MambaAct:為 Flow-Matching 視覺語言動作模型打造高效 Mamba 動作專家
MambaAct: Efficient Mamba Action Experts for Flow-Matching Vision-Language-Action Models
MambaAct 以精簡的 Mamba 動作專家和上下文壓縮器,取代 Flow-Matching VLA 策略中的 Transformer 動作專家,以降低推理延遲並提升機械人操作成功率。
Published on Oct 16
Authors:
,
,
Abstract
MambaAct replaces the transformer action expert in flow-matching VLA policies with a compact Mamba-based expert and a context compressor to cut inference latency while improving robotic manipulation success.
Vision-language-action (VLA) models have shown strong promise for generalist robotic manipulation, but their inference cost remains a major bottleneck for real-time control. This limitation is especially pronounced in flow-matching VLAs such as π_{0.5}, where the action expert is evaluated repeatedly during iterative denoising. We introduce MambaAct, an efficient Mamba action expert for flow-matching VLA policies. MambaAct retains the pretrained visual-language prefix encoder of π_{0.5}, while replacing its transformer-based action expert with a compact Mamba-based action expert. Within this expert, Mamba serves as the action mixer that models dependencies across the noisy continuous-action sequence. To preserve visual-language conditioning without repeated token-level cross-attention, MambaAct uses a lightweight Context Compressor to map Vision-language model (VLM) prefix tokens into a compact conditioning signal that gates and modulates each Mamba action block. MambaAct uses a 10times smaller action expert and reduces flow-matching denoising latency by 64.8% on LIBERO and 58.8% in real-world deployment, while improving mean LIBERO success by 1.08 percentage points across three independent fine-tuning seeds and maintaining gains on LIBERO-Plus and real-world benchmarks. Our code and model weights are publicly available at https://github.com/giakhuyendihoc/MambaAct.
View arXiv page View PDF GitHub Add to collection
Get this paper in your agent:
hf papers read 2610.22951
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2610.22951 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2610.22951 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.22951 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co