Syn-GRPO: Self-evolving Data Synthesis for MLLM Perception Reasoning

Read full text
Authors: Qihan Huang, Haofei Zhang, Rong Wei, Yi Wang, Rui Tang, Mingli Song, Jie Song
Cited by: 0
References: 14

Fields of Study & Subjects

Reinforcement Learning in Robotics Multimodal Machine Learning Applications Advanced Neural Network Applications

Publication details

Journal / source
Lecture notes in computer science
Pages
240–257
Publication date
1 January 2026
Language
EN