mlsanityData to 14 Oct 2026

Papers

New on arXiv

Tue 20 May 2025

601 papers

  1. Adaptive Shielding for Safe Reinforcement Learning under Hidden-Parameter Dynamics ShiftsDeep reinforcement learning methods → Safe and constrained RL
  2. Prefill-Guided Thinking for zero-shot detection of AI-generated imagesLLM reasoning → Multimodal reasoning
  3. Output Scaling: YingLong-Delayed Chain of Thought in a Large Pretrained Time Series Forecasting ModelLLM reasoning → Time series reasoning
  4. From Reasoning to Code: GRPO Optimization for Underrepresented LanguagesLLM reasoning → Reinforcement learning for reasoning
  5. Co-LoRA: Collaborative Model Personalization on Heterogeneous Multi-Modal ClientsLLM agents and tool use → Agentic AI for wireless networks
  6. Modality-Balancing Preference Optimization of Large Multimodal Models by Adversarial Negative MiningMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  7. NovelHopQA: Diagnosing Multi-Hop Reasoning Failures in Long Narrative ContextsLLM reasoning → Reasoning benchmarks and evaluation
  8. Riemannian Flow Matching for Brain Connectivity Matrices via Pullback GeometryDiffusion models → Flow matching, time series and science
  9. Chain-of-Thought Driven Adversarial Scenario Extrapolation for Robust Language ModelsLLM reasoning → Reasoning for agents, planning and code +1
  10. Advancing Multi-Agent RAG Systems with Minimalist Reinforcement LearningRetrieval-augmented generation → Agentic RAG, agents and memory +1
  11. GemMaroc: Unlocking Darija Proficiency in LLMs with Minimal DataLLM reasoning → Reasoning benchmarks and evaluation
  12. Semi-Clairvoyant Scheduling of Speculative Decoding Requests to Minimize LLM Inference LatencyEfficient LLM inference and serving → Speculative decoding
  13. Mechanistic Interpretability of GPT-like Models on Summarization TasksMechanistic interpretability → Knowledge and representations inside LLMs
  14. JARVIS: A Multi-Agent Code Assistant for High-Quality EDA Script GenerationLLM agents and tool use → Software engineering coding agents
  15. Flattening Hierarchies with Policy BootstrappingSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training +1
  16. Multimodal Cultural Safety: Evaluation Framework and Alignment StrategiesMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  17. Self-Evolving Curriculum for LLM ReasoningLLM reasoning → Reinforcement learning for reasoning +1
  18. STree: Speculative Tree Decoding for Hybrid State-Space ModelsEfficient LLM inference and serving → Speculative decoding
  19. Programmatic Video Prediction Using Large Language ModelsWorld models → Embodied and robot world models
  20. Reinforcement Learning from User FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
  21. Unlearning Algorithmic Biases over GraphsLLM safety and security → Graph unlearning
  22. FOL-Traces: Verified First-Order Logic Reasoning Traces at ScaleLLM reasoning → Reasoning benchmarks and evaluation
  23. Super-Resolution Optical Coherence Tomography Using Diffusion Model-Based Plug-and-Play PriorsDiffusion models → Medical imaging and segmentation
  24. Personalized Diffusion Model Reshapes Cold-Start Bundle RecommendationDiffusion models → Diffusion recommenders
  25. REFLEX: Metacognitive Reasoning for Reflective Zero-Shot Robotic Planning with Large Language ModelsLLM reasoning → Spatial and embodied reasoning
  26. Learning POMDPs with Linear Function Approximation and Finite MemoryDeep reinforcement learning methods → RL theory and sample complexity
  27. Balanced and Elastic End-to-end Training of Dynamic LLMsEfficient LLM inference and serving → Serving systems and request scheduling
  28. EasyMath: A 0-shot Math Benchmark for SLMsLLM reasoning → Mathematical reasoning
  29. MAATS: A Multi-Agent Automated Translation System Based on MQM EvaluationLLM agents and tool use → General LLM agent frameworks and benchmarks
  30. SEPS: A Separability Measure for Robust Unlearning in LLMsLLM safety and security → Machine unlearning
  31. Sample and Computationally Efficient Continuous-Time Reinforcement Learning with General Function ApproximationDeep reinforcement learning methods → RL theory and sample complexity
  32. Imitation Learning via Focused SatisficingOffline RL and imitation learning from data → Imitation learning methods
  33. DORA: Object Affordance-Guided Reinforcement Learning for Dexterous Robotic ManipulationDeep reinforcement learning methods → RL for robot locomotion and manipulation
  34. Language Mixing in Reasoning Language Models: Patterns, Impact, and Internal CausesLLM reasoning → Reasoning benchmarks and evaluation
  35. Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning ModelsLLM reasoning → Mathematical reasoning +1
  36. Self Distillation via Iterative Constructive PerturbationsKnowledge distillation → General knowledge distillation methods
  37. Communication-Efficient Diffusion Denoising Parallelization via Reuse-then-Predict MechanismDiffusion models → Diffusion foundations and sampling
  38. Time Series Similarity Score Functions to Monitor and Interact with the Training and Denoising Process of a Time Series Diffusion Model applied to a Human Activity Recognition Dataset based on IMUsDiffusion models → Flow matching, time series and science
  39. R&D-Agent: An LLM-Agent Framework Towards Autonomous Data ScienceLLM agents and tool use → Web, search, and research agents
  40. The Energy Cost of Reasoning: Analyzing Energy Usage in LLMs with Test-time ComputeLLM reasoning → Test-time compute and efficient thinking
  41. Uncovering Cultural Representation Disparities in Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  42. MORALISE: A Structured Benchmark for Moral Alignment in Visual Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  43. The Evolution of Alpha in Finance Harnessing Human Insight and LLM AgentsLLM agents and tool use → Financial trading and forecasting agents
  44. Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion TransformersDiffusion models → Video generation
  45. Mind the Gap: Bridging Thought Leap for Improved Chain-of-Thought TuningLLM reasoning → Prompting and chain-of-thought reasoning
  46. UniGen: Enhanced Training & Test-Time Strategies for Unified Multimodal Understanding and GenerationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  47. Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional TrainingLLM reasoning → Test-time compute and efficient thinking +1
  48. NExT-Search: Rebuilding User Feedback Ecosystem for Generative AI SearchLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
  49. Visionary-R1: Mitigating Shortcuts in Visual Reasoning with Reinforcement LearningLLM reasoning → Multimodal reasoning
  50. Reward Reasoning ModelLLM reasoning → Reinforcement learning for reasoning +1
  51. Training-Free Watermarking for Autoregressive Image GenerationLLM safety and security → Watermarking generated content and models
  52. ContextAgent: Context-Aware Proactive LLM Agents with Open-World Sensory PerceptionsLLM agents and tool use → Multimodal and embodied agents
  53. SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early AlignmentLLM reasoning → Reasoning for agents, planning and code +1
  54. Beyond Words: Multimodal LLM Knows When to SpeakMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  55. General-Reasoner: Advancing LLM Reasoning Across All DomainsLLM reasoning → Reinforcement learning for reasoning
  56. VideoEval-Pro: Robust and Realistic Long Video Understanding EvaluationMultimodal LLMs / vision-language models → Video understanding with MLLMs
  57. Think Only When You Need with Large Hybrid-Reasoning ModelsLLM reasoning → Test-time compute and efficient thinking
  58. Debating for Better Reasoning: An Unsupervised Multimodal ApproachLLM reasoning → Multimodal reasoning +1
  59. TinyV: Reducing False Negatives in Verification Improves RL for LLM ReasoningLLM reasoning → Reinforcement learning for reasoning
  60. The Hawthorne Effect in Reasoning Models: Evaluating and Steering Test AwarenessLLM reasoning → Test-time compute and efficient thinking +1
