: A General Framework for Robust Post-hoc Explainable AI
  196. Uncovering the Computational Ingredients of Human-Like Representations in LLMs
  197. Hypothesis-Driven Feature Manifold Analysis in LLMs via Supervised Multi-Dimensional Scaling
  198. VDW-GNNs: Vector diffusion wavelets for geometric graph neural networks
  199. The Good, the Bad, and the Sampled: a No-Regret Approach to Safe Online Classification
  200. Quantifying the noise sensitivity of the Wasserstein metric for images
  201. Revisiting Adversarial Training under Hyperspectral Image
  202. Random Feature Spiking Neural Networks
  203. Integrating AI and Ensemble Forecasting: Explainable Materials Planning with Scorecards and Trend Insights for a Large-Scale Manufacturer
  204. TextCAM: Explaining Class Activation Map with Text
  205. Improving Code Localization with Repository Memory
  206. SoftCFG: Uncertainty-guided Stable Guidance for Visual Autoregressive Model
  207. Visual Self-Refinement for Autoregressive Models
  208. A Scene is Worth a Thousand Features: Feed-Forward Camera Localization from a Collection of Image Features
  209. Adaptive Federated Few-Shot Rare-Disease Diagnosis with Energy-Aware Secure Aggregation
  210. JEPA-T: Joint-Embedding Predictive Architecture with Text Fusion for Image Generation
  211. Deep Learning-Based Approach for Improving Relational Aggregated Search
  212. A Neuro-Fuzzy System for Interpretable Long-Term Stock Market Forecasting
  213. Test-Time Search in Neural Graph Coarsening Procedures for the Capacitated Vehicle Routing Problem
  214. Bridging the Gap Between Simulated and Real Network Data Using Transfer Learning
  215. Modeling Market States with Clustering and State Machines
  216. InfVSR: Toward Consistency-Driven Streaming Generative Video Super-Resolution
  217. Resolution as a Direction: Vector-Panning Feature Alignment for Cross-Resolution Re-Identification
  218. Making, not Taking, the Best of N
  219. Equivariant Splitting: Self-supervised learning from incomplete data
  220. PAL-Net: A Point-Wise CNN with Patch-Attention for 3D Facial Landmark Localization
  221. "We are not Future-ready": Understanding AI Privacy Risks and Existing Mitigation Strategies from the Perspective of AI Developers in Europe
  222. Bridging Language Gaps: Advances in Cross-Lingual Information Retrieval with Multilingual LLMs
  223. BoMGene: Integrating Boruta-mRMR feature selection for enhanced Gene expression classification
  224. Intuitions of Machine Learning Researchers about Transfer Learning for Medical Image Classification
  225. FusionAdapter for Few-Shot Relation Learning in Multimodal Knowledge Graphs
  226. Span-level Detection of AI-generated Scientific Text via Contrastive Learning and Structural Calibration
  227. COMMET: orders-of-magnitude speed-up in finite element method via batch-vectorized neural constitutive updates
  228. GLAI: GreenLightningAI for Accelerated Training through Knowledge Decoupling
  229. AI-CNet3D: An Anatomically-Informed Cross-Attention Network with Multi-Task Consistency Fine-tuning for 3D Glaucoma Classification
  230. Unveiling Interesting Insights: Monte Carlo Tree Search for Knowledge Discovery
  231. False Discovery Rate Control via Bayesian Mirror Statistic
  232. Reducci'on de ruido por medio de autoencoders: caso de estudio con la se~nal GW150914
  233. A Visual Diagnostics Framework for District Heating Data: Enhancing Data Quality for AI-Driven Heat Consumption Prediction
  234. Target Population Synthesis using CT-GAN
  235. Removing Noise, not Finding Gold: Quality Filtering for Large-Scale Pretraining
  236. Population Synthesis using Incomplete Information
  237. ManagerBench: Evaluating the Safety-Pragmatism Trade-off in Autonomous LLMs
  238. LLM Routing with Dueling Feedback
  239. Feature Identification for Hierarchical Contrastive Learning
  240. Improving Cryptocurrency Pump-and-Dump Detection through Ensemble-Based Models and Synthetic Oversampling Techniques
