Reproduce “Fewer Tokens, More Self-Teaching: On-Policy Self-Distillation for Extreme Visual Token Reduction” 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
Junxian Li, Ruixuan Yang, Tianao Zhang, Tiange Xu, Weisheng Dong, Yulun Zhang
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.