RLHF | Yang Cai http://www.cs.yale.edu/homes/cai/tag/rlhf/ RLHF Wowchemy (https://wowchemy.com)en-usSun, 04 Jan 2026 18:39:04 -0400 http://www.cs.yale.edu/homes/cai/media/icon_hu2863fb787e1951439c40d39e27eaa50a_1119_512x512_fill_lanczos_center_3.png RLHF http://www.cs.yale.edu/homes/cai/tag/rlhf/ COMAL: A Convergent Meta-Algorithm for Aligning LLMs with General Preferences http://www.cs.yale.edu/homes/cai/publication/cai-comal-2026/ Sun, 04 Jan 2026 18:39:04 -0400 http://www.cs.yale.edu/homes/cai/publication/cai-comal-2026/