Max Ryabinin
@m_ryabinin
Large-scale deep learning & research @togethercompute
Learning@home/Hivemind author (DeDLOC, SWARM, Petals)
246 Following 2.6K Followers
RL with LLMs is very unstable when training and sampling policies differ. Standard fixes (matching numerics, importance sampling) work around the problem.
We find the root cause of this instability from first principles and propose a way to directly cancel it. Score Centering is competitive and compatible with existing approaches — while simple to implement!
🧵 [1/6]
Show more