  61. SATBench: Benchmarking LLMs' Logical Reasoning via Automated Puzzle Generation from SAT FormulasLLM reasoning → Reasoning benchmarks and evaluation
  62. sudoLLM: On Multi-role Alignment of Language ModelsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  63. Let LRMs Break Free from Overthinking via Self-Braking TuningLLM reasoning → Test-time compute and efficient thinking
  64. Context Reasoner: Incentivizing Reasoning Capability for Contextualized Privacy and Safety Compliance via Reinforcement LearningLLM reasoning → Reasoning for agents, planning and code
  65. Can Pruning Improve Reasoning? Revisiting Long-CoT Compression with Capability in Mind for Better ReasoningLLM reasoning → Test-time compute and efficient thinking
  66. KIPPO: Koopman-Inspired Proximal Policy OptimizationDeep reinforcement learning methods → RL theory and sample complexity
  67. Bellman operator convergence enhancements in reinforcement learning algorithmsDeep reinforcement learning methods → RL theory and sample complexity
  68. KORGym: A Dynamic Game Platform for LLM Reasoning EvaluationLLM reasoning → Reasoning for agents, planning and code
  69. Breaking Bad Tokens: Detoxification of LLMs Using Sparse AutoencodersMechanistic interpretability → Steering and probing for LLM safety
  70. Lessons from Defending Gemini Against Indirect Prompt InjectionsLLM safety and security → Prompt injection and agent security
  71. Energy-Efficient Deep Reinforcement Learning with Spiking TransformersDeep reinforcement learning methods → Spiking and neuromorphic RL
  72. SifterNet: A Generalized and Model-Agnostic Trigger Purification ApproachLLM safety and security → Backdoor and data poisoning attacks
  73. Internal Chain-of-Thought: Empirical Evidence for Layer-wise Subtask Scheduling in LLMsLLM reasoning → Prompting and chain-of-thought reasoning
  74. RoboRAN: A Unified Robotics Framework for Reinforcement Learning-Based Autonomous NavigationDeep reinforcement learning methods → RL for robot navigation and UAV control
  75. Guarded Query Routing for Large Language ModelsLLM safety and security → Safety alignment, refusal and guardrails
  76. Sparc3D: Sparse Representation and Construction for High-Resolution 3D Shapes ModelingDiffusion models → 3D, point cloud and scene generation
  77. Latent Flow TransformerDiffusion models → Diffusion foundations and sampling
  78. Learning to Integrate Diffusion ODEs by Averaging the DerivativesDiffusion models → Diffusion foundations and sampling
  79. Reasoning Models Better Express Their ConfidenceLLM reasoning → Test-time compute and efficient thinking
  80. MoMoE: Mixture of Moderation Experts Framework for AI-Assisted Online GovernanceLLM safety and security → Safety alignment, refusal and guardrails
  81. PlanGPT-VL: Enhancing Urban Planning with Domain-Specific Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  82. Reliable Proof Generation with LLMs via Analogical Retrieval and Symbolic Verification: A Case Study in Euclidean GeometryLLM reasoning → Mathematical reasoning
  83. Attributional Safety Failures in Large Language Models under Code-Mixed PerturbationsLLM safety and security → Safety alignment, refusal and guardrails
  84. FlowTSE: Target Speaker Extraction with Flow MatchingDiffusion models → Audio, speech and music
  85. Not All Correct Answers Are Equal: Why Your Distillation Source MattersLLM reasoning → Prompting and chain-of-thought reasoning
  86. RAVENEA: A Benchmark for Multimodal Retrieval-Augmented Visual Culture UnderstandingMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning +1
  87. VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to RankLLM reasoning → Multimodal reasoning
  88. Interpretable Reinforcement Learning for Load Balancing using Kolmogorov-Arnold NetworksDeep reinforcement learning methods → RL for energy, networks and operations
  89. CtrlDiff: Boosting Large Diffusion Language Models with Dynamic Block Prediction and Controllable GenerationDiffusion models → Discrete and text diffusion
  90. Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language ModelsEfficient LLM inference and serving → Visual token pruning in multimodal models
  91. Semantically-driven Deep Reinforcement Learning for Inspection Path PlanningDeep reinforcement learning methods → RL for robot navigation and UAV control
  92. Creative Preference OptimizationLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  93. Rank-K: Test-Time Reasoning for Listwise RerankingLLM reasoning → Knowledge- and tool-augmented reasoning
  94. From Templates to Natural Language: Generalization Challenges in Instruction-Tuned LLMs for Spatial ReasoningLLM reasoning → Spatial and embodied reasoning
  95. Scaling Low-Resource MT via Synthetic Data Generation with LLMsSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  96. SAE-FiRE: Enhancing Earnings Surprise Predictions Through Sparse Autoencoder Feature SelectionMechanistic interpretability → SAE features and their applications
  97. SCOPE: Compress Mathematical Reasoning Steps for Efficient Automated Process AnnotationLLM reasoning → Reinforcement learning for reasoning +1
  98. Hidden Ghost Hand: Unveiling Backdoor Vulnerabilities in MLLM-Powered Mobile GUI AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  99. PRL: Prompts from Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  100. Investigating and Enhancing the Robustness of Large Multimodal Models Against Temporal InconsistencyMultimodal LLMs / vision-language models → Video understanding with MLLMs
All 601
  1. ViC-Bench: Benchmarking Visual-Interleaved Chain-of-Thought Capability in MLLMs with Free-Style Intermediate State RepresentationsLLM reasoning → Multimodal reasoning +1
  2. Unearthing Gems from Stones: Policy Optimization with Negative Sample Augmentation for LLM ReasoningLLM reasoning → Reinforcement learning for reasoning
  3. Log-Augmented Generation: Scaling Test-Time Reasoning with Reusable ComputationLLM reasoning → Test-time compute and efficient thinking +2
  4. Causal Cartographer: From Mapping to Reasoning Over Counterfactual WorldsWorld models → World models for language agents +1
  5. Beyond the First Error: Process Reward Models for Reflective Mathematical ReasoningLLM reasoning → Reinforcement learning for reasoning +1
  6. SCAN: Semantic Document Layout Analysis for Textual and Visual Retrieval-Augmented GenerationMultimodal LLMs / vision-language models → Document understanding and multimodal RAG +1
  7. From ASR to ASP: Evaluating Prompt Attack Vulnerabilities Against Open-Source LLMsLLM safety and security → Prompt injection and agent security
  8. Towards Embodied Cognition in Robots via Spatially Grounded Synthetic WorldsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  9. DeepEyes: Incentivizing "Thinking with Images" via Reinforcement LearningLLM reasoning → Multimodal reasoning +2
  10. Vision-Language Modeling Meets Remote Sensing: Models, Datasets and PerspectivesMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  11. Vid2World: Crafting Video Diffusion Models to Interactive World ModelsWorld models → Video-generation world models and simulators +1
  12. WirelessMathBench: A Mathematical Modeling Benchmark for LLMs in Wireless CommunicationsLLM reasoning → Mathematical reasoning
  13. Towards eliciting latent knowledge from LLMs with mechanistic interpretabilityMechanistic interpretability → Knowledge and representations inside LLMs
  14. Plane Geometry Problem Solving with Multi-modal Reasoning: A SurveyLLM reasoning → Spatial and embodied reasoning +1
  15. Scaling and Enhancing LLM-based AVSR: A Sparse Mixture of Projectors ApproachMixture-of-experts → Multimodal MoE models
  16. Breaking Down Video LLM Benchmarks: Knowledge, Spatial Perception, or True Temporal Understanding?LLM reasoning → Multimodal reasoning
  17. Exploring Jailbreak Attacks on LLMs through Intent Concealment and DiversionLLM safety and security → Jailbreaking
  18. Teaching Small Language Models to Learn Logic through Meta-LearningLLM reasoning → Reasoning benchmarks and evaluation
