AI Paper Atlas

Research map / Video / Video generation

Interact2Ar: Full-Body Human-Human Interaction Generation via Autoregressive Diffusion Models

Pablo Ruiz-Ponce, Sergio Escalera, José García-Rodríguez, Jiankang Deng, Rolandos Alexandros Potamias

CVPR 2026 · Video › Video generation · approach: Text-to-motion diffusion · 7 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 autoregressive generation with Mixed Memory instead of non-autoregressive (ablation)Interact2Ar · Inter-X full bodyFID: 0.556 -> 0.277Improved
use autoregressive generation (ablation)Interact2Ar · Inter-X full bodyAUJ (smoothness): 54.97 -> 8.837Improved
add dedicated hands/body/trajectory heads with cooperative denoiserInteract2Ar vs InterMask · Inter-X hands onlyFID: 1.960 -> 0.906 (non-AR)Improved
increase regular memory from 15 to 90 frames (ablation)Interact2Ar autoregressive · Inter-X full bodyFID: 0.283 -> 0.412Hurt
add Mixed Memory (short plus downsampled long-term) at 60-frame context (ablation)Interact2Ar autoregressive · Inter-X full bodyFID: 0.316 (60 regular) -> 0.277 (24 frames)Improved
extend Mixed Memory long-term window from 45 to 105 (ablation)Interact2Ar · Inter-X full bodyFID: 0.277 -> 0.325No clear effect
retrain evaluator on global joint positionsInter-X evaluator · noise on trajectory onlyFID: 0.122 -> 62.05Improved

Later papers that compared with this method

1 later accepted paper reports Interact2Ar as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.

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