AI Paper Atlas

Research map / Video / Video generation

InternVideo-Next: Towards World-Understanding Video Models

Chenting Wang, Yuhan Zhu, Yicheng Xu, Jiange Yang, Ziang Yan, Yali Wang, Yi Wang, Limin Wang

CVPR 2026 · Video › Video generation · approach: Compositional text-to-video diffusion

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
naively add SigLIP alignment to pixel reconstruction with a linear decoder (ablation)Stage 1 · K400 linear probingtop-1 accuracy: 70.7 -> 69.8Hurt
add semantic alignment to pixel reconstruction baseline (ablation)Stage 1 · K400 linear probingtop-1 accuracy: 47.2 -> 69.8Improved
replace linear decoder with conditional diffusion decoder (ablation)Stage 1 Pixel Rec. + Align · K400 linear probingtop-1 accuracy: 69.8 -> 74.2Improved
add text-decoder predictor initialization without diffusion decoder (ablation)Stage 1 Pixel Rec. + Align · K400 linear probingtop-1 accuracy: 69.8 -> 69.4Hurt
combine diffusion decoder with text-decoder init (ablation)Stage 1 · K400 linear probingtop-1 accuracy: 74.2 -> 75.8Improved
use diffusion MLP decoder (D6 W1536) instead of linear head (ablation)Stage 1 · K400 linear probingtop-1 accuracy: 69.4 -> 75.8Improved
initialize predictor from pretrained text decoder (ablation)Stage 1 predictor (ModernBert-L last5) · K400 linear probingtop-1 accuracy: 74.2 -> 75.8Improved
use SigLIP image teacher instead of DinoV2 or CLIP-ViT for semantic alignment (ablation)Stage 1 · K400 linear probingtop-1 accuracy: 69.3 -> 75.8 (DinoV2 vs SigLIP)Improved
add Stage 2 latent prediction with frozen Stage 1 target (ablation)InternVideo-Next ViT-B · SSv2 linear probingtop-1 accuracy: 36.9 -> 56.9Improved
use momentum-updated target instead of frozen target in Stage 2 (ablation)Stage 2 · SSv2 linear probingtop-1 accuracy: 56.9 -> 54.3Hurt
use frozen SigLIP2 target instead of Stage 1 target in Stage 2 (ablation)Stage 2 · SSv2 linear probingtop-1 accuracy: 56.9 -> 45.7Hurt
add pixel reconstruction loss in Stage 2 (ablation)Stage 2 · SSv2 linear probingtop-1 accuracy: 56.9 -> 57.0No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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