  19. Studying the Role of Input-Neighbor Overlap in Retrieval-Augmented Language Models Training EfficiencyRetrieval-augmented generation → Generation and context integration
  20. Empowering LLMs in Task-Oriented Dialogues: A Domain-Independent Multi-Agent Framework and Fine-Tuning StrategyLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  21. EVA: Evolving Semantic Adversaries for Red-Teaming GUI Agents Against Environmental Injection AttacksLLM agents and tool use → Agent threats, guardrails and governance +1
  22. Think-J: Learning to Think for Generative LLM-as-a-JudgeLLM reasoning → Reinforcement learning for reasoning +1
  23. AAPO: Enhancing the Reasoning Capabilities of LLMs with Advantage MarginLLM reasoning → Reinforcement learning for reasoning
  24. Speculative Decoding Reimagined for Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  25. Mitigating Hallucination in Large Vision-Language Models through Aligning Attention Distribution to Information FlowMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  26. Instructing Text-to-Image Diffusion Models via Classifier-Guided Semantic OptimizationDiffusion models → Image generation, text-to-image and editing
  27. Visual Agentic Reinforcement Fine-TuningLLM reasoning → Multimodal reasoning +1
  28. UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement LearningLLM reasoning → Multimodal reasoning
  29. Reinforcement Learning vs. Distillation: Understanding Accuracy and Capability in LLM ReasoningLLM reasoning → Reinforcement learning for reasoning +1
  30. Safety Degradation in AI AgentsLLM agents and tool use → Agent threats, guardrails and governance
  31. Embedded Mean Field Reinforcement Learning for Perimeter-defense GameDeep reinforcement learning methods → RL for robot navigation and UAV control
  32. Towards Omnidirectional Reasoning with 360-R1: A Dataset, Benchmark, and GRPO-based MethodLLM reasoning → Spatial and embodied reasoning
  33. Safety Subspaces are Not Linearly Distinct: A Fine-Tuning Case StudyLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  34. ThinkSwitcher: When to Think Hard, When to Think FastLLM reasoning → Test-time compute and efficient thinking
  35. Tokenization Constraints in LLMs: A Study of Symbolic and Arithmetic Reasoning LimitsLLM reasoning → Mathematical reasoning
  36. Cheaper, Better, Faster, Stronger: Robust Text-to-SQL without Chain-of-Thought or Fine-TuningLLM reasoning → Knowledge- and tool-augmented reasoning
  37. THOR-MoE: Hierarchical Task-Guided and Context-Responsive Routing for Neural Machine TranslationMixture-of-experts → MoE large language models
  38. LMP: Leveraging Motion Prior in Zero-Shot Video Generation with Diffusion TransformerDiffusion models → Video generation
  39. DSMentor: Enhancing Data Science Agents with Curriculum Learning and Online Knowledge AccumulationLLM agents and tool use → Web, search, and research agents
  40. Breaking Language Barriers or Reinforcing Bias? A Study of Gender and Racial Disparities in Multilingual Contrastive Vision Language ModelsMultimodal LLMs / vision-language models → Social bias and fairness in VLMs
  41. ReactDiff: Latent Diffusion for Facial Reaction GenerationDiffusion models → Audio, speech and music
  42. MM-Agent: LLM as Agents for Real-world Mathematical Modeling ProblemLLM agents and tool use → Educational agents and math problem solving
  43. SHARP: Synthesizing High-quality Aligned Reasoning Problems for Large Reasoning Models Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning
  44. s3: You Don't Need That Much Data to Train a Search Agent via RLRetrieval-augmented generation → Agentic RAG, agents and memory +1
  45. Multimodal Mixture of Low-Rank Experts for Sentiment Analysis and Emotion RecognitionMixture-of-experts → Multimodal MoE models
  46. Building a Stable Planner: An Extended Finite State Machine Based Planning Module for Mobile GUI AgentLLM agents and tool use → GUI and mobile agents
  47. RL of Thoughts: Navigating LLM Reasoning with Inference-time Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning
  48. FlowQ: Energy-Guided Flow Policies for Offline Reinforcement LearningDiffusion models → Diffusion and flow policies for robotics +1
  49. Local Mixtures of Experts: Essentially Free Test-Time Training via Model MergingMixture-of-experts → MoE large language models
  50. MAS-KCL: Knowledge component graph structure learning with large language model-based agentic workflowLLM agents and tool use → Web, search, and research agents
  51. Intra-class Patch Swap for Self-DistillationKnowledge distillation → General knowledge distillation methods
  52. Self-Reasoning Language Models: Unfold Hidden Reasoning Chains with Few Reasoning CatalystLLM reasoning → Test-time compute and efficient thinking
  53. Invisible Entropy: Towards Safe and Efficient Low-Entropy LLM WatermarkingLLM safety and security → Watermarking generated content and models
  54. DiagnosisArena: Benchmarking Diagnostic Reasoning for Large Language ModelsLLM reasoning → Clinical and biomedical applications
  55. AudioJailbreak: Jailbreak Attacks against End-to-End Large Audio-Language ModelsLLM safety and security → Audio jailbreaks and speech backdoors
  56. Generalizable Multispectral Land Cover Classification via Frequency-Aware Mixture of Low-Rank Token ExpertsMixture-of-experts → Vision mixture-of-experts
  57. BAR: A Backward Reasoning based Agent for Complex Minecraft TasksLLM reasoning → Reasoning for agents, planning and code +1
  58. Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  59. Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement LearningRetrieval-augmented generation → Agentic RAG, agents and memory +1
  60. NOVA: A Benchmark for Anomaly Localization and Clinical Reasoning in Brain MRILLM reasoning → Clinical and biomedical applications +1
  61. FractalMamba++: Scaling Vision Mamba Across Resolutions via Hilbert Fractal GeometryState-space sequence models (S4, Mamba) → Vision Mamba backbones
  62. Improved Methods for Model Pruning and Knowledge DistillationKnowledge distillation → Knowledge distillation for LLMs
  63. Selective Structured State Space for Multispectral-fused Small Target DetectionState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  64. ProMind-LLM: Proactive Mental Health Care via Causal Reasoning with Sensor DataLLM reasoning → Clinical and biomedical applications
  65. Adaptive Inference-Time Scaling via Cyclic Diffusion SearchLLM reasoning → Diffusion reasoning and test-time scaling +1
  66. ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMsLLM reasoning → Reasoning benchmarks and evaluation
  67. AutoBio: A Simulation and Benchmark for Robotic Automation in Digital Biology LaboratoryVision-language-action models → Generalist VLA models and benchmarks
  68. Activation-Guided Consensus Merging for Large Language ModelsLLM reasoning → Test-time compute and efficient thinking
  69. StPR: Spatiotemporal Preservation and Routing for Exemplar-Free Video Class-Incremental LearningMixture-of-experts → Mixture of LoRA experts
  70. Divide by Question, Conquer by Agent: SPLIT-RAG with Question-Driven Graph PartitioningRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG +1
  71. The Hallucination Tax of Reinforcement FinetuningLLM reasoning → Hallucination detection and mitigation
  72. RIDGECUT: Learning Graph Partitioning with Rings and WedgesDeep reinforcement learning methods → RL for games and combinatorial optimization
  73. Combining Deterministic Enhanced Conditions with Dual-Streaming Encoding for Diffusion-Based Speech EnhancementDiffusion models → Audio, speech and music
  74. DRP: Distilled Reasoning Pruning with Skill-aware Step Decomposition for Efficient Large Reasoning ModelsLLM reasoning → Prompting and chain-of-thought reasoning +1
  75. Toward Effective Reinforcement Learning Fine-Tuning for Medical VQA in Vision-Language ModelsLLM reasoning → Clinical and biomedical applications +1
  76. CAFES: A Collaborative Multi-Agent Framework for Multi-Granular Multimodal Essay ScoringLLM agents and tool use → General LLM agent frameworks and benchmarks
  77. MultiDrive: A Co-Simulation Framework Bridging 2D and 3D Driving Simulation for AV Software ValidationEnd-to-end autonomous driving → Adversarial scenarios and safety testing
