Yihe Deng (@yihe__deng) 's Twitter Profile
Yihe Deng

@yihe__deng

CS PhD candidate @UCLA, Student Researcher @GoogleAI | Prev. Research Intern @MSFTResearch @AWS | LLM post-training, synthetic data

ID: 1462223072203722756

linkhttps://yihe-deng.notion.site/Yihe-Deng-167ab2d2c1fb80b3a76dfb120f716c84 calendar_today21-11-2021 00:55:36

175 Tweet

2,2K Followers

1,1K Following

Yihe Deng (@yihe__deng) 's Twitter Profile Photo
Yihe Deng
@yihe__deng

a month ago

🙌 We've released the full version of our paper, OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles Our OpenVLThinker-v1.2 is trained through three lightweight SFT → RL cycles, where SFT first “highlights” reasoning behaviors and RL then explores and

🙌 We've released the full version of our paper, OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles Our OpenVLThinker-v1.2 is trained through three lightweight SFT → RL cycles, where SFT first “highlights” reasoning behaviors and RL then explores and