Fetching the paper…

Reading the bibliography…

2025

VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inference

Tang, Jiaming, Sun, Yufei, Zhao, Yilong et al.

Original
PDF
Post on X

Understand

Vision-Language-Action models (VLAs) are becoming increasingly capable across diverse robotic tasks.

However, these models are typically deployed under synchronous inference, where the robot waits for model inference to complete before acting, and cannot perceive or respond to environmental changes during action execution.
This not only introduces noticeable action stalls, but also significantly increases reaction latency, fundamentally limiting the applicability of VLAs to dynamic, real-time tasks.
Asynchronous inference offers a promising solution to achieve continuous and low-latency control by enabling robots to execute actions and perform inference simultaneously.

VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inference · Around

Built on

I. O. Tolstikhin, N. Houlsby, A. Kolesnikov, L. Beyer, X. Zhai, T. Unterthiner, J. Yung, A. Steiner, D. Keysers, J. Uszkoreit et al. , “Mlp-mixer: An all-mlp architecture for vision,” Advances in neural information processing systems , vol. 34, pp. 24 261–24 272, 2021
2021
Earlier work this paper cites.
T. Z. Zhao, V. Kumar, S. Levine, and C. Finn, “Learning fine-grained bimanual manipulation with low-cost hardware,” arXiv preprint arXiv:2304.13705 , 2023
Original
2023
Earlier work this paper cites.
B. Liu, Y. Zhu, C. Gao, Y. Feng, Q. Liu, Y. Zhu, and P. Stone, “Libero: Benchmarking knowledge transfer for lifelong robot learning,” arXiv preprint arXiv:2306.03310 , 2023
Original
2023
Earlier work this paper cites.
K. Black, N. Brown, D. Driess, A. Esmail, M. Equi, C. Finn, N. Fusai, L. Groom, K. Hausman, B. Ichter et al. , “ π 0 \pi_{0} : A vision-language-action flow model for general robot control,” arXiv preprint arXiv:2410.24164 , 2024
Original
2024
Earlier work this paper cites.
M. Kim, K. Pertsch, S. Karamcheti, T. Xiao, A. Balakrishna, S. Nair, R. Rafailov, E. Foster, G. Lam, P. Sanketi, Q. Vuong, T. Kollar, B. Burchfiel, R. Tedrake, D. Sadigh, S. Levine, P. Liang, and C. Finn, “Openvla: An open-source vision-language-action model,” arXiv preprint arXiv:2406.09246 , 2024
Original
2024
Earlier work this paper cites.
R. Cadene, S. Alibert, A. Soare, Q. Gallouedec, A. Zouitine, S. Palma, P. Kooijmans, M. Aractingi, M. Shukor, D. Aubakirova, M. Russi, F. Capuano, C. Pascal, J. Choghari, J. Moss, and T. Wolf, “Lerobot: State-of-the-art machine learning for real-world robotics in pytorch,” https://github.com/huggingface/lerobot , 2024
2024
Earlier work this paper cites.
P. Intelligence, K. Black, N. Brown, J. Darpinian, K. Dhabalia, D. Driess, A. Esmail, M. Equi, C. Finn, N. Fusai et al. , “ π 0.5 \pi_{0.5} : a vision-language-action model with open-world generalization,” arXiv preprint arXiv:2504.16054 , 2025
Original
2025
Earlier work this paper cites.
J. Bjorck, F. Castañeda, N. Cherniadev, X. Da, R. Ding, L. Fan, Y. Fang, D. Fox, F. Hu, S. Huang et al. , “GR00T N1: An open foundation model for generalist humanoid robots,” arXiv preprint arXiv:2503.14734 , 2025
Original
2025
Earlier work this paper cites.

Similar

K. Black, M. Y. Galliker, and S. Levine, “Real-time execution of action chunking flow policies,” arXiv preprint arXiv:2506.07339 , 2025
Original
2025
Cited alongside, same era.
M. Shukor, D. Aubakirova, F. Capuano, P. Kooijmans, S. Palma, A. Zouitine, M. Aractingi, C. Pascal, M. Russi, A. Marafioti et al. , “Smolvla: A vision-language-action model for affordable and efficient robotics,” arXiv preprint arXiv:2506.01844 , 2025
Original
2025
Cited alongside, same era.
K. Sendai, M. Alvarez, T. Matsushima, Y. Matsuo, and Y. Iwasawa, “Leave no observation behind: Real-time correction for vla action chunks,” arXiv preprint arXiv:2509.23224 , 2025
Original
2025
Cited alongside, same era.
Y. Ma, Y. Zhou, Y. Yang, T. Wang, and H. Fan, “Running vlas at real-time speed,” arXiv preprint arXiv:2510.26742 , 2025
Original
2025
Cited alongside, same era.

Then

L. Guo, Z. Xue, Z. Xu, and H. Xu, “Demospeedup: Accelerating visuomotor policies via entropy-guided demonstration acceleration,” arXiv preprint arXiv:2506.05064 , 2025
Original
2025
Closest in time.
D. Driess, J. T. Springenberg, B. Ichter, L. Yu, A. Li-Bell, K. Pertsch, A. Z. Ren, H. Walke, Q. Vuong, L. X. Shi et al. , “Knowledge insulating vision-language-action models: Train fast, run fast, generalize better,” arXiv preprint arXiv:2505.23705 , 2025
Original
2025
Closest in time.
Galaxea AI Technology Co., Ltd., “R1 lite,” https://galaxea-ai.com/cn/products/R1-Lite , 2025
2025
Closest in time.
Hugging Face, Inc., “So-101,” https://huggingface.co/docs/lerobot/en/so101 , 2025
2025
Closest in time.
Galaxea AI Technology Co., Ltd., “Galaxea ai,” https://galaxea-ai.com/cn , 2025
2025
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

NVIDIA, “NVIDIA Isaac GR00T N1.6,” https://huggingface.co/nvidia/GR00T-N1.6-3B , 2025

2025

Cited alongside, same era.

M. Matthews, M. Beukman, C. Lu, and J. Foerster, “Kinetix: Investigating the training of general agents through open-ended physics-based control tasks,” in International Conference on Learning Representations , 2025. [Online]. Available: https://openreview.net/forum?id=zCxGCdzreM

2025

Cited alongside, same era.

K. Black, A. Z. Ren, M. Equi, and S. Levine, “Training-time action conditioning for efficient real-time chunking,” arXiv preprint arXiv:2512.05964 , 2025

2025

Cited alongside, same era.

Figure AI, “Helix accelerating real-world logistics,” https://www.figure.ai/news/helix-logistics , 2025

2025

Cited alongside, same era.

S. Liu, B. Li, K. Ma, L. Wu, H. Tan, X. Ouyang, H. Su, and J. Zhu, “Rdt2: Exploring the scaling limit of umi data towards zero-shot cross-embodiment generalization,” arXiv preprint arXiv:2602.03310 , 2026

2026

Closest in time.

H. Xie, B. Wen, J. Zheng, Z. Chen, F. Hong, H. Diao, and Z. Liu, “Dynamicvla: A vision-language-action model for dynamic object manipulation,” arXiv preprint arXiv:2601.22153 , 2026

2026

Closest in time.