AI Paper Atlas

Research map / Video / Video generation

Text2Interact: High-Fidelity and Diverse Text-to-Two-Person Interaction Generation

Qingxuan Wu, Zhiyang Dou, chuan guo, Yiming Huang, Qiao Feng, Bing Zhou, Jian Wang, Lingjie Liu

ICLR 2026 · Video › Video generation · approach: Text-to-motion diffusion · 10 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
fine-tune on filtered InterCompose synthetic data (ablation)InterActor · InterHuman testFID: 5.701 -> 5.191Improved
fine-tune on filtered InterCompose synthetic data (ablation)InterActor · InterHuman testR-Precision Top-1: 0.485 -> 0.483No clear effect
raise filter lower radius d_min from 0.25 to 0.35 (ablation)InterCompose filtering · InterHuman testFID: 5.981 -> 5.191Improved
add word-level conditioning instead of sentence-level AdaLN (ablation)InterActor · InterHuman testFID: 5.877 -> 5.701Improved
add word-level conditioning instead of sentence-level AdaLN (ablation)InterActor · InterHuman testR-Precision Top-1: 0.484 -> 0.485Improved
add adaptive interaction loss instead of flat distance map loss (ablation)InterActor · InterHuman testFID: 6.192 -> 5.701Improved
add all three components (WLC, AIL, FT) (ablation)InterActor · InterHuman testFID: 6.237 -> 5.191Improved
add all three components (WLC, AIL, FT) (ablation)InterActor · InterHuman testR-Precision Top-1: 0.441 -> 0.483Improved
word-level conditioning and adaptive loss vs InterMaskInterActor · InterHuman testR-Precision Top-1: 0.449 -> 0.483Improved
InterActor vs InterMaskInterActor · InterHuman testFID: 5.154 vs 5.191No clear effect
InterActor vs prior methodsInterActor · InterHuman testMModality: 1.737 (InterMask) -> 1.051Hurt

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