  78. Beyond Text: Unveiling Privacy Vulnerabilities in Multi-modal Retrieval-Augmented GenerationRetrieval-augmented generation → Privacy and security of RAG
  79. FlashThink: An Early Exit Method For Efficient ReasoningLLM reasoning → Test-time compute and efficient thinking +1
  80. A Probabilistic Perspective on Model CollapseSynthetic data and self-improvement for LLMs → Model collapse from synthetic data
  81. Visual Instruction Bottleneck TuningMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  82. MLZero: A Multi-Agent System for End-to-end Machine Learning AutomationLLM agents and tool use → Web, search, and research agents
  83. DrugPilot: LLM-based Parameterized Reasoning Agent for Drug DiscoveryLLM reasoning → Clinical and biomedical applications +1
  84. RLVR-World: Training World Models with Reinforcement LearningWorld models → Latent dynamics models and model-based RL
  85. BiCrossMamba-ST: Speech Deepfake Detection with Bidirectional Mamba Spectro-Temporal Cross-AttentionState-space sequence models (S4, Mamba) → Speech and audio SSMs
  86. Time Reversal Symmetry for Efficient Robotic Manipulations in Deep Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  87. APEX: Empowering LLMs with Physics-Based Task Planning for Real-time InsightLLM reasoning → Spatial and embodied reasoning
  88. Efficient Agent Training for Computer UseLLM agents and tool use → GUI and mobile agents
  89. Let's Verify Math Questions Step by StepLLM reasoning → Mathematical reasoning
  90. Mapping the Minds of LLMs: A Graph-Based Analysis of Reasoning LLMLLM reasoning → Prompting and chain-of-thought reasoning
  91. InSpire: Vision-Language-Action Models with Intrinsic Spatial ReasoningLLM reasoning → Spatial and embodied reasoning +2
  92. Game-RL: Synthesizing Multimodal Verifiable Game Data to Boost VLMs' General ReasoningLLM reasoning → Multimodal reasoning
  93. U-SAM: An audio language Model for Unified Speech, Audio, and Music UnderstandingMixture-of-experts → Multimodal MoE models
  94. InfiFPO: Implicit Model Fusion via Preference Optimization in Large Language ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  95. Safety2Drive: Safety-Critical Scenario Benchmark for the Evaluation of Autonomous DrivingEnd-to-end autonomous driving → Adversarial scenarios and safety testing
  96. Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM ReasoningLLM reasoning → Test-time compute and efficient thinking +1
  97. PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking AttacksLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  98. Domain Adaptation of VLM for Soccer Video UnderstandingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  99. A Semantic Information-based Hierarchical Speech Enhancement Method Using Factorized Codec and Diffusion ModelDiffusion models → Audio, speech and music
  100. EfficientLLM: Efficiency in Large Language ModelsMixture-of-experts → Efficient MoE training and inference systems
  101. Toward Real-World Cooperative and Competitive Soccer with Quadrupedal Robot TeamsDeep reinforcement learning methods → RL for robot locomotion and manipulation
  102. Pushing the Frontiers of Self-Distillation Prototypes Network with Dimension Regularization and Score NormalizationKnowledge distillation → Speech and audio distillation
  103. Structured Agent Distillation for Large Language ModelLLM agents and tool use → General LLM agent frameworks and benchmarks
  104. Fragments to Facts: Partial-Information Fragment Inference from LLMsLLM safety and security → Membership inference attacks
  105. InstanceBEV: Unifying Instance and BEV Representation for 3D Panoptic SegmentationEnd-to-end autonomous driving → VLMs for autonomous driving
  106. Context-Free Synthetic Data Mitigates ForgettingSynthetic data and self-improvement for LLMs → Model collapse from synthetic data
  107. Interpretable Traces, Unexpected Outcomes: Investigating the Disconnect in Trace-Based Knowledge DistillationLLM reasoning → Prompting and chain-of-thought reasoning +1
  108. Scalable Autoregressive 3D Molecule GenerationDiffusion models → Flow matching, time series and science
  109. Preference Learning with Lie Detectors can Induce Honesty or EvasionLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  110. Super Kawaii Vocalics: Amplifying the "Cute" Factor in Computer Voice
  111. Extreme mass distributions for quasi-copulas
  112. Deep Learning Approach to Bearing and Induction Motor Fault Diagnosis via Data Fusion
  113. Forward Target Propagation: A Forward-Only Approach to Global Error Credit Assignment via Local Losses
  114. Enhancing Epidemic Forecasting: Evaluating the Role of Mobility Data and Graph Convolutional Networks
  115. Evaluating Privacy-Utility Tradeoffs in Synthetic Smart Grid Data
  116. When Algorithms Play Favorites: Lookism in the Generation and Perception of Faces
  117. OntoGSN: An Ontology-Based Framework for Semantic Management and Extension of Assurance Cases
  118. FlowBERT: Prompt-tuned BERT for variable flow field prediction
  119. Adaptive stable distribution and Hurst exponent by method of moments moving estimator for nonstationary time series
  120. UniSim: A Unified Simulator for Time-Coarsened Dynamics of Biomolecules
  121. Fusing Cross-Domain Knowledge from Multimodal Data to Solve Problems in the Physical World
  122. Machine Learning for Consistency Violation Faults Analysis
  123. Inter(sectional) Alia(s): Ambiguity in Voice Agent Identity via Intersectional Japanese Self-Referents
  124. Amadeus-Verbo Technical Report: The powerful Qwen2.5 family models trained in Portuguese
  125. Unified AI for Accurate Audio Anomaly Detection
  126. More-than-Human Storytelling: Designing Longitudinal Narrative Engagements with Generative AI
  127. Enhancing Vision Transformer Explainability Using Artificial Astrocytes
  128. The Role of Visualization in LLM-Assisted Knowledge Graph Systems: Effects on User Trust, Exploration, and Workflows
  129. Large Language Model Powered Decision Support for a Metal Additive Manufacturing Knowledge Graph
  130. Acoustic and Machine Learning Methods for Speech-Based Suicide Risk Assessment: A Systematic Review
  131. Large Language Model-Driven Distributed Integrated Multimodal Sensing and Semantic Communications
  132. Large Language Models Implicitly Learn to See and Hear Just By Reading
  133. EmoSign: A Multimodal Dataset for Understanding Emotions in American Sign Language
  134. From Weak Labels to Strong Results: Utilizing 5,000 Hours of Noisy Classroom Transcripts with Minimal Accurate Data
  135. Informatics for Food Processing
  136. GSDFuse: Capturing Cognitive Inconsistencies from Multi-Dimensional Weak Signals in Social Media Steganalysis
  137. From nuclear safety to LLM security: Applying non-probabilistic risk management strategies to build safe and secure LLM-powered systems
  138. Scale-invariant Attention
  139. Not Minds, but Signs: Reframing LLMs through Semiotics
  140. GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace
  141. Streamlining HTTP Flooding Attack Detection through Incremental Feature Selection
  142. Impact of Frame Rates on Speech Tokenizer: A Case Study on Mandarin and English
  143. Development and Validation of Engagement and Rapport Scales for Evaluating User Experience in Multimodal Dialogue Systems
  144. DisastIR: A Comprehensive Information Retrieval Benchmark for Disaster Management
  145. Integration of TinyML and LargeML: A Survey of 6G and Beyond
  146. Exploring Moral Exercises for Human Oversight of AI systems: Insights from Three Pilot Studies
  147. SDLog: A Deep Learning Framework for Detecting Sensitive Information in Software Logs
  148. DECASTE: Unveiling Caste Stereotypes in Large Language Models through Multi-Dimensional Bias Analysis
  149. Anomaly Detection Based on Critical Paths for Deep Neural Networks
  150. The Achilles Heel of AI: Fundamentals of Risk-Aware Training Data for High-Consequence Models
  151. MedBrowseComp: Benchmarking Medical Deep Research and Computer Use
