Papers

New on arXiv

Tue 24 Jun 2025

350 papers

Causal-Paced Deep Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
Fine-grained Token Allocation Via Operation Pruning for Efficient MLLMsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
Enhancing Sports Strategy with Video Analytics and Data Mining: Assessing the effectiveness of Multimodal LLMs in tennis video analysisMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Controllable diffusion-based generation for multi-channel biological dataDiffusion models → Medical imaging and segmentation
Hallucination Detection with Small Language ModelsRetrieval-augmented generation → Hallucination detection in RAG
FrankenBot: Brain-Morphic Modular Orchestration for Robotic Manipulation with Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
ToSA: Token Merging with Spatial AwarenessEfficient LLM inference and serving → Token pruning and merging for ViTs
Beyond Autocomplete: Designing CopilotLens Towards Transparent and Explainable AI Coding AgentsLLM agents and tool use → Software engineering coding agents
Controlled Retrieval-augmented Context Evaluation for Long-form RAGRetrieval-augmented generation → RAG pipeline design and evaluation
A Principled Path to Fitted Distributional EvaluationDeep reinforcement learning methods → RL theory and sample complexity
GNN's Uncertainty Quantification using Self-DistillationKnowledge distillation → Graph neural network distillation
Cross-Layer Discrete Concept Discovery for Interpreting Language ModelsMechanistic interpretability → SAE features and their applications
Verifiable Unlearning on EdgeLLM safety and security → Machine unlearning
Hierarchical Reinforcement Learning and Value Optimization for Challenging Quadruped LocomotionDeep reinforcement learning methods → RL for robot locomotion and manipulation
Elucidated Rolling Diffusion Models for Probabilistic Forecasting of Complex DynamicsDiffusion models → Flow matching, time series and science
Persona-Assigned Large Language Models Exhibit Human-Like Motivated ReasoningLLM reasoning → Reasoning benchmarks and evaluation
Accurate and Energy Efficient: Local Retrieval-Augmented Generation Models Outperform Commercial Large Language Models in Medical TasksRetrieval-augmented generation → Medical and biomedical RAG
Doc2Agent: Scalable Generation of Tool-Using Agents from API DocumentationLLM agents and tool use → Software engineering coding agents
TRACED: Transition-aware Regret Approximation with Co-learnability for Environment DesignDeep reinforcement learning methods → Deep RL algorithms and representations
Context Attribution with Multi-Armed Bandit OptimizationRetrieval-augmented generation → RAG robustness and adaptive retrieval
Inference Scaled GraphRAG: Improving Multi Hop Question Answering on Knowledge GraphsLLM reasoning → Knowledge- and tool-augmented reasoning
CycleDistill: Bootstrapping Machine Translation using LLMs with Cyclical DistillationSynthetic data and self-improvement for LLMs → LLM synthetic data generation
Any-Order GPT as Masked Diffusion Model: Decoupling Formulation and ArchitectureDiffusion models → Discrete and text diffusion
A Comparative Analysis of Reinforcement Learning and Conventional Deep Learning Approaches for Bearing Fault DiagnosisDeep reinforcement learning methods → Deep RL algorithms and representations
Prover Agent: An Agent-Based Framework for Formal Mathematical ProofsLLM agents and tool use → Educational agents and math problem solving
Distillation-Enabled Knowledge Alignment for Generative Semantic Communications of AIGC ImagesKnowledge distillation → General knowledge distillation methods
Orthogonal Soft Pruning for Efficient Class UnlearningLLM safety and security → Federated unlearning and poisoning
Causal-Aware Intelligent QoE Optimization for VR Interaction with Adaptive Keyframe ExtractionDeep reinforcement learning methods → Deep RL algorithms and representations
Radial Attention: O(nlog n) Sparse Attention with Energy Decay for Long Video GenerationDiffusion models → Video generation
AnimaX: Animating the Inanimate in 3D with Joint Video-Pose Diffusion ModelsDiffusion models → Video generation
Unified Vision-Language-Action ModelVision-language-action models → Generalist VLA models and benchmarks
HiMA-Ecom: Enabling Joint Training of Hierarchical Multi-Agent E-commerce AssistantsLLM agents and tool use → Reinforcement learning for LLM agents
Temporal-IRL: Modeling Port Congestion and Berth Scheduling with Inverse Reinforcement LearningDeep reinforcement learning methods → RL for robot navigation and UAV control
