AI Paper Atlas

Research map / Video / Video generation

Think Before You Move: Latent Motion Reasoning for Text-to-Motion Generation

Yijie Qian, Juncheng Wang, Yuxiang Feng, Chao Xu, Wang Lu, Yang Liu, Baigui Sun, Yiqiang Chen, Yong Liu, Shujun Wang

TPAMI 2026 · Video › Video generation · approach: Text-to-motion diffusion · 6 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
add dual-granularity reasoning latent to T2M-GPTT2M-GPT · HumanML3DFID: 0.141 -> 0.040Improved
add dual-granularity reasoning latent to MotionStreamerMotionStreamer · HumanML3D (continuous)FID: 11.790 -> 9.937Improved
add reasoning tokens at 1/4 length versus 1/2 (ablation)LMR · HumanML3DgFID: 0.212 -> 0.040Improved
add reasoning tokens at 1/4 versus 1/8 length (ablation)LMR · HumanML3DgFID: 0.062 -> 0.040Improved
use dual sequences instead of single joint sequence (ablation)LMR · HumanML3DgFID: 0.354 -> 0.040Improved
downsample execution tokens to 1/4 (ablation)T2M-GPT · HumanML3DMPJPE: 16.608 -> 30.294Hurt
two-stage freeze versus end-to-end joint tokenizer training (ablation)LMR tokenizer · HumanML3DgFID: 0.145 -> 0.040Improved
two-stage freeze versus finetuning execution branch (ablation)LMR tokenizer · HumanML3DgFID: 0.109 -> 0.040Improved
shared encoder versus independent networks (ablation)LMR tokenizer · HumanML3DgFID: 0.097 -> 0.040Improved
learned reasoning tokens versus TMR embeddings (ablation)LMR · HumanML3DR-Precision Top-1: 0.472 -> 0.537Improved
reasoning tokens versus coarse-to-fine AR (ablation)LMR · HumanML3DFID: 0.154 -> 0.040Improved
reasoning tokens versus explicit language CoT (ablation)LMR · HumanML3DFID: 0.188 -> 0.040Improved

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