Chengshuai Shi(@chengshuai_shi):Wondering how VLMs can be trained to play games using only visual inputs, like Anthropic’s newly released Claude Fable 5? Check out our recent work, Odysseus: https://t.co/CQW37Av7cm In Odysseus, we train VLMs to play games directly from visual inputs, using Super Mario Land as a testbed, and scale RL to improve their long-horizon decision-making capabilities. Excited to see more exploration in this direction!

Chengshuai Shi

@chengshuai_shi

Postdoc @PrincetonPLI; Previous @TechAtBloomberg @uvaece; Working on intelligent decision-making; Opinions are my own.

参加 August 2019

726 フォロー中 354 ファン

Chengshuai Shi@chengshuai_shi

2026.06.09 21:24

Wondering how VLMs can be trained to play games using only visual inputs, like Anthropic’s newly released Claude Fable 5? Check out our recent work, Odysseus: In Odysseus, we train VLMs to play games directly from visual inputs, using Super Mario Land as a testbed, and scale RL to improve their long-horizon decision-making capabilities. Excited to see more exploration in this direction!