conftrace_

strong student

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

weak teacher (2) negative behavior construction (1) positive behavior augmentation (1) learning rule (1) large language model (1) contrastive preference optimization (1) random feature model (1) early stopping (1) feature space (1)

Papers

MACPO: Weak-to-Strong Alignment via Multi-Agent Contrastive Preference Optimization ICLR 2025 Weak-to-Strong Generalization Even in Random Feature Networks, Provably ICML 2025