Vela: Scaling Vision-Language-Action Models with Adaptive Action Curve Parametrization
Most vision-language-action models represent future motion as fixed-rate action chunks, tying temporal resolution and prediction horizon to a fixed output budget. This pointwise representation wastes capacity on highly correlated neighboring actions, leaves temporal continuity and smoothness to be learned implicitly, and forces a tradeoff between long-horizon coverage and the local precision required for contact-rich manipulation. To address these limitations, we introduce Vela, a vision-language-action foundation model that represents future robot behavior as continuous trajectories. Vela combines a compact spline-based action representation with motion-dependent temporal support and a s...
| Authors | Yifan Li, Jiaxu Wang, Dongming Wu et al. |
|---|---|
| Primary category | cs.RO |
| Published | 4 October 2026 |
| Last updated at source | 4 October 2026 |
Popularity, last 3 days
0 now (-4 since 2026-10-15). Counts as reported by the source, snapshotted daily by Silytics.
Recent changes
- 16 Oct 2026 Description: Most vision-language-action models represent future motion as fixed-rate action chunks, tying temporal resolution and prediction horizon to a fixed output budget. This pointwise representation wastes capacity on highly correlated neighborin → Most vision-language-action models represent future motion as fixed-rate action chunks, tying temporal resolution and prediction horizon to a fixed output budget. This pointwise representation wastes capacity on highly correlated neighborin
- 16 Oct 2026 Topics added cs.RO, cs.AI removed hf-daily-papers, vision-language-action models, action chunks, spline-based action representation, continuous trajectories, multi-embodiment robot data, libero-x, ebench
Changes detected by Silytics between refreshes of the source.
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.