This is a heavily interactive web application, and JavaScript is required. Simple HTML interfaces are possible, but that is not what this is.
Post
Zaid Khan
codezakh.bsky.social
did:plc:pjftayddske5he65o3vt6yaz
LMs can self-improve at inferring EFAs with execution feedback!
We self-train Llama-3.1-8B-Instruct with rejection finetuning using our derived unit tests as a verifiable reward signal and see substantial improvements in the model’s ability to infer EFAs, especially on harder problems.
2025-04-15T19:37:56.648Z