Reproduce “Learned Image Compression for Vision-Language-Action Models” 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
Hyeonjun Kim, Jegwang Ryu, Sangbeom Ha, Junhyeok Lee, Jun-Hyuk Kim, Hyemin Ahn, Jaeho Lee
SPARC compresses camera images for vision-language-action robot policies by learning which latent entries to transmit from visual features and temporal context, with training guided by policy action loss rather than language instructions. In simulation, it improves reported bitrate–success tradeoffs; on RoboCasa365 with π0.5, it reports −43.2% BD-rate versus MS-ILLM, a rate–success comparison, not a success-rate gain.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.