Papers

New on arXiv

Tue 18 Mar 2025

379 papers

Zero-Shot Scene Understanding with Multimodal Large Language Models for Automated VehiclesMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
DashCLIP: Leveraging multimodal models for generating semantic embeddings for DoorDashMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
Leveraging Vision-Language Models for Open-Vocabulary Instance Segmentation and TrackingMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
Do Multimodal Large Language Models Understand Welding?Multimodal LLMs / vision-language models → Chart understanding and anomaly detection
Safety Evaluation and Enhancement of DeepSeek Models in Chinese ContextsLLM reasoning → Reasoning for agents, planning and code
HDLCoRe: A Training-Free Framework for Mitigating Hallucinations in LLM-Generated HDLRetrieval-augmented generation → RAG for code
Cosmos-Reason1: From Physical Common Sense To Embodied ReasoningLLM reasoning → Spatial and embodied reasoning
Personalized Attacks of Social Engineering in Multi-turn Conversations: LLM Agents for Simulation and DetectionLLM agents and tool use → Agent threats, guardrails and governance
ShapeShift: Text-to-Mosaic Synthesis via Semantic Phase-Field GuidanceDiffusion models → Image generation, text-to-image and editing
TestForge: Feedback-Driven, Agentic Test Suite GenerationLLM agents and tool use → Software engineering coding agents
Elevating Visual Question Answering through Implicitly Learned Reasoning Pathways in LVLMsLLM reasoning → Multimodal reasoning +1
Core-Periphery Principle Guided State Space Model for Functional Connectome ClassificationMixture-of-experts → Medical and biomedical MoE +1
A Simple Combination of Diffusion Models for Better Quality Trade-Offs in Image DenoisingDiffusion models → Diffusion foundations and sampling
RAGO: Systematic Performance Optimization for Retrieval-Augmented Generation ServingRetrieval-augmented generation → RAG pipeline design and evaluation +1
Retrieval-Augmented Simulacra: Generative Agents for Up-to-date and Knowledge-Adaptive SimulationsRetrieval-augmented generation → Agentic RAG, agents and memory +1
Can Large Vision Language Models Read Maps Like a Human?Multimodal LLMs / vision-language models → Embodied and 3D vision-language models
Image Captioning Evaluation in the Age of Multimodal LLMs: Challenges and Future PerspectivesMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Potential Score Matching: Debiasing Molecular Structure Sampling with Potential Energy GuidanceDiffusion models → Flow matching, time series and science
SuperPC: A Single Diffusion Model for Point Cloud Completion, Upsampling, Denoising, and ColorizationWorld models → World modeling from LiDAR generation +1
Generating Causal Explanations of Vehicular Agent Behavioural Interactions with Learnt Reward ProfilesLLM reasoning → Chain-of-thought reasoning for driving
MusicInfuser: Making Video Diffusion Listen and DanceDiffusion models → Audio, speech and music
Aligning Multimodal LLM with Human Preference: A SurveyMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
Tracking Meets Large Multimodal Models for Driving Scenario UnderstandingMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
Temporal Consistency for LLM Reasoning Process Error IdentificationLLM reasoning → Mathematical reasoning
Stable Virtual Camera: Generative View Synthesis with Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
DiffMoE: Dynamic Token Selection for Scalable Diffusion TransformersDiffusion models → Diffusion foundations and sampling
Lux Post Facto: Learning Portrait Performance Relighting with Conditional Video Diffusion and a Hybrid DatasetDiffusion models → 3D, point cloud and scene generation
DAPO: An Open-Source LLM Reinforcement Learning System at ScaleLLM reasoning → Reinforcement learning for reasoning
SIR-DIFF: Sparse Image Sets Restoration with Multi-View Diffusion ModelDiffusion models → Inverse problems and image restoration
Pauli Network Circuit Synthesis with Reinforcement LearningDeep reinforcement learning methods → Quantum reinforcement learning
Bolt3D: Generating 3D Scenes in SecondsDiffusion models → 3D, point cloud and scene generation
PLAY2PROMPT: Zero-shot Tool Instruction Optimization for LLM Agents via Tool PlayLLM agents and tool use → Tool learning and function calling
DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D TeachersKnowledge distillation → Detection and dense prediction distillation
