1 citations · 1 across the 5 of their papers we have counts for
3 papers · 1 filter
torchtune: PyTorch native post-training library
Mark Obozov, Maxime Griot, Joseph Cummings +8
Modern LLMs typically require multistage training pipelines to achieve strong downstream performance, with post-training serving as the main interface for adapting open-weight mode…
Teaching Models to Teach Themselves: Reasoning at the Edge of Learnability
Shobhita Sundaram, John Quan, Ariel Kwiatkowski +3
RL methods for scaling large reasoning models stall on datasets with low initial success rates, and thus little training signal. We investigate a fundamental question: Can a pretra…
PILAF: Optimal Human Preference Sampling for Reward Modeling
Yunzhen Feng, Ariel Kwiatkowski, Kunhao Zheng +2
As large language models increasingly drive real-world applications, aligning them with human values becomes paramount. Reinforcement Learning from Human Feedback (RLHF) has emerge…