  152. Privacy Preserving Conversion Modeling in Data Clean Room
  153. MultiMAE Meets Earth Observation: Pre-training Multi-modal Multi-task Masked Autoencoders for Earth Observation Tasks
  154. Soft Prompts for Evaluation: Measuring Conditional Distance of Capabilities
  155. To Be or Not To Be: Vector ontologies as a truly formal ontological framework
  156. Scan, Materialize, Simulate: A Generalizable Framework for Physically Grounded Robot Planning
  157. Foundations of Unknown-aware Machine Learning
  158. Colors Matter: AI-Driven Exploration of Human Feature Colors
  159. Pathobiological Dictionary Defining Pathomics and Texture Features: Addressing Understandable AI Issues in Personalized Liver Cancer; Dictionary Version LCP1.0
  160. Too Long, Didn't Model: Decomposing LLM Long-Context Understanding With Novels
  161. SecCAN: An Extended CAN Controller with Embedded Intrusion Detection
  162. TxPert: Leveraging Biochemical Relationships for Out-of-Distribution Transcriptomic Perturbation Prediction
  163. Reliable Decision Support with LLMs: A Framework for Evaluating Consistency in Binary Text Classification Applications
  164. ConspEmoLLM-v2: A robust and stable model to detect sentiment-transformed conspiracy theories
  165. TCSinger 2: Customizable Multilingual Zero-shot Singing Voice Synthesis
  166. Understanding 6G through Language Models: A Case Study on LLM-aided Structured Entity Extraction in Telecom Domain
  167. Concept Incongruence: An Exploration of Time and Death in Role Playing
  168. When to retrain a machine learning model
  169. Multi-Channel Swin Transformer Framework for Bearing Remaining Useful Life Prediction
  170. Feature-Weighted MMD-CORAL for Domain Adaptation in Power Transformer Fault Diagnosis
  171. On the Day They Experience: Awakening Self-Sovereign Experiential AI Agents
  172. Scaling Laws for State Dynamics in Large Language Models
  173. In-Context Learning Boosts Speech Recognition via Human-like Adaptation to Speakers and Language Varieties
  174. Strategic Planning and Rationalizing on Trees Make LLMs Better Debaters
  175. Polar Sparsity: High Throughput Batched LLM Inferencing with Scalable Contextual Sparsity
  176. An active learning framework for multi-group mean estimation
  177. Incorporating Token Usage into Prompting Strategy Evaluation
  178. A self-regulated convolutional neural network for classifying variable stars
  179. Towards Inclusive ASR: Investigating Voice Conversion for Dysarthric Speech Recognition in Low-Resource Languages
  180. Saten: Sparse Augmented Tensor Networks for Post-Training Compression of Large Language Models
  181. VisTopics: A Visual Semantic Unsupervised Approach to Topic Modeling of Video and Image Data
  182. LOBSTUR: A Local Bootstrap Framework for Tuning Unsupervised Representations in Graph Neural Networks
  183. UPTor: Unified 3D Human Pose Dynamics and Trajectory Prediction for Human-Robot Interaction
  184. Replay Attacks Against Audio Deepfake Detection
  185. Open-Set Semi-Supervised Learning for Long-Tailed Medical Datasets
  186. Subquadratic Algorithms and Hardness for Attention with Any Temperature
  187. In-depth Research Impact Summarization through Fine-Grained Temporal Citation Analysis
  188. Deep Koopman operator framework for causal discovery in nonlinear dynamical systems
  189. Text Generation Beyond Discrete Token Sampling
  190. FisherSFT: Data-Efficient Supervised Fine-Tuning of Language Models Using Information Gain
  191. Assimilative Causal Inference
  192. Tracing Multilingual Factual Knowledge Acquisition in Pretraining
  193. WebNovelBench: Placing LLM Novelists on the Web Novel Distribution
  194. GraphemeAug: A Systematic Approach to Synthesized Hard Negative Keyword Spotting Examples
  195. Out-of-Distribution Generalization of In-Context Learning: A Low-Dimensional Subspace Perspective
  196. Place Cells as Multi-Scale Position Embeddings: Random Walk Transition Kernels for Path Planning
  197. Automated Journalistic Questions: A New Method for Extracting 5W1H in French
  198. SurvUnc: A Meta-Model Based Uncertainty Quantification Framework for Survival Analysis
  199. Text embedding models can be great data engineers
  200. KO: Kinetics-inspired Neural Optimizer with PDE Simulation Approaches
  201. This Time is Different: An Observability Perspective on Time Series Foundation Models
  202. Deep Learning-Based Forecasting of Boarding Patient Counts to Address ED Overcrowding
  203. Unifying Inference-Time Planning Language Generation
  204. LEANCODE: Understanding Models Better for Code Simplification of Pre-trained Large Language Models
  205. Kaleidoscope Gallery: Exploring Ethics and Generative AI Through Art
  206. Bridge2AI: Building A Cross-disciplinary Curriculum Towards AI-Enhanced Biomedical and Clinical Care
  207. LLINBO: Trustworthy LLM-in-the-Loop Bayesian Optimization
  208. Model-Independent Machine Learning Approach for Nanometric Axial Localization and Tracking
  209. TransMedSeg: A Transferable Semantic Framework for Semi-Supervised Medical Image Segmentation
  210. LLMSynthor: Macro-Aligned Micro-Records Synthesis with Large Language Models
  211. Cooperative Causal GraphSAGE
  212. LOD1 3D City Model from LiDAR: The Impact of Segmentation Accuracy on Quality of Urban 3D Modeling and Morphology Extraction
  213. Explainable Prediction of the Mechanical Properties of Composites with CNNs
  214. Beyond Either-Or Reasoning: Transduction and Induction as Cooperative Problem-Solving Paradigms
  215. Quaff: Quantized Parameter-Efficient Fine-Tuning under Outlier Spatial Stability Hypothesis
  216. Leveraging Multivariate Long-Term History Representation for Time Series Forecasting
  217. Effective climate policies for major emission reductions of ozone precursors: Global evidence from two decades
  218. Predicting Neoadjuvant Chemotherapy Response in Triple-Negative Breast Cancer Using Pre-Treatment Histopathologic Images
  219. MedBLIP: Fine-tuning BLIP for Medical Image Captioning
  220. Language Models use Lookbacks to Track Beliefs
  221. Emerging Properties in Unified Multimodal Pretraining
  222. UltraEdit: Training-, Subject-, and Memory-Free Lifelong Editing in Language Models
  223. UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens
  224. Quantum Optimization via Gradient-Based Hamiltonian Descent
  225. Quartet: Native FP4 Training Can Be Optimal for Large Language Models
  226. AKRMap: Adaptive Kernel Regression for Trustworthy Visualization of Cross-Modal Embeddings
  227. Abacus: A Cost-Based Optimizer for Semantic Operator Systems
  228. EmoGist: Efficient In-Context Learning for Visual Emotion Understanding
  229. Explainable AI for Securing Healthcare in IoT-Integrated 6G Wireless Networks
  230. Cost-Awareness in Tree-Search LLM Planning: A Systematic Study
  231. Sequential QCQP for Bilevel Optimization with Line Search
  232. CAD-Coder: An Open-Source Vision-Language Model for Computer-Aided Design Code Generation
  233. Early Diagnosis of Atrial Fibrillation Recurrence: A Large Tabular Model Approach with Structured and Unstructured Clinical Data
  234. Dual Precision Quantization for Efficient and Accurate Deep Neural Networks Inference
  235. Bridging Predictive Coding and MDL: A Two-Part Code Framework for Deep Learning
  236. A General Framework for Group Sparsity in Hyperspectral Unmixing Using Endmember Bundles
  237. Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas
  238. KERL: Knowledge-Enhanced Personalized Recipe Recommendation using Large Language Models
  239. 3D Reconstruction from Sketches
  240. Enhancing Learned Knowledge in LoRA Adapters Through Efficient Contrastive Decoding on Ascend NPUs
  241. Virtual Cells: Predict, Explain, Discover
  242. MMD-Newton Method for Multi-objective Optimization
  243. Attacks on Machine-Text Detectors Retain Stylistic Fingerprints
  244. Electrostatics from Laplacian Eigenbasis for Neural Network Interatomic Potentials
  245. Towards a Foundation Model for Communication Systems
  246. Toward Reliable Scientific Hypothesis Generation: Evaluating Truthfulness and Hallucination in Large Language Models