ManiGaussian++: General Robotic Bimanual Manipulation with Hierarchical Gaussian World ModelWorld models → Embodied and robot world models
GenHSI: Controllable Generation of Human-Scene Interaction VideosDiffusion models → Video generation
Improving Progressive Generation with Decomposable Flow MatchingDiffusion models → Flow matching, time series and science
SimpleGVR: A Simple Baseline for Latent-Cascaded Video Super-ResolutionDiffusion models → Inverse problems and image restoration
MAM: Modular Multi-Agent Framework for Multi-Modal Medical Diagnosis via Role-Specialized CollaborationLLM reasoning → Clinical and biomedical applications +1
Scaling Speculative Decoding with Lookahead ReasoningLLM reasoning → Test-time compute and efficient thinking +1
Evaluating Compliance with Visualization Guidelines in Diagrams for Scientific Publications Using Large Vision Language ModelsMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
CronusVLA: Towards Efficient and Robust Manipulation via Multi-Frame Vision-Language-Action ModelingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
KnowRL: Exploring Knowledgeable Reinforcement Learning for FactualityLLM reasoning → Hallucination detection and mitigation +1
Learning Task Belief Similarity with Latent Dynamics for Meta-Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
Listwise Direct Preference Optimization with Multi-Dimensional Preference MixingLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Kling-Foley: Multimodal Diffusion Transformer for High-Quality Video-to-Audio GenerationDiffusion models → Audio, speech and music
SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for ReasoningLLM reasoning → Reinforcement learning for reasoning
Noise Consistency Training: A Native Approach for One-Step Generator in Learning Additional ControlsDiffusion models → Diffusion foundations and sampling
Breaking Barriers: Do Reinforcement Post Training Gains Transfer To Unseen Domains?LLM reasoning → Reinforcement learning for reasoning
From Reproduction to Replication: Evaluating Research Agents with Progressive Code MaskingLLM agents and tool use → Web, search, and research agents
Guidance in the Frequency Domain Enables High-Fidelity Sampling at Low CFG ScalesDiffusion models → Diffusion foundations and sampling
Uncovering Conceptual Blindspots in Generative Image Models Using Sparse AutoencodersMechanistic interpretability → Interpreting vision and multimodal models
Learning-aided Bigraph Matching Approach to Multi-Crew Restoration of Damaged Power Networks Coupled with Road Transportation NetworksDeep reinforcement learning methods → RL for energy, networks and operations
From Memories to Maps: Mechanisms of In-Context Reinforcement Learning in TransformersDeep reinforcement learning methods → Deep RL algorithms and representations
A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense CountermeasuresLLM agents and tool use → Agent threats, guardrails and governance
PEVLM: Parallel Encoding for Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
Unsupervised Data Generation for Offline Reinforcement Learning: A Perspective from ModelOffline RL and imitation learning from data → Offline RL algorithms
ChordPrompt: Orchestrating Cross-Modal Prompt Synergy for Multi-Domain Incremental Learning in CLIPMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
ECCoT: A Framework for Enhancing Effective Cognition via Chain of Thought in Large Language ModelLLM reasoning → Prompting and chain-of-thought reasoning
Adaptive Domain Modeling with Language Models: A Multi-Agent Approach to Task PlanningLLM agents and tool use → General LLM agent frameworks and benchmarks
Fake or Real, Can Robots Tell? Evaluating VLM Robustness to Domain Shift in Single-View Robotic Scene UnderstandingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
MambaOutRS: A Hybrid CNN-Fourier Architecture for Remote Sensing Image ClassificationState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
NTRL: Encounter Generation via Reinforcement Learning for Dynamic Difficulty Adjustment in Dungeons and DragonsDeep reinforcement learning methods → RL for games and combinatorial optimization
Visual hallucination detection in large vision-language models via evidential conflictMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
heiDS at ArchEHR-QA 2025: From Fixed-k to Query-dependent-k for Retrieval Augmented GenerationRetrieval-augmented generation → Medical and biomedical RAG
AnTKV: Anchor Token-Aware Sub-Bit Vector Quantization for KV Cache in Large Language ModelsEfficient LLM inference and serving → KV cache quantization
MATE: LLM-Powered Multi-Agent Translation Environment for Accessibility ApplicationsLLM agents and tool use → GUI and mobile agents
