Papers

New on arXiv

Mon 10 Mar 2025

462 papers

VocalEyes: Enhancing Environmental Perception for the Visually Impaired through Vision-Language Models and Distance-Aware Object DetectionMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
UC-MOA: Utility-Conditioned Multi-Objective Alignment for Distributional Pareto-OptimalityLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
AuthorMist: Evading AI Text Detectors with Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
Simulating Influence Dynamics with LLM AgentsLLM agents and tool use → Social simulation and multi-agent debate
BEARCUBS: A benchmark for computer-using web agentsLLM agents and tool use → Web, search, and research agents
Painting with Words: Elevating Detailed Image Captioning with Benchmark and Alignment LearningMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning +1
Can Memory-Augmented Language Models Generalize on Reasoning-in-a-Haystack Tasks?LLM reasoning → Knowledge- and tool-augmented reasoning
Can Generative Geospatial Diffusion Models Excel as Discriminative Geospatial Foundation Models?Diffusion models → Inverse problems and image restoration
Safety Guardrails for LLM-Enabled RobotsLLM safety and security → Safety alignment, refusal and guardrails
RefactorBench: Evaluating Stateful Reasoning in Language Agents Through CodeLLM reasoning → Reasoning for agents, planning and code +1
Magnet: Multi-turn Tool-use Data Synthesis and Distillation via Graph TranslationLLM agents and tool use → Tool learning and function calling +1
Group Fairness in Multi-Task Reinforcement LearningDeep reinforcement learning methods → RL for games and combinatorial optimization
Training Domain Draft Models for Speculative Decoding: Best Practices and InsightsEfficient LLM inference and serving → Speculative decoding +1
Towards Large Language Models that Benefit for All: Benchmarking Group Fairness in Reward ModelsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
Hallucinatory Image Tokens: A Training-free EAZY Approach on Detecting and Mitigating Object Hallucinations in LVLMsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
RoboCopilot: Human-in-the-loop Interactive Imitation Learning for Robot ManipulationOffline RL and imitation learning from data → Robot manipulation imitation learning
A Simple Approach to Constraint-Aware Imitation Learning with Application to Autonomous RacingOffline RL and imitation learning from data → Imitation learning methods
Seedream 2.0: A Native Chinese-English Bilingual Image Generation Foundation ModelDiffusion models → Image generation, text-to-image and editing
RayFlow: Instance-Aware Diffusion Acceleration via Adaptive Flow TrajectoriesDiffusion models → Diffusion foundations and sampling
PoisonedParrot: Subtle Data Poisoning Attacks to Elicit Copyright-Infringing Content from Large Language ModelsLLM safety and security → Backdoor and data poisoning attacks
Fully Autonomous Programming using Iterative Multi-Agent Debugging with Large Language ModelsLLM agents and tool use → Software engineering coding agents
Using a single actor to output personalized policy for different intersectionsDeep reinforcement learning methods → RL for autonomous driving and traffic
PLADIS: Pushing the Limits of Attention in Diffusion Models at Inference Time by Leveraging SparsityDiffusion models → Diffusion foundations and sampling
DynTaskMAS: A Dynamic Task Graph-driven Framework for Asynchronous and Parallel LLM-based Multi-Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and ReasoningLLM reasoning → Chain-of-thought reasoning for driving +1
Implicit Reasoning in Transformers is Reasoning through ShortcutsLLM reasoning → Reasoning benchmarks and evaluation
Balanced Image Stylization with Style Matching ScoreDiffusion models → Image generation, text-to-image and editing
VACE: All-in-One Video Creation and EditingDiffusion models → Video generation
Filter Images First, Generate Instructions Later: Pre-Instruction Data Selection for Visual Instruction TuningMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
When Large Vision-Language Model Meets Large Remote Sensing Imagery: Coarse-to-Fine Text-Guided Token PruningMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
Robusto-1 Dataset: Comparing Humans and VLMs on real out-of-distribution Autonomous Driving VQA from PeruEnd-to-end autonomous driving → VLMs for autonomous driving
Talking to GDELT Through Knowledge GraphsRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
BOPO: Neural Combinatorial Optimization via Best-anchored and Objective-guided Preference OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Denoising Score Distillation: From Noisy Diffusion Pretraining to One-Step High-Quality GenerationDiffusion models → Diffusion foundations and sampling
