Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study

no code implementations • 16 Apr 2024 • Shusheng Xu, Wei Fu, Jiaxuan Gao, Wenjie Ye, Weilin Liu, Zhiyu Mei, Guangju Wang, Chao Yu, Yi Wu

However, in academic benchmarks, state-of-the-art results are often achieved via reward-free methods, such as Direct Preference Optimization (DPO).

Code Generation

Towards Blockchain-Assisted Privacy-Aware Data Sharing For Edge Intelligence: A Smart Healthcare Perspective

no code implementations • 29 Jun 2023 • Youyang Qu, Lichuan Ma, Wenjie Ye, Xuemeng Zhai, Shui Yu, Yunfeng Li, David Smith

Linkage attack is a type of dominant attack in the privacy domain, which can leverage various data sources for private data mining.

What Happened 3 Seconds Ago? Inferring the Past with Thermal Imaging

1 code implementation • CVPR 2023 • Zitian Tang, Wenjie Ye, Wei-Chiu Ma, Hang Zhao

Inferring past human motion from RGB images is challenging due to the inherent uncertainty of the prediction problem.

Human-Object Interaction Detection Pose Estimation