Reproduce “SPAR: Structural Pruning and Action Recovery 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

Shenli Zheng, Zhou Fang, Yuan Du, Yijiang Liu, Li Du

SPAR learns separate hidden- and FFN-width masks, physically removes channels, and applies simulated reinforcement learning. On π₀.₅, the LLM shrinks from 2.34B to 0.09B parameters. RL raises the 10%/10% model’s four-suite LIBERO mean from 84.55% to 93.45%, still 4.25 points below the unpruned RL baseline.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.