  241. Controlled Comparison of Machine Learning Models for Fault Classification and Localization in Power System Protection
  242. Non-Euclidean Broximal Point Method: A Blueprint for Geometry-Aware Optimization
  243. Logical Consistency Between Disagreeing Experts and Its Role in AI Safety
  244. PhraseStereo: The First Open-Vocabulary Stereo Image Segmentation Dataset
  245. Semantic Bridges Between First Order c-Representations and Cost-Based Semantics: An Initial Perspective
  246. Family Matters: Language Transfer and Merging for Adapting Small LLMs to Faroese
  247. Foundation vs. Specialized Models: Evaluating Catastrophic Forgetting in Continual Time Series Forecasting
  248. What You See is What You Ask: Evaluating Audio Descriptions
  249. From Seeing to Predicting: A Vision-Language Framework for Trajectory Forecasting and Controlled Video Generation
  250. Planning-Augmented Sampling with Early Guidance for High-Reward Discovery
  251. Online Minimization of Polarization and Disagreement via Low-Rank Matrix Bandits
  252. Solar PV Installation Potential Assessment on Building Facades Based on Vision and Language Foundation Models
  253. MetaLogic: Robustness Evaluation of Text-to-Image Models via Logically Equivalent Prompts
  254. Complex System Exploration with Interactive Human Guidance
  255. AI in data science education: experiences from the classroom
  256. In-Place Feedback: Reliable Refinement for Multi-Turn Expert-LLM Collaboration
  257. GeoGraph: Geometric and Graph-based Ensemble Descriptors for Intrinsically Disordered Proteins
  258. Uncertainty-Aware Concept Bottleneck Models with Enhanced Interpretability
  259. ZQBA: Zero Query Black-box Adversarial Attack
  260. LEAP: Local ECT-Based Learnable Positional Encodings for Graphs
  261. Defect Segmentation in OCT scans of ceramic parts for non-destructive inspection using deep learning
  262. How Foundational are Foundation Models for Time Series Forecasting?
  263. Discovering Communities in Continuous-Time Temporal Networks by Optimizing L-Modularity
  264. Approximation of differential entropy in Bayesian optimal experimental design
  265. Neural Diffusion Processes for Physically Interpretable Survival Prediction
  266. EvolProver: Advancing Automated Theorem Proving by Evolving Formalized Problems via Symmetry and Difficulty
  267. Extreme Blind Image Restoration via Prompt-Conditioned Information Bottleneck
  268. DEAP DIVE: Dataset Investigation with Vision transformers for EEG evaluation
  269. Deep learning motion correction of quantitative stress perfusion cardiovascular magnetic resonance
  270. Comparison of Machine Learning Models to Classify Documents on Digital Development
  271. AttentionDep: Domain-Aware Attention for Explainable Depression Severity Assessment
  272. Physics-Informed Extreme Learning Machine (PIELM) for Tunnelling-Induced Soil-Pile Interactions
  273. Inclusive Easy-to-Read Generation for Individuals with Cognitive Impairments
  274. Relevance-Zone Reduction in Game Solving
  275. ProtoMask: Segmentation-Guided Prototype Learning
  276. Milco: Learned Sparse Retrieval Across Languages via a Multilingual Connector
  277. Beyond one-hot encoding? Journey into compact encoding for large multi-class segmentation
  278. Multi-Domain Brain Vessel Segmentation Through Feature Disentanglement
  279. Batch-CAM: Introduction to better reasoning in convolutional deep learning models
  280. Facilitating Cognitive Accessibility with LLMs: A Multi-Task Approach to Easy-to-Read Text Generation
  281. Unsupervised Unfolded rPCA (U2-rPCA): Deep Interpretable Clutter Filtering for Ultrasound Microvascular Imaging
  282. Weakly Supervised Cloud Detection Combining Spectral Features and Multi-Scale Deep Network
  283. OTTER: Open-Tagging via Text-Image Representation for Multi-modal Understanding
  284. FIN: Fast Inference Network for Map Segmentation
  285. Error Feedback for Muon and Friends
  286. LAKAN: Landmark-assisted Adaptive Kolmogorov-Arnold Network for Face Forgery Detection
  287. Virtual Fashion Photo-Shoots: Building a Large-Scale Garment-Lookbook Dataset
