Papers

New on arXiv

Wed 19 Mar 2025

337 papers

Learning Distributions of Complex Fluid Simulations with Diffusion Graph NetworksDiffusion models → Flow matching, time series and science
Reachable Sets-based Trajectory Planning Combining Reinforcement Learning and iLQRDeep reinforcement learning methods → RL for autonomous driving and traffic
MathFlow: Enhancing the Perceptual Flow of MLLMs for Visual Mathematical ProblemsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Empowering Medical Multi-Agents with Clinical Consultation Flow for Dynamic DiagnosisLLM agents and tool use → Medical and scientific domain agents
Comprehensive Review of Reinforcement Learning for Medical Ultrasound ImagingDeep reinforcement learning methods → RL for clinical treatment and surgery
Reward Training Wheels: Adaptive Auxiliary Rewards for Robotics Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
Safety Aware Task Planning via Large Language Models in RoboticsLLM reasoning → Spatial and embodied reasoning
Good Actions Succeed, Bad Actions Generalize: A Case Study on Why RL Generalizes BetterDeep reinforcement learning methods → Deep RL algorithms and representations
Multi-focal Conditioned Latent Diffusion for Person Image SynthesisDiffusion models → 3D, point cloud and scene generation
GASP: Unifying Geometric and Semantic Self-Supervised Pre-training for Autonomous DrivingEnd-to-end autonomous driving → Generative simulation for driving
Enhancing Pancreatic Cancer Staging with Large Language Models: The Role of Retrieval-Augmented GenerationRetrieval-augmented generation → Medical and biomedical RAG
Vision-Speech Models: Teaching Speech Models to Converse about ImagesMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Neural Lyapunov Function Approximation with Self-Supervised Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
LLaVA-MORE: A Comparative Study of LLMs and Visual Backbones for Enhanced Visual Instruction TuningMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Towards Unified and Lossless Latent Space for 3D Molecular Latent Diffusion ModelingDiffusion models → Flow matching, time series and science
Value Profiles for Encoding Human VariationLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning TasksLLM reasoning → Reasoning for agents, planning and code +1
What Makes a Reward Model a Good Teacher? An Optimization PerspectiveLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
FP4DiT: Towards Effective Floating Point Quantization for Diffusion TransformersDiffusion models → Diffusion foundations and sampling
From 1,000,000 Users to Every User: Scaling Up Personalized Preference for User-level AlignmentLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
Dimathtt[M]O: Distilling Masked Diffusion Models into One-step GeneratorDiffusion models → Diffusion foundations and sampling
Bias Evaluation and Mitigation in Retrieval-Augmented Medical Question-Answering SystemsRetrieval-augmented generation → Medical and biomedical RAG
Visual Position Prompt for MLLM based Visual GroundingMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Visual Persona: Foundation Model for Full-Body Human CustomizationDiffusion models → Image generation, text-to-image and editing
CCDP: Composition of Conditional Diffusion Policies with Guided SamplingDiffusion models → Diffusion and flow policies for robotics +1
EfficientLLaVA:Generalizable Auto-Pruning for Large Vision-language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
Online Imitation Learning for Manipulation via Decaying Relative Correction through TeleoperationOffline RL and imitation learning from data → Robot manipulation imitation learning
Boosting HDR Image Reconstruction via Semantic Knowledge TransferKnowledge distillation → Detection and dense prediction distillation
Uncertainty-Guided Chain-of-Thought for Code Generation with LLMsLLM reasoning → Reasoning for agents, planning and code
Reinforcement Learning for Robust Athletic Intelligence: Lessons from the 2nd 'AI Olympics with RealAIGym' CompetitionDeep reinforcement learning methods → RL for robot locomotion and manipulation
MAMM-Refine: A Recipe for Improving Faithfulness in Generation with Multi-Agent CollaborationLLM agents and tool use → General LLM agent frameworks and benchmarks
Do Chains-of-Thoughts of Large Language Models Suffer from Hallucinations, Cognitive Biases, or Phobias in Bayesian Reasoning?LLM reasoning → Prompting and chain-of-thought reasoning
DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement LearningLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment +1
When LLMs Meet API Documentation: Can Retrieval Augmentation Aid Code Generation Just as It Helps Developers?Retrieval-augmented generation → RAG for code
A Peek Behind the Curtain: Using Step-Around Prompt Engineering to Identify Bias and Misinformation in GenAI ModelsLLM safety and security → Safety alignment, refusal and guardrails
Partially Observable Reinforcement Learning with Memory TracesDeep reinforcement learning methods → Deep RL algorithms and representations
Detect-and-Guide: Self-regulation of Diffusion Models for Safe Text-to-Image Generation via Guideline Token OptimizationDiffusion models → Robustness, privacy and adversarial aspects +1
Optimizing Retrieval Strategies for Financial Question Answering Documents in Retrieval-Augmented Generation SystemsRetrieval-augmented generation → Legal and financial RAG
Learning Topology Actions for Power Grid Control: A Graph-Based Soft-Label Imitation Learning ApproachOffline RL and imitation learning from data → Decision transformers and sequence modeling
World Models in Artificial Intelligence: Sensing, Learning, and Reasoning Like a ChildWorld models → World models for language agents
Machine Unlearning in Hyperbolic vs. Euclidean Multimodal Contrastive Learning: Adapting Alignment Calibration to MERULLM safety and security → Machine unlearning
Object-Centric Pretraining via Target Encoder BootstrappingSynthetic data and self-improvement for LLMs → Self-improving MLLMs and synthetic data
Aligning Crowd-sourced Human Feedback for Reinforcement Learning on Code Generation by Large Language ModelsLLM agents and tool use → Software engineering coding agents +1
Increasing the Robustness of the Fine-tuned Multilingual Machine-Generated Text DetectorsLLM safety and security → Watermarking generated content and models
A Comparative Study of Human Motion Models in Reinforcement Learning Algorithms for Social Robot NavigationDeep reinforcement learning methods → RL for robot navigation and UAV control
Reasoning Effort and Problem Complexity: A Scaling Analysis in LLMsLLM reasoning → Test-time compute and efficient thinking
VIPER: Visual Perception and Explainable Reasoning for Sequential Decision-MakingLLM reasoning → Multimodal reasoning +1
StyleLoco: Generative Adversarial Distillation for Natural Humanoid Robot LocomotionDeep reinforcement learning methods → RL for robot locomotion and manipulation
LogiAgent: Automated Logical Testing for REST Systems with LLM-Based Multi-AgentsLLM agents and tool use → Software engineering coding agents
ELTEX: A Framework for Domain-Driven Synthetic Data GenerationSynthetic data and self-improvement for LLMs → LLM synthetic data generation
HAD-Gen: Human-like and Diverse Driving Behavior Modeling for Controllable Scenario GenerationEnd-to-end autonomous driving → Imitation-learning end-to-end planners +2
GraspCorrect: Robotic Grasp Correction via Vision-Language Model-Guided FeedbackMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Forensics-Bench: A Comprehensive Forgery Detection Benchmark Suite for Large Vision Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
Exploiting Diffusion Prior for Real-World Image Dehazing with Unpaired TrainingDiffusion models → Inverse problems and image restoration
Application of linear regression and quasi-Newton methods to the deep reinforcement learning in continuous action casesDeep reinforcement learning methods → Deep RL algorithms and representations
Taming Flow Matching with Unbalanced Optimal Transport into Fast PansharpeningDiffusion models → Inverse problems and image restoration
Behaviour Discovery and Attribution for Explainable Reinforcement LearningDeep reinforcement learning methods → Interpretable and logic-guided RL
Ultrasound Image-to-Video Synthesis via Latent Dynamic Diffusion ModelsDiffusion models → Medical imaging and segmentation
Neuro Symbolic Knowledge Reasoning for Procedural Video Question AnsweringLLM reasoning → Knowledge- and tool-augmented reasoning
Aligning Information Capacity Between Vision and Language via Dense-to-Sparse Feature Distillation for Image-Text MatchingKnowledge distillation → Multimodal distillation
ChatStitch: Visualizing Through Structures via Surround-View Unsupervised Deep Image Stitching with Collaborative LLM-AgentsLLM agents and tool use → Multimodal and embodied agents
