AI Paper Atlas

Research map / Video / Video generation

HandX: Scaling Bimanual Motion and Interaction Generation

Zimu Zhang, Yucheng Zhang, Xiyan Xu, Ziyin Wang, Sirui Xu, Kai Zhou, Bing Zhou, Chuan Guo, Jian Wang, Yu-Xiong Wang, Liang-Yan Gui

CVPR 2026 · Video › Video generation · approach: Text-to-motion diffusion · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
increase diffusion decoder depth from 4 to 12 layers (ablation)Diffusion text-to-motion · HandX (100% data)R-Precision Top-3: 0.327 -> 0.631Improved
increase training data from 5% to 100% (ablation)Diffusion 12 layers · HandXR-Precision Top-3: 0.573 -> 0.631Improved
increase diffusion model from 12 to 16 layers (ablation)Diffusion 100% data · HandXR-Precision Top-3: 0.631 -> 0.603Hurt
scale diffusion model to ultra-large variant (6.7x params of 12-layer) (ablation)Diffusion · HandXall metricsHurt
increase FSQ codebook size alone, fixed small AR model (ablation)FSQ+AR · HandXFID: 8.377 -> 9.934Hurt
jointly increase AR model size and codebook size (ablation)FSQ+AR · HandXFID: 8.377 -> 1.721Improved
add separate text encoding with CLS tokens for left/right/inter-hand promptsDiffusion · HandXqualitative hand assignmentImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy