ACE-Brain-0.6：身体性基盤モデルのための空間グラウンディングのスケーリング
ACE-Brain-0.6: Scaling Spatial Grounding for Physical Foundation Models
ロボット操作記録と多様な視覚データを統合したデータパイプラインで約150万件の検証可能なグラウンディング教師信号を作り、Qwen3.5-9Bを微調整して空間知覚を強化したモデル。7つの公開ベンチマーク中4つでGPT-6 Astraを上回った。
著者: Yinhe Wang, Tao Tao, Zexin He, Shuang Luo, Wei Mao, Yao Mu, Feng Pan, Hanming Deng, Lewei Lu, Zhi Hou, Xingang Pan, Dahua Lin, Dacheng Tao, Xiaogang Wang
分類: cs.RO
原文アブストラクト
General-purpose multimodal models, including GPT-6 Astra and Claude Opus 5.5, demonstrate broad capabilities in embodied manipulation. Our analysis indicates that this generality is accompanied by strong spatial perception, as Astra can determine where to interact with task-relevant entities amid visual distractors. Because spatial perception connects high-level reasoning to the physical scene, we investigate scaling visual grounding to strengthen the perceptual foundation of general embodied operation. We develop a unified data pipeline that combines robot manipulation recordings with complementary visual data from diverse sources. After automatically annotating the robot recordings, the pipeline converts the collected data into verifiable grounding supervision. Fine-tuning Qwen3.5-9B on approximately 1.5 million samples produced by this pipeline yields ACE-Brain-0.6. The model outperforms GPT-6 Astra on four of seven public grounding benchmarks, with an overall average score of 75.41 compared with Astra's 73.68. Under a fixed Qwen3.5-9B fine-tuning setup, aggregate grounding performance improves steadily as successive data releases expand the training collection to cover a broader range of grounding scenarios. These results show that scaling verifiable grounding supervision from diverse sources can strengthen the spatial perception of an open 9B model for general embodied operation.