We have 4 of 15 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
AIM-ZO is proposed, a ZO fine-tuning method based on Activation-Informed Subspace Maintenance that uses forward activations as local directional information and continuously integrates them into a broad, evolving subspace over training.
SkillEvoReg, a general regularization framework for skill evolution inspired by anti-overfitting techniques in neural-network training, is introduced and suggested that explicit regularization is a useful complement to increasingly capable skill updaters.
This work decomposes each operator's utility into a coverage effect on evidence omitted by retention and a signed replacement effect on raw evidence that already fits, which explains why the preferred action changes with relative budget pressure.
These findings position ES as a distinct reasoning post-training paradigm rather than a less effective, memory-efficient alternative to GRPO, and study how hyperparameter design affects the effectiveness of ES, demonstrating that ES requires a smaller population size in a larger LLM.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