  288. Tenyidie Syllabification corpus creation and deep learning applications
  289. Hearing the Order: Investigating Position Bias in Large Audio-Language Models
  290. Is Model Editing Built on Sand? Revealing Its Illusory Success and Fragile Foundation
  291. HARPA: A Testability-Driven, Literature-Grounded Framework for Research Ideation
  292. What Did I Learn? Operational Competence Assessment for AI-Based Trajectory Planners
  293. Robust Context-Aware Object Recognition
  294. Disentangling Foreground and Background for vision-Language Navigation via Online Augmentation
  295. Multi-Agent Stage-wise Conservative Linear Bandits
  296. Designing Ambiguity Sets for Distributionally Robust Optimization Using Structural Causal Optimal Transport
  297. Probability calibration for precipitation nowcasting
  298. Multi-level Dynamic Style Transfer for NeRFs
  299. AI-Driven Self-Evolving Software: A Promising Path Toward Software Automation
  300. U-DFA: A Unified DINOv2-Unet with Dual Fusion Attention for Multi-Dataset Medical Segmentation
  301. Color Models in Image Processing: A Review and Experimental Comparison
  302. SAGE-LD: Towards Scalable and Generalizable End-to-End Language Diarization via Simulated Data Augmentation
  303. Arbitrary Generative Video Interpolation
  304. Private Online Learning against an Adaptive Adversary: Realizable and Agnostic Settings
  305. IntrusionX: A Hybrid Convolutional-LSTM Deep Learning Framework with Squirrel Search Optimization for Network Intrusion Detection
  306. Guaranteed Noisy CP Tensor Recovery via Riemannian Optimization on the Segre Manifold
  307. Are Large Language Models Chronically Online Surfers? A Dataset for Chinese Internet Meme Explanation
  308. Panorama: Fast-Track Nearest Neighbors
  309. Memory Determines Learning Direction: A Theory of Gradient-Based Optimization in State Space Models
  310. Assessing Foundation Models for Mold Colony Detection with Limited Training Data
  311. Mathematical Theory of Collinearity Effects on Machine Learning Variable Importance Measures
  312. PromptPilot: Improving Human-AI Collaboration Through LLM-Enhanced Prompt Engineering
  313. EMR-AGENT: Automating Cohort and Feature Extraction from EMR Databases
  314. Forestpest-YOLO: A High-Performance Detection Framework for Small Forestry Pests
  315. Bayesian Neural Networks for Functional ANOVA model
  316. Interpretable Machine Learning for Life Expectancy Prediction: A Comparative Study of Linear Regression, Decision Tree, and Random Forest
  317. Spectral Scaling Laws in Language Models: How Effectively Do Feed-Forward Networks Use Their Latent Space?
  318. Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum
  319. CardioBench: Do Echocardiography Foundation Models Generalize Beyond the Lab?
  320. Architectural Transformations and Emerging Verification Demands in AI-Enabled Cyber-Physical Systems
  321. Understanding Sensitivity of Differential Attention through the Lens of Adversarial Robustness
  322. EuroSpeech: A Multilingual Speech Corpus
  323. Adaptive Data-Knowledge Alignment in Genetic Perturbation Prediction
  324. JoyAgent-JDGenie: Technical Report on the GAIA
  325. A Fast and Precise Method for Searching Rectangular Tumor Regions in Brain MR Images
  326. A universal compression theory for lottery ticket hypothesis and neural scaling laws
  327. Relative-Absolute Fusion: Rethinking Feature Extraction in Image-Based Iterative Method Selection for Solving Sparse Linear Systems
  328. MOSS-Speech: Towards True Speech-to-Speech Models Without Text Guidance
  329. Agent-ScanKit: Unraveling Memory and Reasoning of Multimodal Agents via Sensitivity Perturbations
  330. Normal-Abnormal Guided Generalist Anomaly Detection
  331. Traj2Action: A Co-Denoising Framework for Trajectory-Guided Human-to-Robot Skill Transfer
  332. Black-Box Time-Series Domain Adaptation via Cross-Prompt Foundation Models
  333. PodEval: A Multimodal Evaluation Framework for Podcast Audio Generation
