arXiv AI June 12, 2026 By Sangkyu Lee, Seohyeon Park, Tackgeun You, Avi Caciularu, Idan Szpektor, Hwasup Lim, Youngjae Yu

Real-Time Execution with Autoregressive Policies

Read the original on arXiv AI →

arXiv:2606. 13355v1 Announce Type: cross Abstract: Real-time execution, enabled by asynchronous inference that ensures both smooth action trajectories and fast reactivity, is critical for realistic deployments of large-scale Vision-Language-Action models.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Jun 9

C$^3$ache: Accelerating World Action Models with Cross Inference Chunk Cache

arXiv:2606. 08962v1 Announce Type: new Abstract: World Action Models (WAMs) generalize better than standard Vision-Language-Action (VLA) policies to novel motions and environments, because a video-modeling objective lets them learn from abundant unlabeled video rather than scarce labeled robot demonstrations.

By Weisen Zhao, Lam Nguyen, Zhicong Lu, Yuzhang Shang

robotics multimodal benchmarks

arXiv Machine Learning

Jul 8

Training-Free Acceleration for Vision-Language-Action Models with Action Caching and Refinement

arXiv:2607. 06370v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have emerged as a promising approach for generalizable robotic manipulations.

By Ryuji Oi, Hikari Otsuka, Kosuke Matsushima, Yuki Ichikawa, Masato Motomura, Tatsuya Kaneko, Daichi Fujiki

diffusion robotics efficiency multimodal

arXiv AI

Sep 15

TIDAL: Temporally Interleaved Diffusion and Action Loop for High-Frequency VLA Control

arXiv:2601.14945v3 Announce Type: replace-cross Abstract: Large-scale Vision-Language-Action (VLA) models offer semantic generalization but suffer from high inference latency because they adopt a low...

By Yuteng Sun, Haoran Wang, Ruofei Bai, Zhengguo Li, Jun Li, Meng Yee Michael Chuah, Wei Yun Yau

rag diffusion robotics efficiency multimodal

arXiv Machine Learning

Aug 4

ActionCache: Training-Free Acceleration for Vision-Language-Action Models with Action Caching and Refinement

arXiv:2607. 06370v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have emerged as a promising approach for generalizable robotic manipulations.

By Ryuji Oi, Hikari Otsuka, Kosuke Matsushima, Yuki Ichikawa, Masato Motomura, Tatsuya Kaneko, Daichi Fujiki

robotics efficiency multimodal

Hugging Face Trending Papers

Jul 7

Training-Free Acceleration for Vision-Language-Action Models with Action Caching and Refinement

Vision-Language-Action (VLA) models have emerged as a promising approach for generalizable robotic manipulations. In particular, flow matching-based VLA models have shown remarkable success due to their capability to generate precise and smooth action sequences and capture multimodal distributions.

diffusion robotics efficiency multimodal

arXiv Computer Vision

Sep 1

BLUE: Toward Better Language Use in Efficient Vision-Language-Action Models for Autonomous Driving

arXiv:2606.08684v2 Announce Type: replace Abstract: We present BLUE, a minimal method for better language use in vision-language-action (VLA) models for autonomous driving (AD). Through extensive ana...

By George Ling, Lijin Yang, Hao Yang, Zhongzhan Huang

agents robotics multimodal benchmarks

One email a morning, machine-written

Related stories

C$^3$ache: Accelerating World Action Models with Cross Inference Chunk Cache

Training-Free Acceleration for Vision-Language-Action Models with Action Caching and Refinement

TIDAL: Temporally Interleaved Diffusion and Action Loop for High-Frequency VLA Control

ActionCache: Training-Free Acceleration for Vision-Language-Action Models with Action Caching and Refinement

Training-Free Acceleration for Vision-Language-Action Models with Action Caching and Refinement

BLUE: Toward Better Language Use in Efficient Vision-Language-Action Models for Autonomous Driving