How much do LLMs learn from negative examples?LLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Good/Evil Reputation Judgment of Celebrities by LLMs via Retrieval Augmented GenerationRetrieval-augmented generation → RAG pipeline design and evaluation
RFMI: Estimating Mutual Information on Rectified Flow for Text-to-Image AlignmentDiffusion models → Image generation, text-to-image and editing
MAST-Pro: Dynamic Mixture-of-Experts for Adaptive Segmentation of Pan-Tumors with Knowledge-Driven PromptsMixture-of-experts → Medical and biomedical MoE
VEGGIE: Instructional Editing and Reasoning Video Concepts with Grounded GenerationLLM reasoning → Multimodal reasoning +1
MANTRA: Enhancing Automated Method-Level Refactoring with Contextual RAG and Multi-Agent LLM CollaborationLLM agents and tool use → Software engineering coding agents
PENCIL: Long Thoughts with Short MemoryLLM reasoning → Prompting and chain-of-thought reasoning
Characterizing higher-order representations through generative diffusion models explains human decoded neurofeedback performanceDiffusion models → Diffusion and flow policies for robotics
EvolvingGrasp: Evolutionary Grasp Generation via Efficient Preference AlignmentLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
LeanVAE: An Ultra-Efficient Reconstruction VAE for Video Diffusion ModelsDiffusion models → Diffusion foundations and sampling
Free-Lunch Color-Texture Disentanglement for Stylized Image GenerationDiffusion models → Image generation, text-to-image and editing
DARS: Dynamic Action Re-Sampling to Enhance Coding Agent Performance by Adaptive Tree TraversalLLM agents and tool use → Software engineering coding agents
Conversational Agents as Catalysts for Critical Thinking: Challenging Social Influence in Group Decision-makingLLM reasoning → Reasoning for agents, planning and code +1
Quantization-Free Autoregressive Action TransformerOffline RL and imitation learning from data → Robot manipulation imitation learning
JuDGE: Benchmarking Judgment Document Generation for Chinese Legal SystemRetrieval-augmented generation → Legal and financial RAG
CTSAC: Curriculum-Based Transformer Soft Actor-Critic for Goal-Oriented Robot ExplorationDeep reinforcement learning methods → RL for robot locomotion and manipulation
Towards a Barrier-free GeoQA Portal: Natural Language Interaction with Geospatial Data Using Multi-Agent LLMs and Semantic SearchLLM agents and tool use → Multimodal and embodied agents
A Parallel Hybrid Action Space Reinforcement Learning Model for Real-world Adaptive Traffic Signal ControlDeep reinforcement learning methods → RL for autonomous driving and traffic
Beyond Single Pass, Looping Through Time: KG-IRAG with Iterative Knowledge RetrievalRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
CRCE: Coreference-Retention Concept Erasure in Text-to-Image Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
Benchmarking Failures in Tool-Augmented Language ModelsLLM agents and tool use → Tool learning and function calling
Towards Harmless Multimodal Assistants with Blind Preference OptimizationMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
Bridging Past and Future: End-to-End Autonomous Driving with Historical Prediction and PlanningEnd-to-end autonomous driving → Generative simulation for driving
Synthetic Clarification and Correction Dialogues about Data-Centric Tasks -- A Teacher-Student ApproachKnowledge distillation → Knowledge distillation for LLMs
CoSpace: Benchmarking Continuous Space Perception Ability for Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Speculative Decoding for Verilog: Speed and Quality, All in OneEfficient LLM inference and serving → Speculative decoding
Marten: Visual Question Answering with Mask Generation for Multi-modal Document UnderstandingMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
DangerMaps: Personalized Safety Advice for Travel in Urban Environments using a Retrieval-Augmented Language ModelRetrieval-augmented generation → RAG for recommendation
Theoretical Foundation of Flow-Based Time Series Generation: Provable Approximation, Generalization, and EfficiencyDiffusion models → Flow matching, time series and science
Growing a Multi-head Twig via Distillation and Reinforcement Learning to Accelerate Large Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
Fast Autoregressive Video Generation with Diagonal DecodingEfficient LLM inference and serving → Fast autoregressive visual generation
Synthetic Data Generation Using Large Language Models: Advances in Text and CodeSynthetic data and self-improvement for LLMs → LLM synthetic data generation
