Chengshuai Shi
@chengshuai_shi
Postdoc @PrincetonPLI; Previous @TechAtBloomberg @uvaece; Working on intelligent decision-making; Opinions are my own.
726 Following 354 Followers
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!
Show more
