Image de couverture de livre

R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yang, Qi, Ni, Bolin, Xiang, Shiming, Hu, Han, Peng, Houwen, Jiang, Jie
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Beyond Sequential Distance: Inter-Modal Distance Invariant Position Encoding
par: Chen, Lin, et autres
Publié: (2026)

VideoRFT: Incentivizing Video Reasoning Capability in MLLMs via Reinforced Fine-Tuning
par: Wang, Qi, et autres
Publié: (2025)

Bee: A High-Quality Corpus and Full-Stack Suite to Unlock Advanced Fully Open MLLMs
par: Zhang, Yi, et autres
Publié: (2025)

Xwin-LM: Strong and Scalable Alignment Practice for LLMs
par: Ni, Bolin, et autres
Publié: (2024)

R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
par: Song, Huatong, et autres
Publié: (2025)

Common 7B Language Models Already Possess Strong Math Capabilities
par: Li, Chen, et autres
Publié: (2024)

Setting Up General Purpose CD-ROM Workstations.
par: Bolin, Robert L.
Publié: (1991)

Context Reasoner: Incentivizing Reasoning Capability for Contextualized Privacy and Safety Compliance via Reinforcement Learning
par: Hu, Wenbin, et autres
Publié: (2025)

SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Reward
par: Fan, Kaixuan, et autres
Publié: (2025)

R-Log: Incentivizing Log Analysis Capability in LLMs via Reasoning-based Reinforcement Learning
par: Liu, Yilun, et autres
Publié: (2025)

Saliency-R1: Incentivizing Unified Saliency Reasoning Capability in MLLM with Confidence-Guided Reinforcement Learning
par: Li, Long, et autres
Publié: (2025)

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
par: DeepSeek-AI, et autres
Publié: (2025)

Enhancing Visual Continual Learning with Language-Guided Supervision
par: Ni, Bolin, et autres
Publié: (2024)

Think 360°: Evaluating the Width-centric Reasoning Capability of MLLMs Beyond Depth
par: Chen, Mingrui, et autres
Publié: (2026)

Defying Imbalanced Forgetting in Class Incremental Learning
par: Xu, Shixiong, et autres
Publié: (2024)

SpaceR: Reinforcing MLLMs in Video Spatial Reasoning
par: Ouyang, Kun, et autres
Publié: (2025)

Thinking with Deltas: Incentivizing Reinforcement Learning via Differential Visual Reasoning Policy
par: Gao, Shujian, et autres
Publié: (2026)

Video-R1: Reinforcing Video Reasoning in MLLMs
par: Feng, Kaituo, et autres
Publié: (2025)

IF-Bench: Benchmarking and Enhancing MLLMs for Infrared Images with Generative Visual Prompting
par: Zhang, Tao, et autres
Publié: (2025)

Urban-R1: Reinforced MLLMs Mitigate Geospatial Biases for Urban General Intelligence
par: Wang, Qiongyan, et autres
Publié: (2025)

DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning
par: Zheng, Ziwei, et autres
Publié: (2025)

Perception-R1: Advancing Multimodal Reasoning Capabilities of MLLMs via Visual Perception Reward
par: Xiao, Tong, et autres
Publié: (2025)

Incentivizing Tool-augmented Thinking with Images for Medical Image Analysis
par: Jiang, Yankai, et autres
Publié: (2025)

Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models
par: Huang, Wenxuan, et autres
Publié: (2025)

VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice
par: Liu, Shuming, et autres
Publié: (2026)

MM-THEBench: Do Reasoning MLLMs Think Reasonably?
par: Huang, Zhidian, et autres
Publié: (2026)

DINO-R1: Incentivizing Reasoning Capability in Vision Foundation Models
par: Pan, Chenbin, et autres
Publié: (2025)

Touch-R1: Reinforcing Touch Reasoning in MLLMs
par: Lai, Yingxin, et autres
Publié: (2026)

Policy Split: Incentivizing Dual-Mode Exploration in LLM Reinforcement with Dual-Mode Entropy Regularization
par: Yao, Jiashu, et autres
Publié: (2026)

GRIT: Teaching MLLMs to Think with Images
par: Fan, Yue, et autres
Publié: (2025)

Incentivizing Cardiologist-Like Reasoning in MLLMs for Interpretable Echocardiographic Diagnosis
par: Qin, Yi, et autres
Publié: (2026)

MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning
par: Pan, Jiazhen, et autres
Publié: (2025)

WorkForceAgent-R1: Incentivizing Reasoning Capability in LLM-based Web Agents via Reinforcement Learning
par: Zhuang, Yuchen, et autres
Publié: (2025)

J1: Incentivizing Thinking in LLM-as-a-Judge via Reinforcement Learning
par: Whitehouse, Chenxi, et autres
Publié: (2025)

rSIM: Incentivizing Reasoning Capabilities of LLMs via Reinforced Strategy Injection
par: Chen, Sijia, et autres
Publié: (2025)

Timelike entanglement entropy in dS$_3$/CFT$_2$
par: Jiang, Xin, et autres
Publié: (2023)

How Einstein's Equation Emerges From CFT$_2$
par: Jiang, Xin, et autres
Publié: (2024)

Timelike entanglement entropy and $T\bar{T}$ deformation
par: Jiang, Xin, et autres
Publié: (2023)

Realization of "ER=EPR"
par: Jiang, Xin, et autres
Publié: (2024)

An alternative to purification in CFT
par: Jiang, Xin, et autres
Publié: (2024)