Skip to content
conftrace_
2025 ICML ICML 2025

Model Steering: Learning with a Reference Model Improves Generalization Bounds and Scaling Laws

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Xiyuan Wei, Ming Lin, Fanjiang Ye, Fengguang Song, Liangliang Cao, My T. Thai, Tianbao Yang

Topics

Artificial Intelligence > Core AI > Foundation Models Deep Learning > Learning Types > Contrastive Learning

Keywords

distributionally robust optimization scaling law contrastive language-image pretraining model steering clip drrho risk minimization
Download PDF