Reproduce “Retrieval Backward Attention without Additional Training: Enhance Embeddings of Large Language Models via Repetition” 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
Yifei Duan, Raphael Shang, Deng Liang, Yongqiang Cai
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.