Models for physical AI tasks, such as robotics and autonomous driving, need not reason solely in language. They can use visual plans--points, bounding boxes, and trajectories--to represent spatial goa
Models for physical AI tasks, such as robotics and autonomous driving, need not reason solely in language. They can use visual plans--points, bounding boxes, and trajectories--to represent spatial goals and anticipate motion. However, autoregressive vision-language models generate these plans one coordinate token at a time, making richer predictions increasingly costly. We introduce VFlash, a method for fast, accurate visual planning through Flash Primitive Decoding. VFlash exploits the known structure of visual primitives to predict their coordinates jointly, using a lightweight drafter that generates an entire primitive in one forward pass. The layout adapts to the primitive's type,…
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
VFlash: Fast, Accurate Visual Planning via Flash Primitive Decoding was first seen on Hugging Face · Daily papers on Nov 6, 2026. Since then it has appeared in 30 checks on 3 different days. Its best position was #1 of 30, reached on Nov 7, 11:28 UTC. It is #2 right now, slipping from #1 to #2 over the last 6 checks.
Position on Hugging Face · Daily papers at every check (lower is better).
Best rank per day (UTC).
▲ as reported by Hugging Face.
Archived daily, weekly and monthly lists that include this entry.
Yes. As of Nov 8, 17:28 UTC it is #2, slipping from #1 to #2 over the last 6 checks.
#1 on Hugging Face · Daily papers, on Nov 7, 11:28 UTC. Trendoday checks this list every 120 minutes.
It was first seen on Nov 6, 2026 and has been on the list on 3 days (30 checks) since.