Papers

New on arXiv

Mon 18 Aug 2025

332 papers

TalkPlayData 2: An Agentic Synthetic Data Pipeline for Multimodal Conversational Music RecommendationLLM agents and tool use → Multimodal and embodied agents +1
2COOOL: 2nd Workshop on the Challenge Of Out-Of-Label Hazards in Autonomous DrivingEnd-to-end autonomous driving → VLMs for autonomous driving
CountLoop: Training-Free High-Instance Image Generation via Iterative Agent GuidanceDiffusion models → Image generation, text-to-image and editing
A Functionality-Grounded Benchmark for Evaluating Web Agents in E-commerce DomainsLLM agents and tool use → Social simulation and multi-agent debate
Mini-Omni-Reasoner: Token-Level Thinking-in-Speaking in Large Speech ModelsLLM reasoning → Audio-language model reasoning
AI Agents for Photonic Integrated Circuit Design AutomationLLM agents and tool use → Software engineering coding agents
3D Cardiac Anatomy Generation Using Mesh Latent Diffusion ModelsDiffusion models → Medical imaging and segmentation
SimGenHOI: Physically Realistic Whole-Body Humanoid-Object Interaction via Generative Modeling and Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
From AI for Science to Agentic Science: A Survey on Autonomous Scientific DiscoveryLLM agents and tool use → Web, search, and research agents
Datarus-R1: An Adaptive Multi-Step Reasoning LLM for Automated Data AnalysisLLM reasoning → Test-time compute and efficient thinking
Stands to Reason: Investigating the Effect of Reasoning on Idiomaticity DetectionLLM reasoning → Reasoning benchmarks and evaluation
X-MoE: Enabling Scalable Training for Emerging Mixture-of-Experts Architectures on HPC PlatformsMixture-of-experts → Efficient MoE training and inference systems
Constraint-Aware Flow Matching via Randomized ExplorationDiffusion models → Flow matching, time series and science
Flow Matching for Efficient and Scalable Data AssimilationDiffusion models → Flow matching, time series and science
Prune2Drive: A Plug-and-Play Framework for Accelerating Vision-Language Models in Autonomous DrivingMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
GaitCrafter: Diffusion Model for Biometric Preserving Gait SynthesisDiffusion models → Video generation
CardAIc-Agents: A Multimodal Framework with Hierarchical Adaptation for Cardiac Care SupportLLM agents and tool use → Medical and scientific domain agents
Explicit v.s. Implicit Memory: Exploring Multi-hop Complex Reasoning Over Personalized InformationLLM reasoning → Knowledge- and tool-augmented reasoning +1
Involuntary Jailbreak: On Self-Prompting AttacksLLM safety and security → Jailbreaking
DianJin-OCR-R1: Enhancing OCR Capabilities via a Reasoning-and-Tool Interleaved Vision-Language ModelLLM reasoning → Multimodal reasoning +1
4DNeX: Feed-Forward 4D Generative Modeling Made EasyDiffusion models → 3D, point cloud and scene generation
Manipulate-to-Navigate: Reinforcement Learning with Visual Affordances and Manipulability PriorsDeep reinforcement learning methods → RL for robot locomotion and manipulation
MDPO: Overcoming the Training-Inference Divide of Masked Diffusion Language ModelsDiffusion models → Discrete and text diffusion
Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing TasksLLM agents and tool use → General LLM agent frameworks and benchmarks
Holistic Evaluation of Multimodal LLMs on Spatial IntelligenceMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
OptimalThinkingBench: Evaluating Over and Underthinking in LLMsLLM reasoning → Test-time compute and efficient thinking
Improving Detection of Watermarked Language ModelsLLM safety and security → Watermarking generated content and models
MuDRiC: Multi-Dialect Reasoning for Arabic Commonsense ValidationLLM reasoning → Reasoning benchmarks and evaluation
AutoBnB-RAG: Enhancing Multi-Agent Incident Response with Retrieval-Augmented GenerationRetrieval-augmented generation → Privacy and security of RAG +1
Contrastive Representations for Temporal ReasoningLLM reasoning → Multimodal reasoning
All for law and law for all: Adaptive RAG Pipeline for Legal ResearchRetrieval-augmented generation → Legal and financial RAG
Grounding Actions in Camera Space: Observation-Centric Vision-Language-Action PolicyVision-language-action models → 3D and spatial-aware VLA
Denoising diffusion models for inverse design of inflatable structures with programmable deformationsDiffusion models → Flow matching, time series and science
DMS:Diffusion-Based Multi-Baseline Stereo Generation for Improving Self-Supervised Depth EstimationDiffusion models → 3D, point cloud and scene generation
