CogVLA: 指示駆動型ルーティングとスパース化による認知整合型視覚-言語-行動モデル
CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification
人間のマルチモーダル協調に着想を得て、指示に応じて視覚トークンを選択・圧縮し、行動意図に基づき不要トークンを刈り込む3段階のVLAアーキテクチャを提案。学習コストと推論遅延を大幅に削減しつつ、LIBEROベンチマークで97.4%の成功率を達成した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Wei Li, Renshan Zhang, Rui Shao, Jie He, Liqiang Nie
分類: cs.CV, cs.RO
原文アブストラクト
Recent Vision-Language-Action (VLA) models built on pre-trained Vision-Language Models (VLMs) require extensive post-training, resulting in high computational overhead that limits scalability and deployment.We propose CogVLA, a Cognition-Aligned Vision-Language-Action framework that leverages instruction-driven routing and sparsification to improve both efficiency and performance. CogVLA draws inspiration from human multimodal coordination and introduces a 3-stage progressive architecture. 1) Encoder-FiLM based Aggregation Routing (EFA-Routing) injects instruction information into the vision encoder to selectively aggregate and compress dual-stream visual tokens, forming a instruction-aware latent representation. 2) Building upon this compact visual encoding, LLM-FiLM based Pruning Routing (LFP-Routing) introduces action intent into the language model by pruning instruction-irrelevant visually grounded tokens, thereby achieving token-level sparsity. 3) To ensure that compressed perception inputs can still support accurate and coherent action generation, we introduce V-L-A Coupled Attention (CAtten), which combines causal vision-language attention with bidirectional action parallel decoding. Extensive experiments on the LIBERO benchmark and real-world robotic tasks demonstrate that CogVLA achieves state-of-the-art performance with success rates of 97.4% and 70.0%, respectively, while reducing training costs by 2.5-fold and decreasing inference latency by 2.8-fold compared to OpenVLA. CogVLA is open-sourced and publicly available at https://github.com/JiuTian-VL/CogVLA.
