Seth Karten
@sethkarten
Prime Agent | Continual Harness, LLM Economist | Research @PrimeIntellect | PhD @Princeton | Former CMU Waymo | NSF GRFP
가입 October 2012
690 팔로잉 중 3.2K 팬
Training VLMs to use vision-only inputs to play games is not just limited to Anthropic.
We showed this was possible using Qwen3-VL-Instruct-8b prior to Fable 5 beating pokemon firered. It is great to see a scaled up version in the latest Claude release
더 보기
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!
더 보기