  247. Success is in the Details: Evaluate and Enhance Details Sensitivity of Code LLMs through Counterfactuals
  248. CSTS: A Benchmark for the Discovery of Correlation Structures in Time Series Clustering
  249. Physics-informed Reduced Order Modeling of Time-dependent PDEs via Differentiable Solvers
  250. Adaptive Pruning of Deep Neural Networks for Resource-Aware Embedded Intrusion Detection on the Edge
  251. MCIP: Protecting MCP Safety via Model Contextual Integrity Protocol
  252. High-Dimensional Analysis of Bootstrap Ensemble Classifiers
  253. Instance Segmentation for Point Sets
  254. Performance Optimization of Energy-Harvesting Underlay Cognitive Radio Networks Using Reinforcement Learning
  255. Inference with correlated priors using sisters cells
  256. TRATES: Trait-Specific Rubric-Assisted Cross-Prompt Essay Scoring
  257. Automated Fetal Biometry Assessment with Deep Ensembles using Sparse-Sampling of 2D Intrapartum Ultrasound Images
  258. Agent Context Protocols Enhance Collective Inference
  259. SSPS: Self-Supervised Positive Sampling for Robust Self-Supervised Speaker Verification
  260. Neural Inverse Scattering with Score-based Regularization
  261. Dynadiff: Single-stage Decoding of Images from Continuously Evolving fMRI
  262. Physics-Guided Learning of Meteorological Dynamics for Weather Downscaling and Forecasting
  263. Pivot Language for Low-Resource Machine Translation
  264. Game of Trust: How Trustworthy Does Your Blockchain Think You Are?
  265. Can Large Language Models Really Recognize Your Name?
  266. Smart Traffic Signals: Comparing MARL and Fixed-Time Strategies
  267. Time to Embed: Unlocking Foundation Models for Time Series with Channel Descriptions
  268. Neural Video Compression with Context Modulation
  269. A Logic of General Attention Using Edge-Conditioned Event Models (Extended Version)
  270. Personalize Your Gaussian: Consistent 3D Scene Personalization from a Single Image
  271. Spiking Neural Networks with Temporal Attention-Guided Adaptive Fusion for imbalanced Multi-modal Learning
  272. A simple estimator of the correlation kernel matrix of a determinantal point process
  273. diffDemorph: Extending Reference-Free Demorphing to Unseen Faces
  274. Exploring Graph Representations of Logical Forms for Language Modeling
  275. Interpretable Dual-Stream Learning for Local Wind Hazard Prediction in Vulnerable Communities
  276. Teaching Audio-Aware Large Language Models What Does Not Hear: Mitigating Hallucinations through Synthesized Negative Samples
  277. Steering Deep Non-Linear Spatially Selective Filters for Weakly Guided Extraction of Moving Speakers in Dynamic Scenarios
  278. Just One Layer Norm Guarantees Stable Extrapolation
  279. ReservoirTTA: Prolonged Test-time Adaptation for Evolving and Recurring Domains
  280. BACON: A fully explainable AI model with graded logic for decision making problems
  281. Federated prediction for scalable and privacy-preserved knowledge-based planning in radiotherapy
  282. ModRWKV: Transformer Multimodality in Linear Time
  283. Enhanced Multimodal Aspect-Based Sentiment Analysis by LLM-Generated Rationales
  284. Personalised Insulin Adjustment with Reinforcement Learning: An In-Silico Validation for People with Diabetes on Intensive Insulin Treatment
  285. Enhancing Interpretability of Sparse Latent Representations with Class Information
  286. Adapting Pretrained Language Models for Citation Classification via Self-Supervised Contrastive Learning
  287. PAST: Phonetic-Acoustic Speech Tokenizer
  288. ServerlessLoRA: Enabling Low-Latency Serverless Multi-LoRA Serving
  289. Void in Language Models
  290. Adverseness vs. Equilibrium: Exploring Graph Adversarial Resilience through Dynamic Equilibrium
  291. How Managers Perceive AI-Assisted Conversational Training for Workplace Communication
  292. RefiDiff: Progressive Refinement Diffusion for Efficient Missing Data Imputation
  293. Mitigating Subgroup Disparities in Multi-Label Speech Emotion Recognition: A Pseudo-Labeling and Unsupervised Learning Approach
  294. S2SBench: A Benchmark for Quantifying Intelligence Degradation in Speech-to-Speech Large Language Models
  295. Neural Incompatibility: The Unbridgeable Gap of Cross-Scale Parametric Knowledge Transfer in Large Language Models
  296. Choosing a Model, Shaping a Future: Comparing LLM Perspectives on Sustainability and its Relationship with AI
  297. Interpretable Neural System Dynamics: Combining Deep Learning with System Dynamics Modeling to Support Critical Applications
  298. Explaining Neural Networks with Reasons
  299. A system identification approach to clustering vector autoregressive time series
  300. Towards Non-Euclidean Foundation Models: Advancing AI Beyond Euclidean Frameworks
  301. Table Foundation Models: on knowledge pre-training for tabular learning
  302. Diving into the Fusion of Monocular Priors for Generalized Stereo Matching
  303. Byte Pair Encoding for Efficient Time Series Forecasting
  304. Pairwise Evaluation of Accent Similarity in Speech Synthesis
  305. Explaining Unreliable Perception in Automated Driving: A Fuzzy-based Monitoring Approach
  306. Pierce the Mists, Greet the Sky: Decipher Knowledge Overshadowing via Knowledge Circuit Analysis
  307. OmniGenBench: A Modular Platform for Reproducible Genomic Foundation Models Benchmarking
  308. MUG-Eval: A Proxy Evaluation Framework for Multilingual Generation Capabilities in Any Language
  309. Knowledge Graph Based Repository-Level Code Generation
  310. Editing Across Languages: A Survey of Multilingual Knowledge Editing
  311. Algorithmic Hiring and Diversity: Reducing Human-Algorithm Similarity for Better Outcomes
  312. When Bias Backfires: The Modulatory Role of Counterfactual Explanations on the Adoption of Algorithmic Bias in XAI-Supported Human Decision-Making
  313. Graph-Guided Passage Retrieval for Author-Centric Structured Feedback
  314. Layer-wise Quantization for Quantized Optimistic Dual Averaging
  315. Dual Decomposition of Weights and Singular Value Low Rank Adaptation
  316. Dual Data Alignment Makes AI-Generated Image Detector Easier Generalizable
  317. PersonaTAB: Predicting Personality Traits using Textual, Acoustic, and Behavioral Cues in Fully-Duplex Speech Dialogs
  318. FMSD-TTS: Few-shot Multi-Speaker Multi-Dialect Text-to-Speech Synthesis for "U-Tsang, Amdo and Kham Speech Dataset Generation
  319. OSoRA: Output-Dimension and Singular-Value Initialized Low-Rank Adaptation
  320. Upgrading Democracies with Fairer Voting Methods
  321. QA-prompting: Improving Summarization with Large Language Models using Question-Answering
  322. Egocentric Action-aware Inertial Localization in Point Clouds with Vision-Language Guidance
  323. Enhancing Classification with Semi-Supervised Deep Learning Using Distance-Based Sample Weights
  324. Mixing times of data-augmentation Gibbs samplers for high-dimensional probit regression
  325. Replace in Translation: Boost Concept Alignment in Counterfactual Text-to-Image
  326. Better Neural Network Expressivity: Subdividing the Simplex
  327. Domain Adaptation for Multi-label Image Classification: a Discriminator-free Approach
  328. Handloom Design Generation Using Generative Networks
  329. Securing Transfer-Learned Networks with Reverse Homomorphic Encryption
  330. Accuracy and Fairness of Facial Recognition Technology in Low-Quality Police Images: An Experiment With Synthetic Faces