T-Rex: Task-Adaptive Spatial Representation Extraction for Robotic Manipulation with Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and RefinementLLM safety and security → Machine unlearning
Is Long-to-Short a Free Lunch? Investigating Inconsistency and Reasoning Efficiency in LRMsLLM reasoning → Test-time compute and efficient thinking
Recalling The Forgotten Class Memberships: Unlearned Models Can Be Noisy Labelers to Leak PrivacyLLM safety and security → Machine unlearning +1
LLM-based Multi-Agent System for Intelligent Refactoring of Haskell CodeLLM agents and tool use → Software engineering coding agents
ADDQ: Adaptive Distributional Double Q-LearningDeep reinforcement learning methods → RL theory and sample complexity
Surgery-R1: Advancing Surgical-VQLA with Reasoning Multimodal Large Language Model via Reinforcement LearningLLM reasoning → Clinical and biomedical applications +1
Can Reasoning Help Large Language Models Capture Human Annotator Disagreement?LLM reasoning → Reasoning benchmarks and evaluation
KunLunBaizeRAG: Reinforcement Learning Driven Inference Performance Leap for Large Language ModelsLLM reasoning → Knowledge- and tool-augmented reasoning
Angio-Diff: Learning a Self-Supervised Adversarial Diffusion Model for Angiographic Geometry GenerationDiffusion models → Medical imaging and segmentation
AMF-MedIT: An Efficient Align-Modulation-Fusion Framework for Medical Image-Tabular DataState-space sequence models (S4, Mamba) → Mamba for medical image analysis
Learning to Disentangle Latent Reasoning Rules with Language VAEs: A Systematic StudyLLM reasoning → Test-time compute and efficient thinking
Generate the Forest before the Trees -- A Hierarchical Diffusion model for Climate DownscalingDiffusion models → Flow matching, time series and science
Emergence of Text Readability in Vision Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
CID-GraphRAG: Enhancing Multi-Turn Dialogue Systems through Dual-Pathway Retrieval of Conversation Flow and Context SemanticsRetrieval-augmented generation → Conversational and speech RAG
Measuring and Guiding MonosemanticityMechanistic interpretability → SAE features and their applications
Path Learning with Trajectory Advantage RegressionDeep reinforcement learning methods → Deep RL algorithms and representations
Computing Tree Structures in Anonymous Graphs via Mobile AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
Partially Observable Residual Reinforcement Learning for PV-Inverter-Based Voltage Control in Distribution GridsDeep reinforcement learning methods → RL for energy, networks and operations
Continual Retinal Vision-Language Pre-training upon Incremental Imaging ModalitiesMultimodal LLMs / vision-language models → Medical vision-language models
JCAPT: A Joint Modeling Approach for CAPTState-space sequence models (S4, Mamba) → Speech and audio SSMs
Robotic Perception with a Large Tactile-Vision-Language Model for Physical Property InferenceMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Open-Vocabulary Camouflaged Object Segmentation with Cascaded Vision Language ModelsMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
Skywork-SWE: Unveiling Data Scaling Laws for Software Engineering in LLMsLLM agents and tool use → Software engineering coding agents
Da Yu: Towards USV-Based Image Captioning for Waterway Surveillance and Scene UnderstandingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Ontology Neural Network and ORTSF: A Framework for Topological Reasoning and Delay-Robust ControlLLM reasoning → Spatial and embodied reasoning
Continuous-variable Quantum Diffusion Model for State Generation and RestorationDiffusion models → Diffusion foundations and sampling
AnchorDP3: 3D Affordance Guided Sparse Diffusion Policy for Robotic ManipulationDiffusion models → Diffusion and flow policies for robotics
3D-SSM: A Novel 3D Selective Scan Module for Remote Sensing Change DetectionState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
What Matters in LLM-generated Data: Diversity and Its Effect on Model Fine-TuningSynthetic data and self-improvement for LLMs → LLM synthetic data generation
MSR-Align: Policy-Grounded Multimodal Alignment for Safety-Aware Reasoning in Vision-Language ModelsLLM reasoning → Reasoning for agents, planning and code +2
Robust Behavior Cloning Via Global Lipschitz RegularizationOffline RL and imitation learning from data → Imitation learning methods
Inference-Time Reward Hacking in Large Language ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1LLM reasoning → LLM reasoning for recommendation

All 350