AI Paper Atlas

Research map / Video / Video generation

ReactDance: Hierarchical Representation for High-Fidelity and Coherent Long-Form Reactive Dance Generation

Jingzhong Lin, Xinru Li, Yuanyuan Qi, Bohao Zhang, Wenxiang Liu, Kecheng Tang, Wenxuan Huang, Xiangfeng Xu, Bangyan Li, Changbo Wang, Gaoqi He

ICLR 2026 · Video › Video generation · approach: Diffusion-based human image animation · 0 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
use HFSQ instead of RVQ-VAE tokenizer (with PM) (ablation)ReactDance · DD100 generationFID_g: 26.98 -> 7.63Improved
use HFSQ instead of plain VAE (ablation)ReactDance · DD100 reconstructionMPJPE: 40.87 -> 28.66Improved
add progressive masking to HFSQ (ablation)ReactDance · DD100 generationFID_g: 10.46 -> 7.63Improved
add progressive masking to HFSQ (ablation)ReactDance · DD100 reconstructionMPJPE: 24.15 -> 28.66Hurt
reduce training stride from 16 to 4 (dense sliding window) (ablation)ReactDance · DD100 duetFID_cd: 22.69 -> 14.17Improved
reduce training stride from 64 to 4 (ablation)ReactDance · DD100 duetFID_cd: 39.50 -> 14.17Improved
use periodic encoding and causal masking instead of latent stitching (ablation)ReactDance · DD100 duetFID_cd: 18.59 -> 14.17Improved
use periodic encoding and causal masking instead of latent stitching (ablation)ReactDance · DD100AITS: 2.03 -> 1.75Improved
use R=2 residual stages instead of R=1 (ablation)HFSQ · DD100 generationFID_k: 13.10 -> 5.57Improved
increase residual stages from R=2 to R=4 (ablation)HFSQ · DD100 generationFID_k: 5.57 -> 6.10Hurt
add leader motion condition (ablation)ReactDance · DD100 duetFID_cd: 48.82 -> 14.17Improved
add music condition (ablation)ReactDance · DD100 duetFID_cd: 35.35 -> 14.17Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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