NVIDIA's VFlash speeds robot trajectory decoding 12x, cuts prediction errors by 61%
NVIDIA’s VFlash speeds robot trajectory decoding 12x, cuts prediction errors by 61%
NVIDIA researchers have developed a new visual planning method called VFlash that accelerates robot trajectory decoding by up to 12 times while reducing 3D trajectory prediction errors by as much as 61% in specific tests. The method allows vision-language models to generate complete trajectories in a single pass, cutting inference latency by about 80% on NVIDIA's Jetson Thor and DGX Spark platforms. In robot manipulation tests, VFlash reduced average displacement error significantly compared with conventional autoregressive approaches. The research was published in November 2026.
Source: Robotics — Robot learning news discovery · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
Reported numbers
inference latency on Jetson Thor
703.3
View original evidence
al information, this sequential approach can increase processing time. VFlash instead uses the known structure of visual predictions to generate an entire geometric object or trajectory in one forward pass. In tests involving robot manipulation, the researchers reported that VFlash reduced inference latency from 3,552.7 milliseconds to 703.3 milliseconds on NVIDIA’s Jetson Thor platform. This represents an approximat
Open source S4inference latency on DGX Spark
649.9
View original evidence
ely 80% reduction compared with conventional autoregressive decoding. On DGX Spark hardware, latency fell from 3,356.5 milliseconds to 649.9 milliseconds. Model predicts complete trajectories VFlash works by identifying the structure of a requested visual prediction before generating its coordinates. For example, a bounding box has a fixed coordinate layout, while a trajectory can contain a variable number of two-dim
Open source S5Reported success rate
70.2%
View original evidence
or robotic manipulation. The model achieved an average success rate of 70.2% across four task suites, compared with 62.6% for the baseline system. The largest improvements appeared in pick-and-place and object-closing tasks, where success increased by 11.6 and 12.8 percentage points, respectively. Beyond robotics, the researchers tested VFlash for autonomous driving using NAVSIM and Waymo datasets. The model generate
Open source S9
- paper: not_reported
What remains unknown
Not established in the collected evidence: Environment, Control, Data origin.
Reported performance applies to the described task. It does not establish general autonomy or deployment readiness.
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
nipulation tests, VFlash also cut overall inference latency by about 80% on NVIDIA’s Jetson Thor and DGX Spark platforms, potentially helping robots respond faster to changing environments. The research addresses a limitation in conventional VLMs, which often generate spatial predictions one coordinate at a time. As robots need to predict longer trajectories, track more objects and process increasingly detailed spati
Open source S3
NVIDIA researchers have developed a new visual planning method that accelerates robot trajectory decoding by up to 12 times, while reducing 3D trajectory prediction errors by as much as 61% in specific tests. Called VFlash, the method allows vision-language models (VLMs) to generate complete robot trajectories and other spatial predictions in a single pass, rather than producing coordinates one at a time. In robot ma
Open source S2
al information, this sequential approach can increase processing time. VFlash instead uses the known structure of visual predictions to generate an entire geometric object or trajectory in one forward pass. In tests involving robot manipulation, the researchers reported that VFlash reduced inference latency from 3,552.7 milliseconds to 703.3 milliseconds on NVIDIA’s Jetson Thor platform. This represents an approximat
Open source S4
ely 80% reduction compared with conventional autoregressive decoding. On DGX Spark hardware, latency fell from 3,356.5 milliseconds to 649.9 milliseconds. Model predicts complete trajectories VFlash works by identifying the structure of a requested visual prediction before generating its coordinates. For example, a bounding box has a fixed coordinate layout, while a trajectory can contain a variable number of two-dim
Open source S5
or robotic manipulation. The model achieved an average success rate of 70.2% across four task suites, compared with 62.6% for the baseline system. The largest improvements appeared in pick-and-place and object-closing tasks, where success increased by 11.6 and 12.8 percentage points, respectively. Beyond robotics, the researchers tested VFlash for autonomous driving using NAVSIM and Waymo datasets. The model generate
Open source S9
Source：Robotics — Robot learning news discovery · msn.com