Papers

New on arXiv

Thu 27 Mar 2025

347 papers

A Survey on (M)LLM-Based GUI AgentsLLM agents and tool use → GUI and mobile agents
Geometric Flow Models over Neural Network WeightsDiffusion models → Flow matching, time series and science
Medical Reasoning in LLMs: An In-Depth Analysis of DeepSeek R1LLM reasoning → Clinical and biomedical applications
Data Poisoning in Deep Learning: A SurveyLLM safety and security → Backdoor and data poisoning attacks
ThinkEdit: Interpretable Weight Editing to Mitigate Overly Short Thinking in Reasoning ModelsLLM reasoning → Test-time compute and efficient thinking
Debate-Driven Multi-Agent LLMs for Phishing Email DetectionLLM agents and tool use → Agent threats, guardrails and governance
CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action ModelsLLM reasoning → Spatial and embodied reasoning +2
Enhancing Domain-Specific Encoder Models with LLM-Generated Data: How to Leverage Ontologies, and How to Do Without ThemSynthetic data and self-improvement for LLMs → LLM synthetic data generation
Bresa: Bio-inspired Reflexive Safe Reinforcement Learning for Contact-Rich Robotic TasksDeep reinforcement learning methods → Safe and constrained RL
Robotic Long-Horizon Manipulation with Bayesian Non-parametric Skill PriorsDeep reinforcement learning methods → RL for robot locomotion and manipulation
RocketPPA: Code-Level Power, Performance, and Area Prediction via LLM and Mixture of ExpertsMixture-of-experts → Mixture of LoRA experts
Q-MambaIR: Accurate Quantized Mamba for Efficient Image RestorationState-space sequence models (S4, Mamba) → Mamba for image restoration
Entropy-Gated Branching for Efficient Test-Time ReasoningLLM reasoning → Test-time compute and efficient thinking
Reward Design for Reinforcement Learning AgentsDeep reinforcement learning methods → Deep RL algorithms and representations
Parametric Shadow Control for Portrait Generation in Text-to-Image Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
Lobster: A GPU-Accelerated Framework for Neurosymbolic ProgrammingLLM reasoning → Reasoning benchmarks and evaluation
Proof or Bluff? Evaluating LLMs on 2025 USA Math OlympiadLLM reasoning → Mathematical reasoning
JEEM: Vision-Language Understanding in Four Arabic DialectsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
StarFlow: Generating Structured Workflow Outputs From Sketch ImagesMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time AlignmentLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
On Large Multimodal Models as Open-World Image ClassifiersMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Vision Language Models versus Machine Learning Models Performance on Polyp Detection and Classification in Colonoscopy ImagesMultimodal LLMs / vision-language models → Medical vision-language models
M-DocSum: Do LVLMs Genuinely Comprehend Interleaved Image-Text in Document Summarization?Multimodal LLMs / vision-language models → MLLM training and visual instruction tuning
VideoMage: Multi-Subject and Motion Customization of Text-to-Video Diffusion ModelsDiffusion models → Video generation
Video-R1: Reinforcing Video Reasoning in MLLMsLLM reasoning → Multimodal reasoning +1
StyleMotif: Multi-Modal Motion Stylization using Style-Content Cross FusionDiffusion models → Image generation, text-to-image and editing
Optimal Stepsize for Diffusion SamplingDiffusion models → Diffusion foundations and sampling
Exploring the Evolution of Physics Cognition in Video Generation: A SurveyDiffusion models → Video generation
MemInsight: Autonomous Memory Augmentation for LLM AgentsLLM agents and tool use → Agent memory systems
Fwd2Bot: LVLM Visual Token Compression with Double Forward BottleneckMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
A Unified Framework for Diffusion Bridge Problems: Flow Matching and Schr"odinger Matching into OneDiffusion models → Diffusion foundations and sampling
VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic FaithfulnessWorld models → Video-generation world models and simulators
GateLens: A Reasoning-Enhanced LLM Agent for Automotive Software Release AnalyticsLLM reasoning → Reasoning for agents, planning and code +1
