Summary of Sharp Analysis For Kl-regularized Contextual Bandits and Rlhf, by Heyang Zhao and Chenlu Ye and Quanquan Gu and Tong Zhang
Sharp Analysis for KL-Regularized Contextual Bandits and RLHFby Heyang Zhao, Chenlu Ye, Quanquan Gu, Tong…
Summary of Salsa: Soup-based Alignment Learning For Stronger Adaptation in Rlhf, by Atoosa Chegini et al.
SALSA: Soup-based Alignment Learning for Stronger Adaptation in RLHFby Atoosa Chegini, Hamid Kazemi, Iman Mirzadeh,…
Summary of Towards Reliable Alignment: Uncertainty-aware Rlhf, by Debangshu Banerjee et al.
Towards Reliable Alignment: Uncertainty-aware RLHFby Debangshu Banerjee, Aditya GopalanFirst submitted to arxiv on: 31 Oct…
Summary of Ra-pbrl: Provably Efficient Risk-aware Preference-based Reinforcement Learning, by Yujie Zhao et al.
RA-PbRL: Provably Efficient Risk-Aware Preference-Based Reinforcement Learningby Yujie Zhao, Jose Efraim Aguilar Escamill, Weyl Lu,…
Summary of Comal: a Convergent Meta-algorithm For Aligning Llms with General Preferences, by Yixin Liu et al.
COMAL: A Convergent Meta-Algorithm for Aligning LLMs with General Preferencesby Yixin Liu, Argyris Oikonomou, Weiqiang…
Summary of Vpo: Leveraging the Number Of Votes in Preference Optimization, by Jae Hyeon Cho et al.
VPO: Leveraging the Number of Votes in Preference Optimizationby Jae Hyeon Cho, Minkyung Park, Byung-Jun…
Summary of Uncertainty-penalized Direct Preference Optimization, by Sam Houliston et al.
Uncertainty-Penalized Direct Preference Optimizationby Sam Houliston, Alizée Pace, Alexander Immer, Gunnar RätschFirst submitted to arxiv…
Summary of Diff-instruct++: Training One-step Text-to-image Generator Model to Align with Human Preferences, by Weijian Luo
Diff-Instruct++: Training One-step Text-to-image Generator Model to Align with Human Preferencesby Weijian LuoFirst submitted to…
Summary of Asynchronous Rlhf: Faster and More Efficient Off-policy Rl For Language Models, by Michael Noukhovitch et al.
Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Modelsby Michael Noukhovitch, Shengyi Huang,…
Summary of Optimal Design For Reward Modeling in Rlhf, by Antoine Scheid et al.
Optimal Design for Reward Modeling in RLHFby Antoine Scheid, Etienne Boursier, Alain Durmus, Michael I.…