AI Paper Atlas

Research map / Video / Video generation

Improving the Diffusability of Motion Tokenizer

Guanhe Huang, Songqiao Han, Tangzheng Lian, Oya Celiktutan

NeurIPS 2026 · Video › Video generation · approach: Text-to-motion diffusion · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Addresses the generation-reconstruction trade-off in latent diffusion for text-driven human motion by improving the diffusability (latent generability) of the motion VAE tokenizer.

Problem

Latent diffusion models with VAE motion tokenizers show a generation-reconstruction trade-off: increasing tokenizer capacity improves reconstruction but does not proportionally improve text-conditioned motion generation.

Approach

Hypothesizes the trade-off stems from the latent space structure being hard to diffuse, and proposes improving the tokenizer's latent diffusability rather than only its reconstruction capacity. Abstract truncated; specific method not stated.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add DiMoT tokenizer (CSA+AMD) to MLD++MLD++ · InterHumanFID: 5.046 -> 4.716Improved
add DiMoT tokenizer to MLD++MLD++ · InterXFID: 0.446 -> 0.335Improved
add Critic Spectral Adaptation to MLD (ablation)MLD · InterHumanR-Top3: 0.636 -> 0.689Improved
add Critic Spectral Adaptation to MLD++ (ablation)MLD++ · InterHumanR-Top3: 0.688 -> 0.746Improved
add Alpha-Flow Motion Decoder to MLD++ (ablation)MLD++ · InterHumanFID: 5.046 -> 4.781Improved
add AMD to MLD (ablation)MLD · InterHumanFID: 5.477 -> 5.209Improved
combine CSA and AMD vs CSA alone on MLD++ (ablation)MLD++ · InterHumanR-Top3: 0.746 -> 0.739Hurt
add CSA to MLD++ tokenizer (ablation)MLD++ · InterHuman reconstructionrFID: 0.080 -> 0.086Hurt
add DiMoT to MLD++MLD++ · InterHuman reconstructionMPJPE: 49.26 -> 41.36Improved
add DiMoT to MLD++MLD++ · InterHumanfoot sliding: 0.0186 -> 0.0168Improved
add DiMoT to MLD++MLD++ · HumanML3DFID: 0.049 -> 0.038Improved
add CSA only to MLD++ (ablation)MLD++ · HumanML3DR-Top3: 0.544 -> 0.552Improved

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.

Surprising findings

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