1
Reward-free Alignment for Conflicting Objectives
无需奖励信号，仅靠目标冲突就能实现高效对齐，ICML 2026 Oral 论文揭秘全新思路。
arXiv:2602.02495v3 Announce Type: replace-cross Abstract: Direct alignment methods are increasingly used to align large language models (LLMs) with hu…