Empowering Smaller Models: Tuning LLaMA and Gemma with Chain-of-Thought for Ukrainian Exam TasksLLM reasoning → Reasoning benchmarks and evaluation
DefectFill: Realistic Defect Generation with Inpainting Diffusion Model for Visual InspectionDiffusion models → Flow matching, time series and science
SpaceVLLM: Endowing Multimodal Large Language Model with Spatio-Temporal Video Grounding CapabilityMultimodal LLMs / vision-language models → Video understanding with MLLMs
Empowering LLMs in Decision Games through Algorithmic Data SynthesisSynthetic data and self-improvement for LLMs → Self-play RL for reasoning
MDocAgent: A Multi-Modal Multi-Agent Framework for Document UnderstandingLLM agents and tool use → Multimodal and embodied agents
Survey of Adversarial Robustness in Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
Improving LLM Video Understanding with 16 Frames Per SecondMultimodal LLMs / vision-language models → Video understanding with MLLMs
SimWorld: A Unified Benchmark for Simulator-Conditioned Scene Generation via World ModelWorld models → World models for autonomous driving
Make the Most of Everything: Further Considerations on Disrupting Diffusion-based CustomizationDiffusion models → Robustness, privacy and adversarial aspects +1
Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language ModelsLLM reasoning → Clinical and biomedical applications +1
ChatBEV: Empowering Traffic Scene Understanding and Simulation via Vision-Language ModelMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
COLSON: Controllable Learning-Based Social Navigation via Diffusion-Based Reinforcement LearningDiffusion models → Diffusion and flow policies for robotics +1
Robust Machine Unlearning for Quantized Neural Networks via Adaptive Gradient Reweighting with Similar LabelsLLM safety and security → Machine unlearning
Where do Large Vision-Language Models Look at when Answering Questions?Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
MoK-RAG: Mixture of Knowledge Paths Enhanced Retrieval-Augmented Generation for Embodied AI EnvironmentsRetrieval-augmented generation → Agentic RAG, agents and memory
MMR: A Large-scale Benchmark Dataset for Multi-target and Multi-granularity Reasoning SegmentationLLM reasoning → Multimodal reasoning
Bridging Social Psychology and LLM Reasoning: Conflict-Aware Meta-Review Generation via Cognitive AlignmentLLM reasoning → Knowledge- and tool-augmented reasoning
RAD: Retrieval-Augmented Decision-Making of Meta-Actions with Vision-Language Models in Autonomous DrivingMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +2
Less is More: Improving Motion Diffusion Models with Sparse KeyframesDiffusion models → Video generation
MDTeamGPT: A Self-Evolving LLM-based Multi-Agent Framework for Multi-Disciplinary Team Medical ConsultationLLM agents and tool use → Medical and scientific domain agents +1
WebNav: An Intelligent Agent for Voice-Controlled Web NavigationLLM agents and tool use → Web, search, and research agents
Counterfactual experience augmented off-policy reinforcement learningDeep reinforcement learning methods → Interpretable and logic-guided RL
SALAD: Skeleton-aware Latent Diffusion for Text-driven Motion Generation and EditingDiffusion models → Video generation
Scale-Aware Contrastive Reverse Distillation for Unsupervised Medical Anomaly DetectionKnowledge distillation → Detection and dense prediction distillation
VARP: Reinforcement Learning from Vision-Language Model Feedback with Agent Regularized PreferencesMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +2
Text-Guided Image Invariant Feature Learning for Robust Image WatermarkingLLM safety and security → Watermarking generated content and models
Identifying and Mitigating Position Bias of Multi-image Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Linear to Neural Networks Regression: QSPR of Drugs via Degree-Distance Indices
Multi-user Wireless Image Semantic Transmission over MIMO Multiple Access Channels
Validating Emergency Department Admission Predictions Based on Local Data Through MIMIC-IV
Enhancing nonnative speech perception and production through an AI-powered application
Binary AddiVortes: (Bayesian) Additive Voronoi Tessellations for Binary Classification with an application to Predicting Home Mortgage Application Outcomes
Robust Object Detection of Underwater Robot based on Domain Generalization
A Real-Time Human Action Recognition Model for Assisted Living
International Agreements on AI Safety: Review and Recommendations for a Conditional AI Safety Treaty

All 379