  334. Make a Video Call with LLM: A Measurement Campaign over Six Mainstream Apps
  335. Expandable Decision-Making States for Multi-Agent Deep Reinforcement Learning in Soccer Tactical Analysis
  336. On the joint estimation of flow fields and particle properties from Lagrangian data
  337. Analyzing Latent Concepts in Code Language Models
  338. Diagnosing Shortcut-Induced Rigidity in Continual Learning: The Einstellung Rigidity Index (ERI)
  339. Feature Identification via the Empirical NTK
  340. Rehearsal-free and Task-free Online Continual Learning With Contrastive Prompt
  341. On the Adversarial Robustness of Learning-based Conformal Novelty Detection
  342. TimeEmb: A Lightweight Static-Dynamic Disentanglement Framework for Time Series Forecasting
  343. Robust Spatiotemporally Contiguous Anomaly Detection Using Tensor Decomposition
  344. VLOD-TTA: Test-Time Adaptation of Vision-Language Object Detectors
  345. UrbanGraph: Physics-Informed Spatio-Temporal Dynamic Heterogeneous Graphs for Urban Microclimate Prediction
  346. Measuring and Controlling the Spectral Bias for Self-Supervised Image Denoising
  347. Cloud Investigation Automation Framework (CIAF): An AI-Driven Approach to Cloud Forensics
  348. Enhancing Rating Prediction with Off-the-Shelf LLMs Using In-Context User Reviews
  349. LongCodeZip: Compress Long Context for Code Language Models
  350. TokMem: One-Token Procedural Memory for Large Language Models
  351. Randomized Matrix Sketching for Neural Network Training and Gradient Monitoring
  352. Automated Evaluation can Distinguish the Good and Bad AI Responses to Patient Questions about Hospitalization
  353. On-the-Fly Data Augmentation via Gradient-Guided and Sample-Aware Influence Estimation
  354. Automated Structured Radiology Report Generation with Rich Clinical Context
  355. Learning a Zeroth-Order Optimizer for Fine-Tuning LLMs
  356. Improving Virtual Contrast Enhancement using Longitudinal Data
  357. Progressively Sampled Equality-Constrained Optimization
  358. Domain-Specialized Interactive Segmentation Framework for Meningioma Radiotherapy Planning
  359. Does Bigger Mean Better? Comparitive Analysis of CNNs and Biomedical Vision Language Modles in Medical Diagnosis
  360. EgoTraj-Bench: Towards Robust Trajectory Prediction Under Ego-view Noisy Observations
  361. Hierarchy-Aware Neural Subgraph Matching with Enhanced Similarity Measure
  362. Physics-Informed Neural Controlled Differential Equations for Scalable Long Horizon Multi-Agent Motion Forecasting
  363. SAGE-Music: Low-Latency Symbolic Music Generation via Attribute-Specialized Key-Value Head Sharing
  364. Graph2Region: Efficient Graph Similarity Learning with Structure and Scale Restoration
  365. A Deep Learning Pipeline for Epilepsy Genomic Analysis Using GPT-2 XL and NVIDIA H100
  366. Bayesian Distributional Models of Executive Functioning
  367. Train on Validation (ToV): Fast data selection with applications to fine-tuning
  368. Learning Passive Continuous-Time Dynamics with Multistep Port-Hamiltonian Gaussian Processes
  369. Efficient Probabilistic Tensor Networks
  370. Semantic-Driven AI Agent Communications: Challenges and Solutions
  371. Composer: A Search Framework for Hybrid Neural Architecture Design
  372. Multidimensional Bayesian Active Machine Learning of Working Memory Task Performance
  373. GDLNN: Marriage of Programming Language and Neural Networks for Accurate and Easy-to-Explain Graph Classification
  374. Combining Large Language Models and Gradient-Free Optimization for Automatic Control Policy Synthesis
  375. Parametric modeling of shear wave velocity profiles for the conterminous U.S
  376. The Transformer Cookbook
  377. CINDES: Classification induced neural density estimator and simulator
  378. Continual Learning with Query-Only Attention
  379. Attribution Gradients: Incrementally Unfolding Citations for Critical Examination of Attributed AI Answers
  380. End-to-End Training of High-Dimensional Optimal Control with Implicit Hamiltonians via Jacobian-Free Backpropagation