TacitVLA:降低具推理能力視覺語言動作模型的延遲
TacitVLA: Reasoning Vision-Language-Action Models Without Reasoning Latency
TacitVLA 是一種視覺語言動作(VLA)模型,其動作專家在當前呼叫中不讀取生成的推理文本,令動作無須等待自回歸解碼。在 RoboMME、RMBench、LIBERO 和 PhysicalAI-AV 四項基準上,其表現匹配顯式推理版本,延遲最多降低 3.4x;與同架構、未以推理訓練的版本相比,延遲相當而成功率最高提升 17.1%。
Published on Oct 13
Authors:
,
,
,
,
,
,
,
,
,
Abstract
Textual reasoning before acting has improved vision-language-action (VLA) models, but at the cost of latency: every action conditioned on the reasoning text must wait for autoregressive decoding. We show that actions do not need to wait for or condition on the generated reasoning to benefit from it, because the reasoning supervision already improves the backbone representation. We introduce TacitVLA, a reasoning VLA whose action expert never attends to the reasoning it generates for the current call. On long-horizon tasks where the reasoning text also serves as episodic memory, it can generate each entry during action execution rather than before acting. We evaluate it in a controlled study on four benchmarks spanning manipulation and autonomous driving, memory and non-memory tasks: RoboMME, RMBench, LIBERO, and PhysicalAI-AV. On all four, TacitVLA matches the performance of its explicit-reasoning counterpart at up to 3.4x lower latency, and matches the latency of the same architecture trained without reasoning at up to +17.1% success. In absolute terms, it surpasses the best previously published results on the RoboMME Counting suite (82.7% vs. 66.8%) and RMBench (77.5% vs. 56.5%), and reaches 72.9% on LIBERO-Plus and a 52.5% scene score on the public split of the PhysicalAI-AV closed-loop driving challenge. Project page: https://tacitvla.github.io.
View arXiv page View PDF Project page Add to collection
Get this paper in your agent:
hf papers read 2610.17540
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/2610.17540 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/2610.17540 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/2610.17540 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