AI Paper Atlas

Research map / Video / Video generation

InterCMDM: Block-Causal Diffusion for Autoregressive Human Interaction Generation

Qing Yu, Kent Fujiwara

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

Read the paper

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 dual-stream instead of single-stream blocks (causal B=3) (ablation)InterCMDM · InterHuman ablationR-Precision Top-1: 0.484 -> 0.529Improved
use dual-stream instead of single-stream blocks (causal B=3) (ablation)InterCMDM · InterHuman ablationFID: 5.068 -> 4.492Improved
use dual-stream in all layers instead of hybrid (ablation)InterCMDM · InterHuman ablationR-Precision Top-1: 0.499 -> 0.529Improved
use separate per-person weights instead of shared in dual-stream (ablation)InterCMDM · InterHuman ablationR-Precision Top-1: 0.506 -> 0.529Improved
use bidirectional instead of causal attention (ablation)InterCMDM (dual) · InterHuman ablationR-Precision Top-1: 0.529 -> 0.549Mixed
use block size 3 instead of 1 (ablation)InterCMDM · InterHuman ablationR-Precision Top-1: 0.514 -> 0.529Improved
use block size 5 instead of 3 (ablation)InterCMDM · InterHuman ablationR-Precision Top-1: 0.529 -> 0.532Mixed
use latent rollout instead of decode-encode composition (ablation)InterCMDM · Long-horizon InterHuman (B/NB ratio)B/NB ratio: 1.91 -> 1.66Improved
use latent rollout instead of naive concatenation (ablation)InterCMDM · Long-horizon InterHuman (B/NB ratio)B/NB ratio: 98.58 -> 1.66Improved
use latent rollout instead of naive concatenation (ablation)InterCMDM · Long-horizon InterHuman (segment FID)FID: 18.37 -> 25.104Hurt
train with multi-task masks instead of simultaneous only (ablation)InterCMDM · Reaction generation InterHumanFID: 2.585 -> 2.121Improved
weighted (60/20/10/10) instead of even mask sampling (ablation)InterCMDM · InterHuman ablationFID: 5.247 -> 4.492Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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