Reproduce “Latent Telepathy: Multi-Robot Communication with Self-Supervised Perceptual Latents” 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
Howard Wang, Han Zheng, Cathy Wu
The authors introduce Latent Telepathy, which sends a frozen shared visual encoder’s 64-value latent plus a relative-position anchor and trains a receiver to use it from team reward. In a simulated corridor task, route choices were correct in 99.7% ± 0.6 percentage points of the last 500 episodes across five seeds. The scout was stationary, and a frozen executor handled movement.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.