Image de couverture de livre

ContextRL: Enhancing MLLM's Knowledge Discovery Efficiency with Context-Augmented RL

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Lu, Xingyu, Wang, Jinpeng, Zhang, YiFan, Ma, Shijie, Hu, Xiao, Zhang, Tianke, fan, Haonan, Jiang, Kaiyu, Liu, Changyi, Tang, Kaiyu, Wen, Bin, Yang, Fan, Gao, Tingting, Li, Han, Yuan, Chun
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

SpatialReward: Bridging the Perception Gap in Online RL for Image Editing via Explicit Spatial Reasoning
par: Long, Yancheng, et autres
Publié: (2026)

InstructEngine: Instruction-driven Text-to-Image Alignment
par: Lu, Xingyu, et autres
Publié: (2025)

Why Distillation can Outperform Zero-RL: The Role of Flexible Reasoning
par: Hu, Xiao, et autres
Publié: (2025)

VLM as Policy: Common-Law Content Moderation Framework for Short Video Platform
par: Lu, Xingyu, et autres
Publié: (2025)

VCap: Hypergeometric Rewards for Weak-to-Strong Visual Captioning
par: Lu, Xingyu, et autres
Publié: (2026)

Joint Reward Modeling: Internalizing Chain-of-Thought for Efficient Visual Reward Models
par: Yang, Yankai, et autres
Publié: (2026)

VideoTemp-o3: Harmonizing Temporal Grounding and Video Understanding in Agentic Thinking-with-Videos
par: Liu, Wenqi, et autres
Publié: (2026)

R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning
par: Zhang, Yi-Fan, et autres
Publié: (2025)

Thyme: Think Beyond Images
par: Zhang, Yi-Fan, et autres
Publié: (2025)

Kwai-STaR: Transform LLMs into State-Transition Reasoners
par: Lu, Xingyu, et autres
Publié: (2024)

Enhancing Few-Shot Out-of-Distribution Detection with Gradient Aligned Context Optimization
par: Tong, Baoshun, et autres
Publié: (2024)

LoongRL: Reinforcement Learning for Advanced Reasoning over Long Contexts
par: Wang, Siyuan, et autres
Publié: (2025)

TimeBrush : An Intelligent Expert System for Restoring Historical Images With Temporal and Stylistic Guidance
par: Kaiyu Zhang
Publié: (2025)

UniRef-Image-Edit: Towards Scalable and Consistent Multi-Reference Image Editing
par: Wei, Hongyang, et autres
Publié: (2026)

From Reasoning to Learning: A Survey on Hypothesis Discovery and Rule Learning with Large Language Models
par: He, Kaiyu, et autres
Publié: (2025)

PEER: Unified Process-Outcome Reinforcement Learning for Structured Empathetic Reasoning
par: Wang, Yunxiao, et autres
Publié: (2025)

TaskGalaxy: Scaling Multi-modal Instruction Fine-tuning with Tens of Thousands Vision Task Types
par: Chen, Jiankang, et autres
Publié: (2025)

BalCapRL: A Balanced Framework for RL-Based MLLM Image Captioning
par: Ye, Shaokai, et autres
Publié: (2026)

Efficient Recurrent Off-Policy RL Requires a Context-Encoder-Specific Learning Rate
par: Luo, Fan-Ming, et autres
Publié: (2024)

Knowledge is Not Enough: Injecting RL Skills for Continual Adaptation
par: Tang, Pingzhi, et autres
Publié: (2026)

Data Augmentation for Continual RL via Adversarial Gradient Episodic Memory
par: Wu, Sihao, et autres
Publié: (2024)

Yes, Q-learning Helps Offline In-Context RL
par: Tarasov, Denis, et autres
Publié: (2025)

StreamRL: Scalable, Heterogeneous, and Elastic RL for LLMs with Disaggregated Stream Generation
par: Zhong, Yinmin, et autres
Publié: (2025)

RAG-RL: Advancing Retrieval-Augmented Generation via RL and Curriculum Learning
par: Huang, Jerry, et autres
Publié: (2025)

Multi-MLLM Knowledge Distillation for Out-of-Context News Detection
par: Gu, Yimeng, et autres
Publié: (2025)

Long Story Generation via Knowledge Graph and Literary Theory
par: Shi, Ge, et autres
Publié: (2025)

Prompt-Driven Domain Adaptation for End-to-End Autonomous Driving via In-Context RL
par: Khurram, Aleesha, et autres
Publié: (2025)

Towards Human-Like Manipulation through RL-Augmented Teleoperation and Mixture-of-Dexterous-Experts VLA
par: Tang, Tutian, et autres
Publié: (2026)

Creation-MMBench: Assessing Context-Aware Creative Intelligence in MLLM
par: Fang, Xinyu, et autres
Publié: (2025)

Scaling In-Context Online Learning Capability of LLMs via Cross-Episode Meta-RL
par: Lin, Xiaofeng, et autres
Publié: (2026)

CurveRL: Principled Distribution-Aware Context Reweighting for LLM Reasoning
par: Sun, Ke, et autres
Publié: (2026)

Test-time Alignment-Enhanced Adapter for Vision-Language Models
par: Tong, Baoshun, et autres
Publié: (2024)

GoLongRL: Capability-Oriented Long Context Reinforcement Learning with Multitask Alignment
par: Lv, Minxuan, et autres
Publié: (2026)

TIPSEMS ‐ VB Trial Reappraised: Infection Control, HE Prophylaxis, and Ischemic Hepatitis Considerations
par: Kaiyu Bian, et autres
Publié: (2025)

Enhancing RAG Efficiency with Adaptive Context Compression
par: Guo, Shuyu, et autres
Publié: (2025)

Rethinking Oversaturation in Classifier-Free Guidance via Low Frequency
par: Song, Kaiyu, et autres
Publié: (2025)

Leveraging Previous Steps: A Training-free Fast Solver for Flow Diffusion
par: Song, Kaiyu, et autres
Publié: (2024)

Improving Training-free Conditional Diffusion Model via Fisher Information
par: Song, Kaiyu, et autres
Publié: (2024)

A Navigation Framework Utilizing Vision-Language Models
par: Duan, Yicheng, et autres
Publié: (2025)

Epistemic Dissemination as Dialogue: A Case of Museum‐Visitor Stance Negotiation Through Multilingualism
par: Kaiyu Qin, et autres
Publié: (2025)