Summary of Simpo: Simple Preference Optimization with a Reference-free Reward, by Yu Meng et al.
SimPO: Simple Preference Optimization with a Reference-Free Rewardby Yu Meng, Mengzhou Xia, Danqi ChenFirst submitted…
Summary of Lire: Listwise Reward Enhancement For Preference Alignment, by Mingye Zhu et al.
LIRE: listwise reward enhancement for preference alignmentby Mingye Zhu, Yi Liu, Lei Zhang, Junbo Guo,…
Summary of A Unified Linear Programming Framework For Offline Reward Learning From Human Demonstrations and Feedback, by Kihyun Kim et al.
A Unified Linear Programming Framework for Offline Reward Learning from Human Demonstrations and Feedbackby Kihyun…
Summary of Openrlhf: An Easy-to-use, Scalable and High-performance Rlhf Framework, by Jian Hu et al.
OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Frameworkby Jian Hu, Xibin Wu, Zilin Zhu, Xianyu,…
Summary of The Power Of Active Multi-task Learning in Reinforcement Learning From Human Feedback, by Ruitao Chen et al.
The Power of Active Multi-Task Learning in Reinforcement Learning from Human Feedbackby Ruitao Chen, Liwei…
Summary of Understanding the Performance Gap Between Online and Offline Alignment Algorithms, by Yunhao Tang et al.
Understanding the performance gap between online and offline alignment algorithmsby Yunhao Tang, Daniel Zhaohan Guo,…
Summary of Rlhf Workflow: From Reward Modeling to Online Rlhf, by Hanze Dong et al.
RLHF Workflow: From Reward Modeling to Online RLHFby Hanze Dong, Wei Xiong, Bo Pang, Haoxiang…
Summary of Open Challenges and Opportunities in Federated Foundation Models Towards Biomedical Healthcare, by Xingyu Li et al.
Open Challenges and Opportunities in Federated Foundation Models Towards Biomedical Healthcareby Xingyu Li, Lu Peng,…
Summary of Metarm: Shifted Distributions Alignment Via Meta-learning, by Shihan Dou et al.
MetaRM: Shifted Distributions Alignment via Meta-Learningby Shihan Dou, Yan Liu, Enyu Zhou, Tianlong Li, Haoxiang…
Summary of Dpo Meets Ppo: Reinforced Token Optimization For Rlhf, by Han Zhong et al.
DPO Meets PPO: Reinforced Token Optimization for RLHFby Han Zhong, Zikang Shan, Guhao Feng, Wei…