Effective Skill Unlearning through Intervention and AbstentionLLM safety and security → Machine unlearning
ReaRAG: Knowledge-guided Reasoning Enhances Factuality of Large Reasoning Models with Iterative Retrieval Augmented GenerationLLM reasoning → Knowledge- and tool-augmented reasoning +1
Collab: Controlled Decoding using Mixture of Agents for LLM AlignmentLLM agents and tool use → General LLM agent frameworks and benchmarks +1
MAVERIX: Multimodal Audio-Visual Evaluation and Recognition IndeXMultimodal LLMs / vision-language models → Video understanding with MLLMs
Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive TasksLLM reasoning → Spatial and embodied reasoning
Progressive Rendering Distillation: Adapting Stable Diffusion for Instant Text-to-Mesh Generation without 3D DataDiffusion models → 3D, point cloud and scene generation
LLM-Gomoku: A Large Language Model-Based System for Strategic Gomoku with Self-Play and Reinforcement LearningSynthetic data and self-improvement for LLMs → Self-play RL for reasoning
A tale of two goals: leveraging sequentiality in multi-goal scenariosDeep reinforcement learning methods → Deep RL algorithms and representations
Cognitive Science-Inspired Evaluation of Core Capabilities for Object Understanding in AIWorld models → World models for language agents
UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement LearningLLM reasoning → Multimodal reasoning +2
A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and BeyondLLM reasoning → Test-time compute and efficient thinking
Prompt, Divide, and Conquer: Bypassing Large Language Model Safety Filters via Segmented and Distributed Prompt ProcessingLLM safety and security → Jailbreaking
Simple and Critical Iterative Denoising: A Recasting of Discrete Diffusion in Graph GenerationDiffusion models → Flow matching, time series and science
debug-gym: A Text-Based Environment for Interactive DebuggingLLM agents and tool use → Software engineering coding agents
SyncSDE: A Probabilistic Framework for Diffusion SynchronizationDiffusion models → Diffusion foundations and sampling
Fine-Grained Evaluation of Large Vision-Language Models in Autonomous DrivingMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
Invert2Restore: Zero-Shot Degradation-Blind Image RestorationDiffusion models → Inverse problems and image restoration
BOLT: Boost Large Vision-Language Model Without Training for Long-form Video UnderstandingMultimodal LLMs / vision-language models → Video understanding with MLLMs
Harnessing Chain-of-Thought Metadata for Task Routing and Adversarial Prompt DetectionLLM reasoning → Prompting and chain-of-thought reasoning +1
Large Language Model Agent: A Survey on Methodology, Applications and ChallengesLLM agents and tool use → General LLM agent frameworks and benchmarks
FaceBench: A Multi-View Multi-Level Facial Attribute VQA Dataset for Benchmarking Face Perception MLLMsMultimodal LLMs / vision-language models → Social bias and fairness in VLMs
Towards Generating Realistic 3D Semantic Training Data for Autonomous DrivingWorld models → World models for autonomous driving
Graph-to-Vision: Multi-graph Understanding and Reasoning using Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
Diffusion Image PriorDiffusion models → Inverse problems and image restoration
Neuro-Symbolic Imitation Learning: Discovering Symbolic Abstractions for Skill LearningOffline RL and imitation learning from data → Robot manipulation imitation learning
Challenging the Boundaries of Reasoning: An Olympiad-Level Math Benchmark for Large Language ModelsLLM reasoning → Mathematical reasoning
CA+: Cognition Augmented Counselor Agent Framework for Long-term Dynamic Client EngagementLLM agents and tool use → Medical and scientific domain agents
HyperGraphRAG: Retrieval-Augmented Generation via Hypergraph-Structured Knowledge RepresentationRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
Tricking Retrievers with Influential Tokens: An Efficient Black-Box Corpus Poisoning AttackRetrieval-augmented generation → Privacy and security of RAG
