Report
βDimension Is Free, Horizon Is Notβ listed as Best Paper runner-up
A post links to OpenReview; the paperβs title pairs evolution strategies with policy gradients for LLM fine-tuning.
TLDR
A post lists βDimension Is Free, Horizon Is Not: When Evolution Strategies Rival Policy Gradients for LLM Fine-Tuningβ as a Best Paper runner-up and links to its OpenReview page.
Combined views
1.1K
2 Sources, first seen ago
Comments