Reproduce “Earlier Tokens Contribute More: Learning Direct Preference Optimization From Temporal Decay Perspective” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Ruichen Shao, Bei Li, Gangao Liu, Yang Chen, Xiang Zhou, Jingang Wang, Xunliang Cai, Peng Li
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.