VisBias: Measuring Explicit and Implicit Social Biases in Vision Language ModelsMultimodal LLMs / vision-language models → Social bias and fairness in VLMs
Optimizing Test-Time Compute via Meta Reinforcement Fine-TuningLLM reasoning → Reinforcement learning for reasoning +1
Inductive Moment MatchingDiffusion models → Diffusion foundations and sampling
AutoSpatial: Visual-Language Reasoning for Social Robot Navigation through Efficient Spatial Reasoning LearningLLM reasoning → Spatial and embodied reasoning
LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RLLLM reasoning → Multimodal reasoning +1
VisRL: Intention-Driven Visual Perception via Reinforced ReasoningLLM reasoning → Multimodal reasoning
TokenButler: Token Importance is PredictableEfficient LLM inference and serving → KV cache optimization
PointVLA: Injecting the 3D World into Vision-Language-Action ModelsLLM reasoning → Spatial and embodied reasoning +3
Think Before You Segment: High-Quality Reasoning Segmentation with GPT Chain of ThoughtsLLM reasoning → Multimodal reasoning
LLaVA-RadZ: Can Multimodal Large Language Models Effectively Tackle Zero-shot Radiology Recognition?Multimodal LLMs / vision-language models → Medical vision-language models
How does Bayesian Sampling help Membership Inference Attacks?LLM safety and security → Membership inference attacks
VLRMBench: A Comprehensive and Challenging Benchmark for Vision-Language Reward ModelsLLM reasoning → Multimodal reasoning +2
MedicalAgentsBench for Complex Medical Reasoning: Comparing Internalized Reasoning Models versus Externalized Agent-based FrameworksLLM reasoning → Clinical and biomedical applications +1
Is a Good Foundation Necessary for Efficient Reinforcement Learning? The Computational Role of the Base Model in ExplorationLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
RePO: Understanding Preference Learning Through ReLU-Based OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Collision Risk Estimation via Loss Prediction in End-to-End Autonomous DrivingEnd-to-end autonomous driving → End-to-end system architecture
AR-Diffusion: Asynchronous Video Generation with Auto-Regressive DiffusionDiffusion models → Video generation
GM-MoE: Low-Light Enhancement with Gated-Mechanism Mixture-of-ExpertsMixture-of-experts → Vision mixture-of-experts
TimeStep Master: Asymmetrical Mixture of Timestep LoRA Experts for Versatile and Efficient Diffusion Models in VisionDiffusion models → Diffusion foundations and sampling
REF-VLM: Triplet-Based Referring Paradigm for Unified Visual DecodingMultimodal LLMs / vision-language models → Visual token pruning and efficiency
PER-DPP Sampling Framework and Its Application in Path PlanningDeep reinforcement learning methods → Deep RL algorithms and representations
SPEED: Scalable, Precise, and Efficient Concept Erasure for Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
TRCE: Towards Reliable Malicious Concept Erasure in Text-to-Image Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
Is My Text in Your AI Model? Gradient-based Membership Inference Test applied to LLMsLLM safety and security → Membership inference attacks
AttentionSwarm: Reinforcement Learning with Attention Control Barier Function for Crazyflie Drones in Dynamic EnvironmentsDeep reinforcement learning methods → RL for robot navigation and UAV control
MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement LearningLLM reasoning → Multimodal reasoning
DaD: Distilled Reinforcement Learning for Diverse Keypoint DetectionDeep reinforcement learning methods → RL for robot locomotion and manipulation
Delta-Triplane Transformers as Occupancy World ModelsWorld models → World models for autonomous driving
Navigating Motion Agents in Dynamic and Cluttered Environments through LLM ReasoningLLM reasoning → Spatial and embodied reasoning +1
Automated Movie Generation via Multi-Agent CoT PlanningLLM agents and tool use → Multimodal and embodied agents
AttenST: A Training-Free Attention-Driven Style Transfer Framework with Pre-Trained Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
Goal Conditioned Reinforcement Learning for Photo Finishing TuningDeep reinforcement learning methods → RL with diffusion and flow models
ALLVB: All-in-One Long Video Understanding BenchmarkMultimodal LLMs / vision-language models → Video understanding with MLLMs
Efficient Distillation of Classifier-Free Guidance using AdaptersDiffusion models → Diffusion foundations and sampling
CoT-Drive: Efficient Motion Forecasting for Autonomous Driving with LLMs and Chain-of-Thought PromptingLLM reasoning → Chain-of-thought reasoning for driving +2