From Transthoracic to Transesophageal: Cross-Modality Generation using LoRA DiffusionDiffusion models → Medical imaging and segmentation
Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A SurveyVision-language-action models → Generalist VLA models and benchmarks
Reinforced Context Order Recovery for Adaptive Reasoning and PlanningLLM reasoning → Reinforcement learning for reasoning +1
Eyes on the Image: Gaze Supervised Multimodal Learning for Chest X-ray Diagnosis and Report GenerationMultimodal LLMs / vision-language models → Medical vision-language models
Odo: Depth-Guided Diffusion for Identity-Preserving Body ReshapingDiffusion models → 3D, point cloud and scene generation
MAJIC: Markovian Adaptive Jailbreaking via Iterative Composition of Diverse Innovative StrategiesLLM safety and security → Jailbreaking
Can Large Models Teach Student Models to Solve Mathematical Problems Like Human Beings? A Reasoning Distillation Method via Multi-LoRA InteractionLLM reasoning → Prompting and chain-of-thought reasoning +1
WebMall -- A Multi-Shop Benchmark for Evaluating Web AgentsLLM agents and tool use → Social simulation and multi-agent debate
G2RPO-A: Guided Group Relative Policy Optimization with Adaptive GuidanceLLM reasoning → Reinforcement learning for reasoning
Empirical Analysis of Decoding Biases in Masked Diffusion ModelsDiffusion models → Discrete and text diffusion
Matrix-game 2.0: An open-source real-time and streaming interactive world modelWorld models → Video-generation world models and simulators +1
EvolMathEval: Towards Evolvable Benchmarks for Mathematical Reasoning via Evolutionary TestingLLM reasoning → Mathematical reasoning
Analyzing Information Sharing and Coordination in Multi-Agent PlanningLLM agents and tool use → General LLM agent frameworks and benchmarks
Adaptive Reinforcement for Open-ended Medical Reasoning via Semantic-Guided Reward Collapse MitigationLLM reasoning → Clinical and biomedical applications +1
OPTIC-ER: A Reinforcement Learning Framework for Real-Time Emergency Response and Equitable Resource Allocation in Underserved African CommunitiesDeep reinforcement learning methods → RL for energy, networks and operations
Towards Open-Ended Emotional Support Conversations in LLMs via Reinforcement Learning with Future-Oriented RewardsLLM alignment / RLHF / preference optimisation → Medical LLM alignment
Do Large Language Model Agents Exhibit a Survival Instinct? An Empirical Study in a Sugarscape-Style SimulationLLM agents and tool use → General LLM agent frameworks and benchmarks
RoboRetriever: Single-Camera Robot Object Retrieval via Active and Interactive Perception with Dynamic Scene GraphLLM reasoning → Spatial and embodied reasoning
CTFlow: Video-Inspired Latent Flow Matching for 3D CT SynthesisDiffusion models → Medical imaging and segmentation
RAJ-PGA: Reasoning-Activated Jailbreak and Principle-Guided Alignment Framework for Large Reasoning ModelsLLM reasoning → Reasoning for agents, planning and code +1
Stochastic Self-Guidance for Training-Free Enhancement of Diffusion ModelsDiffusion models → Diffusion foundations and sampling
Preserve and Sculpt: Manifold-Aligned Fine-tuning of Vision-Language Models for Few-Shot LearningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
An LLM Agent-Based Complex Semantic Table Annotation ApproachLLM agents and tool use → Web, search, and research agents
Cross-Domain Few-Shot Learning via Multi-View Collaborative Optimization with Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Accelerating Edge Inference for Distributed MoE Models with Latency-Optimized Expert PlacementMixture-of-experts → Efficient MoE training and inference systems
Context Matters: Incorporating Target Awareness in Conversational Abusive Language DetectionLLM safety and security → Safety alignment, refusal and guardrails
Learning to Steer: Input-dependent Steering for Multimodal LLMsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
Maximum Score Routing For Mixture-of-ExpertsMixture-of-experts → Expert routing strategies
Atom-Searcher: Enhancing Agentic Deep Research via Fine-Grained Atomic Thought RewardLLM reasoning → Knowledge- and tool-augmented reasoning +2
Reinforcement Learning with Rubric AnchorsDeep reinforcement learning methods → RL training of language and agent models
Leveraging Diffusion Models for Stylization using Multiple Style ImagesDiffusion models → Image generation, text-to-image and editing
HeroBench: A Benchmark for Long-Horizon Planning and Structured Reasoning in Virtual WorldsLLM reasoning → Reasoning for agents, planning and code
HeteroRAG: A Heterogeneous Retrieval-Augmented Generation Framework for Medical Vision Language TasksMultimodal LLMs / vision-language models → Medical vision-language models +1
