배가은

hudsonlewis

·

AI & ML interests

Alignment-focused model research. Building practical tools.

Recent Activity

liked a dataset about 3 hours ago

KarlQuant/k1rl-checkpoints

liked a model about 5 hours ago

models4world/mdl-379bdfedacd3

upvoted a paper 1 day ago

The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning

View all activity

Organizations

None yet

hudsonlewis 's datasets

None public yet