metadata
datasets:
- behavior-1k/2025-challenge-demos
This is the model weights of Team Comet for the 2025 BEHAVIOR Challenge. Our submission achieved a Q-score of 0.2514, securing 2nd place overall and finishing just behind the winning team by a narrow margin—highlighting both the strong competitiveness of our approach and the effectiveness of our end-to-end VLA training strategy.
Please refer to this repository for detailed usage. It provides a unified framework for pre-training, post-training, data generation and evaluation of π0.5 (Pi05) models on BEHAVIOR-1K.
The tech report is available now.