FUTURE-VLA: Forecasting Unified Trajectories Under Real-time Execution
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914336090357760 |
|---|---|
| author | Fan, Jingjing Liu, Yushan Li, Shoujie Ren, Botao Li, Siyuan Zhang, Xiao-Ping Ding, Wenbo Deng, Zhidong |
| author_facet | Fan, Jingjing Liu, Yushan Li, Shoujie Ren, Botao Li, Siyuan Zhang, Xiao-Ping Ding, Wenbo Deng, Zhidong |
| contents | General vision-language models increasingly support unified spatiotemporal reasoning over long video streams, yet deploying such capabilities on robots remains constrained by the prohibitive latency of processing long-horizon histories and generating high-dimensional future predictions. To bridge this gap, we present FUTURE-VLA, a unified architecture that reformulates long-horizon control and future forecasting as a monolithic sequence-generation task. Adopting a dual-sided efficiency paradigm, FUTURE-VLA leverages a temporally adaptive compression strategy to maximize spatiotemporal information density, enabling the ingestion of extensive multi-view histories while maintaining constant inference latency. Simultaneously, it performs latent-space autoregression to align actionable dynamics with reviewable visual look-aheads in a single forward pass. These real-time predictive capabilities further enable a prediction-guided Human-In-the-Loop mechanism via interactive execution gating, allowing operators to dynamically validate behaviors based on interpretable future previews. Extensive evaluations demonstrate that FUTURE-VLA establishes new state-of-the-art performance, attaining success rates of 99.2% on LIBERO, 75.4% on RoboTwin, and 78.0% on a real-world Piper platform, all with a $16\times$ extended spatiotemporal window while maintaining the inference latency of a single-frame baseline. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_15882 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FUTURE-VLA: Forecasting Unified Trajectories Under Real-time Execution Fan, Jingjing Liu, Yushan Li, Shoujie Ren, Botao Li, Siyuan Zhang, Xiao-Ping Ding, Wenbo Deng, Zhidong Robotics Artificial Intelligence General vision-language models increasingly support unified spatiotemporal reasoning over long video streams, yet deploying such capabilities on robots remains constrained by the prohibitive latency of processing long-horizon histories and generating high-dimensional future predictions. To bridge this gap, we present FUTURE-VLA, a unified architecture that reformulates long-horizon control and future forecasting as a monolithic sequence-generation task. Adopting a dual-sided efficiency paradigm, FUTURE-VLA leverages a temporally adaptive compression strategy to maximize spatiotemporal information density, enabling the ingestion of extensive multi-view histories while maintaining constant inference latency. Simultaneously, it performs latent-space autoregression to align actionable dynamics with reviewable visual look-aheads in a single forward pass. These real-time predictive capabilities further enable a prediction-guided Human-In-the-Loop mechanism via interactive execution gating, allowing operators to dynamically validate behaviors based on interpretable future previews. Extensive evaluations demonstrate that FUTURE-VLA establishes new state-of-the-art performance, attaining success rates of 99.2% on LIBERO, 75.4% on RoboTwin, and 78.0% on a real-world Piper platform, all with a $16\times$ extended spatiotemporal window while maintaining the inference latency of a single-frame baseline. |
| title | FUTURE-VLA: Forecasting Unified Trajectories Under Real-time Execution |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2602.15882 |