InternVL-X: Advancing and Accelerating InternVL Series with Efficient Visual Token CompressionMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
R-PRM: Reasoning-Driven Process Reward ModelingLLM reasoning → Reinforcement learning for reasoning +1
Delving Deep into Semantic Relation DistillationKnowledge distillation → General knowledge distillation methods
OminiAdapt: Learning Cross-Task Invariance for Robust and Environment-Aware Robotic ManipulationOffline RL and imitation learning from data → Real-world robot offline RL
DynamiCtrl: Rethinking the Basic Structure and the Role of Text for High-quality Human Image AnimationDiffusion models → Video generation
Bias-Aware Agent: Enhancing Fairness in AI-Driven Knowledge RetrievalLLM agents and tool use → Web, search, and research agents
Clean Image May be Dangerous: Data Poisoning Attacks Against Deep HashingLLM safety and security → Backdoor and data poisoning attacks
Knowledge Graphs as World Models for Semantic Material-Aware Obstacle Handling in Autonomous VehiclesWorld models → World models for autonomous driving +1
LLaVA-CMoE: Towards Continual Mixture of Experts for Large Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP +1
VoxRep: Enhancing 3D Spatial Understanding in 2D Vision-Language Models via Voxel RepresentationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Toward Generalizable Forgery Detection and ReasoningLLM reasoning → Multimodal reasoning
Model as a Game: On Numerical and Spatial Consistency for Generative GamesWorld models → Video-generation world models and simulators
VADMamba: Exploring State Space Models for Fast Video Anomaly DetectionState-space sequence models (S4, Mamba) → Time series forecasting with SSMs
Real-Time Evaluation Models for RAG: Who Detects Hallucinations Best?Retrieval-augmented generation → Hallucination detection in RAG
ChatAnyone: Stylized Real-time Portrait Video Generation with Hierarchical Motion Diffusion ModelDiffusion models → Audio, speech and music
DynaMo: Runtime Switchable Quantization for MoE with Cross-Dataset AdaptationMixture-of-experts → MoE large language models
ZJUKLAB at SemEval-2025 Task 4: Unlearning via Model MergingLLM safety and security → Machine unlearning
Can Video Diffusion Model Reconstruct 4D Geometry?Diffusion models → 3D, point cloud and scene generation
EmoDebt: Bayesian-Optimized Emotional Intelligence for Strategic Agent-to-Agent Debt RecoveryLLM agents and tool use → Social simulation and multi-agent debate
Efficient Multi-Instance Generation with Janus-Pro-Dirven Prompt ParsingDiffusion models → Image generation, text-to-image and editing
Online Reasoning Video Segmentation with Just-in-Time Digital TwinsLLM reasoning → Multimodal reasoning
Empirical Studies of Large Scale Environment Scanning by Consumer Electronics
Immersive Multimedia Communication: State-of-the-Art on eXtended Reality Streaming
Research on the Design of a Short Video Recommendation System Based on Multimodal Information and Differential Privacy
EquiNO: A Physics-Informed Neural Operator for Multiscale Simulations
Gaze-Guided 3D Hand Motion Prediction for Detecting Intent in Egocentric Grasping Tasks
ObscuraCoder: Powering Efficient Code LM Pre-Training Via Obfuscation Grounding
SandboxEval: Towards Securing Test Environment for Untrusted Code
Enhance Vision-based Tactile Sensors via Dynamic Illumination and Image Fusion
Boosting Large Language Models with Mask Fine-Tuning
The Cost of Local and Global Fairness in Federated Learning
Malicious and Unintentional Disclosure Risks in Large Language Models for Code Generation
Multiple Embeddings for Quantum Machine Learning
Towards an intelligent assessment system for evaluating the development of algorithmic thinking skills: An exploratory study in Swiss compulsory schools
Reasoning Under Threat: Symbolic and Neural Techniques for Cybersecurity Verification
Model Lake: a New Alternative for Machine Learning Models Management and Governance
Combating the Bullwhip Effect in Rival Online Food Delivery Platforms Using Deep Learning
From Individual to Group: Developing a Context-Aware Multi-Criteria Group Recommender System

All 347