MMAIF: Multi-task and Multi-degradation All-in-One for Image Fusion with Language GuidanceDiffusion models → Image generation, text-to-image and editing
UPME: An Unsupervised Peer Review Framework for Multimodal Large Language Model EvaluationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
VisNumBench: Evaluating Number Sense of Multimodal Large Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
FAVOR-Bench: A Comprehensive Benchmark for Fine-Grained Video Motion UnderstandingMultimodal LLMs / vision-language models → Video understanding with MLLMs
Derm1M: A Million-scale Vision-Language Dataset Aligned with Clinical Ontology Knowledge for DermatologyMultimodal LLMs / vision-language models → Medical vision-language models
Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact ExplanationMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
Deep Contrastive Unlearning for Language ModelsLLM safety and security → Machine unlearning
Mitigating Object Hallucinations in MLLMs via Multi-Frequency PerturbationsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
MetaLadder: Ascending Mathematical Solution Quality via Analogical-Problem Reasoning TransferLLM reasoning → Mathematical reasoning
Envisioning an AI-Enhanced Mental Health EcosystemLLM agents and tool use → Medical and scientific domain agents
Visual Autoregressive Transformers Must Use Omega(n2 d) MemoryEfficient LLM inference and serving → Fast autoregressive visual generation
Efficient Personalization of Quantized Diffusion Model without BackpropagationDiffusion models → Image generation, text-to-image and editing
Temporal-Consistent Video Restoration with Pre-trained Diffusion ModelsDiffusion models → Inverse problems and image restoration
1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching CapabilitiesDeep reinforcement learning methods → Deep RL algorithms and representations
Unlocking the Capabilities of Large Vision-Language Models for Generalizable and Explainable Deepfake DetectionMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
Think Like Human Developers: Harnessing Community Knowledge for Structured Code ReasoningLLM reasoning → Reasoning for agents, planning and code
Curiosity-Diffuser: Curiosity Guide Diffusion Models for ReliabilityDiffusion models → Diffusion and flow policies for robotics
Decompositional Neural Scene Reconstruction with Generative Diffusion PriorDiffusion models → 3D, point cloud and scene generation
Learning with Expert Abstractions for Efficient Multi-Task Continuous ControlDeep reinforcement learning methods → Deep RL algorithms and representations
Graph-Based Re-ranking in Information Retrieval and Beyond: A SurveyRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
Prompt engineering and framework: implementation to increase code reliability based guideline for LLMs
Exploring Visual Complaints through a test battery in Acquired Brain Injury Patients: A Detailed Analysis of the DiaNAH Dataset
Intelligent Orchestration of Distributed Large Foundation Model Inference at the Edge
Enhanced ECG Arrhythmia Detection Accuracy by Optimizing Divergence-Based Data Fusion
PETIMOT: A Novel Framework for Inferring Protein Motions from Sparse Data Using SE(3)-Equivariant Graph Neural Networks
ECLAIR: Enhanced Clarification for Interactive Responses in an Enterprise AI Assistant
Representative Ranking for Deliberation in the Public Sphere
An Approach to Analyze Niche Evolution in XCS Models
Seven-dimensional Trajectory Reconstruction for VAMOS++
Advancing Deep Learning through Probability Engineering: A Pragmatic Paradigm for Modern AI
ChatGPT or A Silent Everywhere Helper: A Survey of Large Language Models
Enhanced Vascular Flow Simulations in Aortic Aneurysm via Physics-Informed Neural Networks and Deep Operator Networks
AIJIM: A Scalable Model for Real-Time AI in Environmental Journalism
TripNet: Learning Large-scale High-fidelity 3D Car Aerodynamics with Triplane Networks
Investigating Cultural Dimensions and Technological Acceptance: The Adoption of Electronic Performance and Tracking Systems in Qatar's Football Sector
Reliable Radiologic Skeletal Muscle Area Assessment -- A Biomarker for Cancer Cachexia Diagnosis
Explainable AI Components for Narrative Map Extraction
A Foundational Individual Mobility Prediction Model based on Open-Source Large Language Models
Unified Enhancement of the Generalization and Robustness of Language Models via Bi-Stage Optimization

All 337