isospectral

Tag

Cards List
#isospectral

ISO: An RLVR-Native Optimization Stack

Hugging Face Daily Papers · 2d ago Cached

This paper studies the optimization layer for reinforcement learning with verifiable rewards (RLVR), proposing Isospectral Optimization (ISO) — a fixed-spectrum framework that reuses base model weight spectra while optimizing input/output singular frames. ISO-Merger and ISO-AdamW achieve strong performance with fewer training steps on reasoning and coding tasks.

0 favorites 0 likes
← Back to home

Submit Feedback