  331. RETRO: REthinking Tactile Representation Learning with Material PriOrs
  332. RADAR: Enhancing Radiology Report Generation with Supplementary Knowledge Injection
  333. Low-Cost FlashAttention with Fused Exponential and Multiplication Hardware Operators
  334. MultiTab: A Comprehensive Benchmark Suite for Multi-Dimensional Evaluation in Tabular Domains
  335. HausaNLP: Current Status, Challenges and Future Directions for Hausa Natural Language Processing
  336. Taming Recommendation Bias with Causal Intervention on Evolving Personal Popularity
  337. JOLT-SQL: Joint Loss Tuning of Text-to-SQL with Confusion-aware Noisy Schema Sampling
  338. Optimizing Binary and Ternary Neural Network Inference on RRAM Crossbars using CIM-Explorer
  339. Scaling Law for Quantization-Aware Training
  340. Beyond Black-Box Obfuscation: Mechanistic Analysis and Defense of White-Box Monitors
  341. A Review of Vision-Based Assistive Systems for Visually Impaired People: Technologies, Applications, and Future Directions
  342. Cross-Lingual Optimization for Language Transfer in Large Language Models
  343. Towards Generating Realistic Underwater Images
  344. Benchmarking data encoding methods in Quantum Machine Learning
  345. Universal Acoustic Adversarial Attacks for Flexible Control of Speech-LLMs
  346. AquaSignal: An Integrated Framework for Robust Underwater Acoustic Analysis
  347. The Post Double LASSO for Efficiency Analysis
  348. YESciEval: Robust LLM-as-a-Judge for Scientific Question Answering
  349. X-KAN: Optimizing Local Kolmogorov-Arnold Networks via Evolutionary Rule-Based Machine Learning
  350. Data-Efficient Hate Speech Detection via Cross-Lingual Nearest Neighbor Retrieval with Limited Labeled Data
  351. FAID: Fine-Grained AI-Generated Text Detection Using Multi-Task Auxiliary and Multi-Level Contrastive Learning
  352. RA-Touch: Retrieval-Augmented Touch Understanding with Enriched Visual Data
  353. FuxiMT: Sparsifying Large Language Models for Chinese-Centric Multilingual Machine Translation
  354. Hybrid Adaptive Modeling in Process Monitoring: Leveraging Sequence Encoders and Physics-Informed Neural Networks
  355. A Private Approximation of the 2nd-Moment Matrix of Any Subsamplable Input
  356. Path-integral molecular dynamics with actively-trained and universal machine learning force fields
  357. TransBench: Benchmarking Machine Translation for Industrial-Scale Applications
  358. Technical Report on classification of literature related to children speech disorder
  359. Learning with Local Search MCMC Layers
  360. Decoupling Classifier for Boosting Few-shot Object Detection and Instance Segmentation
  361. ABBA-Adapters: Efficient and Expressive Fine-Tuning of Foundation Models
  362. Toward Embodied AGI: A Review of Embodied AI and the Road Ahead
  363. Fast, close, non-singular and property-preserving approximations of entropic measures
  364. Mechanistic Fine-tuning for In-context Learning
  365. VoQA: Visual-only Question Answering
  366. Phonetic Perturbations Reveal Tokenizer-Rooted Safety Gaps in LLMs
  367. Flexible-weighted Chamfer Distance: Enhanced Objective Function for Point Cloud Completion
  368. Federated learning in low-resource settings: A chest imaging study in Africa -- Challenges and lessons learned
  369. Regularized least squares learning with heavy-tailed noise is minimax optimal
  370. Automatic Dataset Generation for Knowledge Intensive Question Answering Tasks
  371. A PID-Controlled Tensor Wheel Decomposition Model for Dynamic Link Prediction
  372. Challenges and Limitations of Generative AI in Synthesizing Wearable Sensor Data
  373. Beginning with You: Perceptual-Initialization Improves Vision-Language Representation and Alignment
  374. MSDformer: Multi-scale Discrete Transformer For Time Series Generation
  375. FLASH-D: FlashAttention with Hidden Softmax Division
  376. Unraveling Interwoven Roles of Large Language Models in Authorship Privacy: Obfuscation, Mimicking, and Verification
  377. Dynamic Replanning for Improved Public Transport Routing
  378. QSVM-QNN: Quantum Support Vector Machine Based Quantum Neural Network Learning Algorithm for Brain-Computer Interfacing Systems
  379. α-GAN by R'enyi Cross Entropy
  380. SlangDIT: Benchmarking LLMs in Interpretative Slang Translation
  381. Bridge the Gap between Past and Future: Siamese Model Optimization for Context-Aware Document Ranking
  382. Enhancing Abstractive Summarization of Scientific Papers Using Structure Information
  383. From stability of Langevin diffusion to convergence of proximal MCMC for non-log-concave sampling
  384. The Strawberry Problem: Emergence of Character-level Understanding in Tokenized Language Models
  385. Nonparametric Teaching for Graph Property Learners
  386. PL-FGSA: A Prompt Learning Framework for Fine-Grained Sentiment Analysis Based on MindSpore
  387. Hybrid Bernstein Normalizing Flows for Flexible Multivariate Density Regression with Interpretable Marginals
  388. Personalized Bayesian Federated Learning with Wasserstein Barycenter Aggregation
  389. M3Depth: Wavelet-Enhanced Depth Estimation on Mars via Mutual Boosting of Dual-Modal Data
  390. Temporal Alignment of Time Sensitive Facts with Activation Engineering
  391. Prior Prompt Engineering for Reinforcement Fine-Tuning
  392. Unify Graph Learning with Text: Unleashing LLM Potentials for Session Search
  393. Enhancing Keyphrase Extraction from Academic Articles Using Section Structure Information
  394. Memory Assignment for Finite-Memory Strategies in Adversarial Patrolling Games
  395. Hunyuan-Game: Industrial-grade Intelligent Game Creation Model
  396. Texts or Images? A Fine-grained Analysis on the Effectiveness of Input Representations and Models for Table Question Answering
  397. Probing BERT for German Compound Semantics
  398. A Methodological Framework for Measuring Spatial Labeling Similarity
  399. Contrastive Consolidation of Top-Down Modulations Achieves Sparsely Supervised Continual Learning
  400. Assessing wildfire susceptibility in Iran: Leveraging machine learning for geospatial analysis of climatic and anthropogenic factors
  401. Collaborative Unlabeled Data Optimization
  402. CONSIGN: Conformal Segmentation Informed by Spatial Groupings via Decomposition
  403. A Personalized Conversational Benchmark: Towards Simulating Personalized Conversations
  404. Mitigating Pretraining-Induced Attention Asymmetry in 2D+ Electron Microscopy Image Segmentation
  405. Legal Rule Induction: Towards Generalizable Principle Discovery from Analogous Judicial Precedents
  406. High-dimensional Nonparametric Contextual Bandit Problem
  407. MultiHal: Multilingual Dataset for Knowledge-Graph Grounded Evaluation of LLM Hallucinations
  408. Unlocking the Power of SAM 2 for Few-Shot Segmentation
  409. Beyond Chains: Bridging Large Language Models and Knowledge Bases in Complex Question Answering
  410. Large-Scale Multi-Character Interaction Synthesis
  411. Computational Efficiency under Covariate Shift in Kernel Ridge Regression
  412. Personalized and Resilient Distributed Learning Through Opinion Dynamics
  413. Gender Trouble in Language Models: An Empirical Audit Guided by Gender Performativity Theory
  414. Personalized Student Knowledge Modeling for Future Learning Resource Prediction
  415. Enhancing LLMs via High-Knowledge Data Selection
  416. Place Recognition Meet Multiple Modalitie: A Comprehensive Review, Current Challenges and Future Directions
