Task adaptation of Vision-Language-Action model: 1st Place Solution for the 2025 BEHAVIOR Challenge

Ilia Larchenko, Gleb Zarin, Akash Karnatak

Task adaptation of Vision-Language-Action model: 1st Place Solution for the 2025 BEHAVIOR Challenge: 4 upvotes on Hugging Face Daily Papers, #17 of 21 papers on 2025-12-15. Day-by-day upvote history.

We present a vision-action policy that won 1st place in the 2025 BEHAVIOR Challenge - a large-scale benchmark featuring 50 diverse long-horizon household tasks in photo-realistic simulation, requiring bimanual manipulation, navigation, and context-aware decision making. Building on the Pi0.5 architecture, we introduce several innovations. Our primary contribution is correlated noise for flow matching, which improves training efficiency and enables correlation-aware inpainting for smooth action sequences. We also apply learnable mixed-layer attention and System 2 stage tracking for ambiguity resolution. Training employs multi-sample flow matching to reduce variance, while inference uses action compression and challenge-specific correction rules. Our approach achieves 26% q-score across all 50 tasks on both public and private leaderboards.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.