Imagen de Portada

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

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	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
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Artificial Intelligence Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

SpatialReward: Bridging the Perception Gap in Online RL for Image Editing via Explicit Spatial Reasoning
por: Long, Yancheng, et al.
Publicado: (2026)

InstructEngine: Instruction-driven Text-to-Image Alignment
por: Lu, Xingyu, et al.
Publicado: (2025)

Why Distillation can Outperform Zero-RL: The Role of Flexible Reasoning
por: Hu, Xiao, et al.
Publicado: (2025)

VLM as Policy: Common-Law Content Moderation Framework for Short Video Platform
por: Lu, Xingyu, et al.
Publicado: (2025)

VCap: Hypergeometric Rewards for Weak-to-Strong Visual Captioning
por: Lu, Xingyu, et al.
Publicado: (2026)

Joint Reward Modeling: Internalizing Chain-of-Thought for Efficient Visual Reward Models
por: Yang, Yankai, et al.
Publicado: (2026)

VideoTemp-o3: Harmonizing Temporal Grounding and Video Understanding in Agentic Thinking-with-Videos
por: Liu, Wenqi, et al.
Publicado: (2026)

R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning
por: Zhang, Yi-Fan, et al.
Publicado: (2025)

Thyme: Think Beyond Images
por: Zhang, Yi-Fan, et al.
Publicado: (2025)

Kwai-STaR: Transform LLMs into State-Transition Reasoners
por: Lu, Xingyu, et al.
Publicado: (2024)

Enhancing Few-Shot Out-of-Distribution Detection with Gradient Aligned Context Optimization
por: Tong, Baoshun, et al.
Publicado: (2024)

LoongRL: Reinforcement Learning for Advanced Reasoning over Long Contexts
por: Wang, Siyuan, et al.
Publicado: (2025)

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

UniRef-Image-Edit: Towards Scalable and Consistent Multi-Reference Image Editing
por: Wei, Hongyang, et al.
Publicado: (2026)

From Reasoning to Learning: A Survey on Hypothesis Discovery and Rule Learning with Large Language Models
por: He, Kaiyu, et al.
Publicado: (2025)

PEER: Unified Process-Outcome Reinforcement Learning for Structured Empathetic Reasoning
por: Wang, Yunxiao, et al.
Publicado: (2025)

TaskGalaxy: Scaling Multi-modal Instruction Fine-tuning with Tens of Thousands Vision Task Types
por: Chen, Jiankang, et al.
Publicado: (2025)

BalCapRL: A Balanced Framework for RL-Based MLLM Image Captioning
por: Ye, Shaokai, et al.
Publicado: (2026)

Efficient Recurrent Off-Policy RL Requires a Context-Encoder-Specific Learning Rate
por: Luo, Fan-Ming, et al.
Publicado: (2024)

Knowledge is Not Enough: Injecting RL Skills for Continual Adaptation
por: Tang, Pingzhi, et al.
Publicado: (2026)

Data Augmentation for Continual RL via Adversarial Gradient Episodic Memory
por: Wu, Sihao, et al.
Publicado: (2024)

Yes, Q-learning Helps Offline In-Context RL
por: Tarasov, Denis, et al.
Publicado: (2025)

StreamRL: Scalable, Heterogeneous, and Elastic RL for LLMs with Disaggregated Stream Generation
por: Zhong, Yinmin, et al.
Publicado: (2025)

RAG-RL: Advancing Retrieval-Augmented Generation via RL and Curriculum Learning
por: Huang, Jerry, et al.
Publicado: (2025)

Multi-MLLM Knowledge Distillation for Out-of-Context News Detection
por: Gu, Yimeng, et al.
Publicado: (2025)

Long Story Generation via Knowledge Graph and Literary Theory
por: Shi, Ge, et al.
Publicado: (2025)

Prompt-Driven Domain Adaptation for End-to-End Autonomous Driving via In-Context RL
por: Khurram, Aleesha, et al.
Publicado: (2025)

Towards Human-Like Manipulation through RL-Augmented Teleoperation and Mixture-of-Dexterous-Experts VLA
por: Tang, Tutian, et al.
Publicado: (2026)

Creation-MMBench: Assessing Context-Aware Creative Intelligence in MLLM
por: Fang, Xinyu, et al.
Publicado: (2025)

Scaling In-Context Online Learning Capability of LLMs via Cross-Episode Meta-RL
por: Lin, Xiaofeng, et al.
Publicado: (2026)

CurveRL: Principled Distribution-Aware Context Reweighting for LLM Reasoning
por: Sun, Ke, et al.
Publicado: (2026)

Test-time Alignment-Enhanced Adapter for Vision-Language Models
por: Tong, Baoshun, et al.
Publicado: (2024)

GoLongRL: Capability-Oriented Long Context Reinforcement Learning with Multitask Alignment
por: Lv, Minxuan, et al.
Publicado: (2026)

TIPSEMS ‐ VB Trial Reappraised: Infection Control, HE Prophylaxis, and Ischemic Hepatitis Considerations
por: Kaiyu Bian, et al.
Publicado: (2025)

Enhancing RAG Efficiency with Adaptive Context Compression
por: Guo, Shuyu, et al.
Publicado: (2025)

Rethinking Oversaturation in Classifier-Free Guidance via Low Frequency
por: Song, Kaiyu, et al.
Publicado: (2025)

Leveraging Previous Steps: A Training-free Fast Solver for Flow Diffusion
por: Song, Kaiyu, et al.
Publicado: (2024)

Improving Training-free Conditional Diffusion Model via Fisher Information
por: Song, Kaiyu, et al.
Publicado: (2024)

A Navigation Framework Utilizing Vision-Language Models
por: Duan, Yicheng, et al.
Publicado: (2025)

Epistemic Dissemination as Dialogue: A Case of Museum‐Visitor Stance Negotiation Through Multilingualism
por: Kaiyu Qin, et al.
Publicado: (2025)