Tag
This paper investigates the loss of model plasticity after excessive supervised fine-tuning (SFT) in the SFT-then-RL pipeline for LLMs, and proposes Rejuvenation, a method that restores plasticity via base-anchored model fusion and targeted neuron reset, consistently improving RL performance.
David Sinclair plans to test an oral epigenetic reprogramming drug, SL-100, in the XPrize competition for whole-body rejuvenation, aiming for a 10-year age reversal.