  417. Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting
  418. Field Matters: A Lightweight LLM-enhanced Method for CTR Prediction
  419. Learning Concept-Driven Logical Rules for Interpretable and Generalizable Medical Image Classification
  420. From Unaligned to Aligned: Scaling Multilingual LLMs with Multi-Way Parallel Corpora
  421. Generalized Category Discovery via Token Manifold Capacity Learning
  422. Adversarially Pretrained Transformers May Be Universally Robust In-Context Learners
  423. Unsupervised Graph Clustering with Deep Structural Entropy
  424. Learning High-dimensional Ionic Model Dynamics Using Fourier Neural Operators
  425. Partition-wise Graph Filtering: A Unified Perspective Through the Lens of Graph Coarsening
  426. AppleGrowthVision: A large-scale stereo dataset for phenological analysis, fruit detection, and 3D reconstruction in apple orchards
  427. OmniStyle: Filtering High Quality Style Transfer Data at Scale
  428. CSAGC-IDS: A Dual-Module Deep Learning Network Intrusion Detection Model for Complex and Imbalanced Data
  429. FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix
  430. Towards Efficient Multi-Scale Deformable Attention on NPU
  431. Adversarial Training from Mean Field Perspective
  432. Disentangled Multi-span Evolutionary Network against Temporal Knowledge Graph Reasoning
  433. End-to-end Cortical Surface Reconstruction from Clinical Magnetic Resonance Images
  434. ThermoONet -- a deep learning-based small body thermophysical network: applications to modelling water activity of comets
  435. AUTOLAW: Enhancing Legal Compliance in Large Language Models via Case Law Generation and Jury-Inspired Deliberation
  436. EGFormer: Towards Efficient and Generalizable Multimodal Semantic Segmentation
  437. Adaptive Sentencing Prediction with Guaranteed Accuracy and Legal Interpretability
  438. UHD Image Dehazing via anDehazeFormer with Atmospheric-aware KV Cache
  439. Multi-Label Stereo Matching for Transparent Scene Depth Estimation
  440. Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks
  441. VeRecycle: Reclaiming Guarantees from Probabilistic Certificates for Stochastic Dynamical Systems after Change
  442. ELEPHANT: Measuring and understanding social sycophancy in LLMs
  443. DecIF: Improving Instruction-Following through Meta-Decomposition
  444. When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty
  445. Mixed Signals: Understanding Model Disagreement in Multimodal Empathy Detection
  446. Truth or Twist? Optimal Model Selection for Reliable Label Flipping Evaluation in LLM-based Counterfactuals
  447. The Multimodal Information Based Speech Processing (MISP) 2025 Challenge: Audio-Visual Diarization and Recognition
  448. Hypothesis on the Functional Advantages of the Selection-Broadcast Cycle Structure: Global Workspace Theory and Dealing with a Real-Time World
  449. Through a Compressed Lens: Investigating The Impact of Quantization on Factual Knowledge Recall
  450. VAMO: Efficient Zeroth-Order Variance Reduction for SGD with Faster Convergence
  451. Memory-Centric Embodied Question Answering
  452. WAVE++: Capturing Within-Task Variance for Continual Relation Extraction with Adaptive Prompting
  453. From Press to Pixels: Evolving Urdu Text Recognition
  454. CLEVER: A Curated Benchmark for Formally Verified Code Generation
  455. EEG-to-Text Translation: A Model for Deciphering Human Brain Activity
  456. LoVR: A Benchmark for Long Video Retrieval in Multimodal Contexts
  457. An Explorative Analysis of SVM Classifier and ResNet50 Architecture on African Food Classification
  458. Blind Restoration of High-Resolution Ultrasound Video
  459. Parallel Belief Revision via Order Aggregation
  460. Word length predicts word order: "Min-max"-ing drives language evolution
  461. Bronchovascular Tree-Guided Weakly Supervised Learning Method for Pulmonary Segment Segmentation
  462. ShortcutProbe: Probing Prediction Shortcuts for Learning Robust Models
  463. Cross-Linguistic Transfer in Multilingual NLP: The Role of Language Families and Morphology
  464. Cross-Domain Diffusion with Progressive Alignment for Efficient Adaptive Retrieval
  465. XDementNET: An Explainable Attention Based Deep Convolutional Network to Detect Alzheimer Progression from MRI data
  466. 4D-ROLLS: 4D Radar Occupancy Learning via LiDAR Supervision
  467. Learning to Insert for Constructive Neural Vehicle Routing Solver
  468. An Asymptotic Equation Linking WAIC and WBIC in Singular Models
  469. New Evidence of the Two-Phase Learning Dynamics of Neural Networks
  470. Causes and Consequences of Representational Similarity in Machine Learning Models
  471. Do Language Models Use Their Depth Efficiently?
  472. CRAFT: Time Series Forecasting with Cross-Future Behavior Awareness
  473. InfiGFusion: Graph-on-Logits Distillation via Efficient Gromov-Wasserstein for Model Fusion
  474. Certifiably Safe Manipulation of Deformable Linear Objects via Joint Shape and Tension Prediction
  475. Mobile-Agent-V: A Video-Guided Approach for Effortless and Efficient Operational Knowledge Injection in Mobile Automation
  476. TranSUN: A Preemptive Paradigm to Eradicate Retransformation Bias Intrinsically from Regression Models in Recommender Systems
  477. Automated Quality Evaluation of Cervical Cytopathology Whole Slide Images Based on Content Analysis
  478. Utilizing Strategic Pre-training to Reduce Overfitting: Baguan -- A Pre-trained Weather Forecasting Model
  479. Graphon Mixtures
  480. Enforcing Hard Linear Constraints in Deep Learning Models with Decision Rules
  481. Learning Spatio-Temporal Dynamics for Trajectory Recovery via Time-Aware Transformer
  482. SuperMapNet for Long-Range and High-Accuracy Vectorized HD Map Construction
  483. Domain Gating Ensemble Networks for AI-Generated Text Detection
  484. Rethink the Role of Deep Learning towards Large-scale Quantum Systems
  485. A Challenge to Build Neuro-Symbolic Video Agents
  486. Forensic deepfake audio detection using segmental speech features
  487. Improve Language Model and Brain Alignment via Associative Memory
  488. Exploring Image Quality Assessment from a New Perspective: Pupil Size
  489. MGStream: Motion-aware 3D Gaussian for Streamable Dynamic Scene Reconstruction
  490. Enhancing Robot Navigation Policies with Task-Specific Uncertainty Managements
  491. TelePlanNet: An AI-Driven Framework for Efficient Telecom Network Planning
  492. Multimodal RAG-driven Anomaly Detection and Classification in Laser Powder Bed Fusion using Large Language Models
  493. Articulatory Feature Prediction from Surface EMG during Speech Production
  494. FlashKAT: Understanding and Addressing Performance Bottlenecks in the Kolmogorov-Arnold Transformer
  495. Physics-Driven Local-Whole Elastic Deformation Modeling for Point Cloud Representation Learning
  496. Semiparametric Off-Policy Inference for Optimal Policy Values under Possible Non-Uniqueness
  497. RAG/LLM Augmented Switching Driven Polymorphic Metaheuristic Framework
  498. ClapFM-EVC: High-Fidelity and Flexible Emotional Voice Conversion with Dual Control from Natural Language and Speech
  499. LLM-based Evaluation Policy Extraction for Ecological Modeling
  500. Ground-V: Teaching VLMs to Ground Complex Instructions in Pixels
  501. Transfer Learning from Visual Speech Recognition to Mouthing Recognition in German Sign Language