Task adaptation of Vision-Language-Action model: 1st Place Solution for the 2025 BEHAVIOR Challenge
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914211643260928 |
|---|---|
| author | Larchenko, Ilia Zarin, Gleb Karnatak, Akash |
| author_facet | Larchenko, Ilia Zarin, Gleb Karnatak, Akash |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_06951 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Task adaptation of Vision-Language-Action model: 1st Place Solution for the 2025 BEHAVIOR Challenge Larchenko, Ilia Zarin, Gleb Karnatak, Akash Robotics Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning 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. |
| title | Task adaptation of Vision-Language-Action model: 1st Place Solution for the 2025 BEHAVIOR Challenge |
| topic | Robotics Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2512.06951 |