Hugging Face Journal Club: AI Research Preference Models

Describes filtering candidate experiments with a learned preference model before spending hours of GPU time evaluating them, a reusable pattern for agentic research workflows.

• AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
• eval — A repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.

• videoTeaching Tiny Models to Prove Hard Theorems | Lewis Tunstall | HF ML Club India EP1
• videoRoPE: Understanding Rotary Positional Embeddings in transformers
• videoBenchmarking LLMs at the Game Of Science (Eleusis)
• videoMoE Token Routing Explained: How Mixture of Experts Works (with Code)

• articlePredictive Human Preference: From Model Ranking to Model RoutingChip Huyen
• videoHugging Face Journal Club - DeepSeek R1Hugging Face
• podcastAjeya Cotra – Inside the OpenAI agent swarm that hacked Hugging FaceDwarkesh Patel

Checking sign-in…

Loading comments…