Boosting Diffusion-Based Text Image Super-Resolution Model Towards Generalized Real-World ScenariosDiffusion models → Inverse problems and image restoration
Effective and Efficient Masked Image Generation ModelsDiffusion models → Diffusion foundations and sampling
Ideas in Inference-time Scaling can Benefit Generative Pre-training AlgorithmsLLM reasoning → Diffusion reasoning and test-time scaling +1
Controllable 3D Outdoor Scene Generation via Scene GraphsWorld models → Video-generation world models and simulators +1
Hierarchical Neuro-Symbolic Decision TransformerOffline RL and imitation learning from data → Decision transformers and sequence modeling
Application of Multiple Chain-of-Thought in Contrastive Reasoning for Implicit Sentiment AnalysisLLM reasoning → Audio-language model reasoning
A Comprehensive Survey of Mixture-of-Experts: Algorithms, Theory, and ApplicationsMixture-of-experts → MoE theory and gating functions
FEB-Cache: Frequency-Guided Exposure Bias Reduction for Enhancing Diffusion Transformer CachingDiffusion models → Diffusion foundations and sampling
A Novel Ophthalmic Benchmark for Evaluating Multimodal Large Language Models with Fundus Photographs and OCT ImagesMultimodal LLMs / vision-language models → Medical vision-language models
RS2AD: End-to-End Autonomous Driving Data Generation from Roadside Sensor ObservationsEnd-to-end autonomous driving → End-to-end system architecture
XR-VLM: Cross-Relationship Modeling with Multi-part Prompts and Visual Features for Fine-Grained RecognitionMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Boosting the Generalization and Reasoning of Vision Language Models with Curriculum Reinforcement LearningLLM reasoning → Multimodal reasoning +1
Generative method for aerodynamic optimization based on classifier-free guided denoising diffusion probabilistic modelDiffusion models → Flow matching, time series and science
TIDE : Temporal-Aware Sparse Autoencoders for Interpretable Diffusion Transformers in Image GenerationDiffusion models → Diffusion foundations and sampling +1
VMTS: Vision-Assisted Teacher-Student Reinforcement Learning for Multi-Terrain Locomotion in Bipedal RobotsDeep reinforcement learning methods → RL for robot locomotion and manipulation
Recovering Partially Corrupted Objects via Sketch-Guided Bidirectional Feature InteractionDiffusion models → 3D, point cloud and scene generation
MambaFlow: A Mamba-Centric Architecture for End-to-End Optical Flow EstimationState-space sequence models (S4, Mamba) → Vision Mamba backbones
DatawiseAgent: A Notebook-Centric LLM Agent Framework for Adaptive and Robust Data Science AutomationLLM agents and tool use → Web, search, and research agents
EasyControl: Adding Efficient and Flexible Control for Diffusion TransformerDiffusion models → Diffusion foundations and sampling
Driving Through Uncertainty: Risk-Averse Control with LLM Commonsense for Autonomous Driving under Perception DeficitsEnd-to-end autonomous driving → Large language models for driving
Toward Multi-Session Personalized Conversation: A Large-Scale Dataset and Hierarchical Tree Framework for Implicit ReasoningLLM reasoning → Reasoning for agents, planning and code
How to Train Your Robots? The Impact of Demonstration Modality on Imitation LearningOffline RL and imitation learning from data → Robot manipulation imitation learning
ProjectEval: A Benchmark for Programming Agents Automated Evaluation on Project-Level Code GenerationLLM agents and tool use → Software engineering coding agents
Taking Notes Brings Focus? Towards Multi-Turn Multimodal Dialogue LearningMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
SOYO: A Tuning-Free Approach for Video Style Morphing via Style-Adaptive Interpolation in Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
CAPT: Class-Aware Prompt Tuning for Federated Long-Tailed Learning with Vision-Language ModelMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Are We Truly Forgetting? A Critical Re-examination of Machine Unlearning Evaluation ProtocolsLLM safety and security → Machine unlearning
Probabilistic Modeling of Jailbreak on Multimodal LLMs: From Quantification to ApplicationMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
Exploring Multimodal Perception in Large Language Models Through Perceptual Strength RatingsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Task-Specific Knowledge Distillation from the Vision Foundation Model for Enhanced Medical Image SegmentationKnowledge distillation → Distillation for medical imaging
ReAgent: Reversible Multi-Agent Reasoning for Knowledge-Enhanced Multi-Hop QALLM reasoning → Knowledge- and tool-augmented reasoning +1

All 462