Deep Research: A Survey of Autonomous Research AgentsLLM agents and tool use → Web, search, and research agents
D2-Mamba: Dual-Scale Fusion and Dual-Path Scanning with SSMs for Shadow RemovalState-space sequence models (S4, Mamba) → Mamba for image restoration
A Multi-Resolution Benchmark Framework for Spatial Reasoning Assessment in Neural NetworksLLM reasoning → Spatial and embodied reasoning
LinguaSafe: A Comprehensive Multilingual Safety Benchmark for Large Language ModelsLLM safety and security → Safety alignment, refusal and guardrails
Unlearning Comparator: A Visual Analytics System for Comparative Evaluation of Machine Unlearning MethodsLLM safety and security → Machine unlearning
DESIGNER: Design-Logic-Guided Multidisciplinary Data Synthesis for LLM ReasoningLLM reasoning → Reasoning benchmarks and evaluation +1
Single-Reference Text-to-Image Manipulation with Dual Contrastive Denoising ScoreDiffusion models → Image generation, text-to-image and editing
Asymmetric Diffusion Recommendation ModelDiffusion models → Diffusion recommenders
Multi-Level Knowledge Distillation and Dynamic Self-Supervised Learning for Continual LearningKnowledge distillation → Distillation for continual learning
Adaptive Hybrid Caching for Efficient Text-to-Video Diffusion Model AccelerationDiffusion models → Video generation
EGOILLUSION: Benchmarking Hallucinations in Egocentric Video UnderstandingMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
ToolACE-MT: Non-Autoregressive Generation for Agentic Multi-Turn InteractionLLM agents and tool use → General LLM agent frameworks and benchmarks
A Taxonomy of Hierarchical Multi-Agent Systems: Design Patterns, Coordination Mechanisms, and Industrial ApplicationsLLM agents and tool use → General LLM agent frameworks and benchmarks
GridCodex: A RAG-Driven AI Framework for Power Grid Code Reasoning and ComplianceLLM reasoning → Knowledge- and tool-augmented reasoning
Vision-G1: Towards General Vision Language Reasoning with Multi-Domain Data CurationLLM reasoning → Multimodal reasoning
Stable Diffusion-Based Approach for Human De-OcclusionDiffusion models → 3D, point cloud and scene generation
Synthesizing Accurate and Realistic T1-weighted Contrast-Enhanced MR Images using Posterior-Mean Rectified FlowDiffusion models → Medical imaging and segmentation
edgeVLM: Cloud-edge Collaborative Real-time VLM based on Context TransferMultimodal LLMs / vision-language models → Visual token pruning and efficiency
Semantic Anchoring in Agentic Memory: Leveraging Linguistic Structures for Persistent Conversational ContextLLM agents and tool use → Agent memory systems
FlowMol3: Flow Matching for 3D De Novo Small-Molecule GenerationDiffusion models → Flow matching, time series and science
Creative4U: MLLMs-based Advertising Creative Image Selector with Comparative ReasoningLLM reasoning → Multimodal reasoning
Consiglieres in the Shadow: Understanding the Use of Uncensored Large Language Models in CybercrimesLLM safety and security → Prompt injection and agent security
ViDA-UGC: Detailed Image Quality Analysis via Visual Distortion Assessment for UGC ImagesMultimodal LLMs / vision-language models → Image editing and quality assessment
SSPO: Self-traced Step-wise Preference Optimization for Process Supervision and Reasoning CompressionLLM reasoning → Reinforcement learning for reasoning +1
ViLaD: A Large Vision Language Diffusion Framework for End-to-End Autonomous DrivingMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
Energy-Efficient Wireless LLM Inference via Uncertainty and Importance-Aware Speculative DecodingEfficient LLM inference and serving → Speculative decoding
Multimodal Chain of Continuous Thought for Latent-Space Reasoning in Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
Help or Hurdle? Rethinking Model Context Protocol-Augmented Large Language ModelsLLM reasoning → Reasoning for agents, planning and code +1
Illuminating LLM Coding Agents: Visual Analytics for Deeper Understanding and EnhancementLLM agents and tool use → Software engineering coding agents
TuneAgent: Agentic Operating System Kernel Tuning with Reinforcement LearningLLM agents and tool use → Software engineering coding agents
REVEAL -- Reasoning and Evaluation of Visual Evidence through Aligned LanguageLLM reasoning → Multimodal reasoning +1
MCPXKIT: The Unified Toolkit for Analyzing Model Context Protocol SecurityLLM agents and tool use → Agent threats, guardrails and governance
jXBW: A Compressed Index Enabling Structure-Aware JSONL Retrieval for Structured RAGRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG

All 332