ainewsblitz.com

Breaking

ByteDance Seed and academic partners introduce Trace Anything, a feed-forward 4D trajectory-field model

ByteDance Seed and academic partners introduce Trace Anything, a feed-forward 4D trajectory-field model
  • Research & Papers
  • Open Source
  • Robotics

Researchers from ByteDance Seed, HKUST, Zhejiang University, and Dartmouth College have released Trace Anything, a neural network that represents any video as a dense field of continuous, parametric 3D trajectories—one B-spline path per pixel per frame—predicted in a single feed-forward pass. The work, posted on arXiv on 15 October 2025 and listed as an ICLR 2026 paper, is accompanied by official code, a project page, and model weights.

Continue reading

The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.

$20
Read this article
$29/month
Unlimited — all 27,625 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year