AI Paper Atlas

Research map / Video / Video generation

TV2TV: A Unified Framework for Interleaved Language and Video Generation

Xiaochuang Han, Youssef Emad, Melissa Hall, John Nguyen, Karthik Padthe, Liam Robbins, Amir Bar, Delong Chen, Michal Drozdzal, Maha Elbayad, Yushi Hu, Shang-Wen Li and 5 more

CVPR 2026 · Video › Video generation · approach: Compositional text-to-video diffusion · 3 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
interleave planning text with video chunks instead of generating no text (T2V) (ablation)TV2TV 3B-MoT · CS:GO pairwise human visual qualitypreference rate (%): 91% vs. 1%Improved
interleave text with video chunks instead of generating the full text plan first (Think2V) (ablation)TV2TV 3B-MoT · CS:GO pairwise human visual qualitypreference rate (%): 48% vs. 38%Improved
interleave text with video chunks instead of think-then-act (ablation)TV2TV 3B-MoT · CS:GO fine-grained controllabilityinstruction following accuracy: 19 point improvementImproved
interleave text with video chunks (vs Think2V) for the backward and reload interventions (ablation)TV2TV 3B-MoT · CS:GO interventionsintervention correctnessMixed
interleave text with video chunks (vs Think2V) for left-click and jump interventions (ablation)TV2TV 3B-MoT · CS:GO interventionsintervention correctnessImproved
interleave text with video chunks, assessed on visual quality after manual interventions (ablation)TV2TV 3B-MoT · CS:GO interventionsvisual qualityImproved
evaluate on long (64 s) rather than short videosTV2TV 3B-MoT · CS:GO pairwise human visual qualitypreference rateImproved
train on interleaved sports captions instead of T2V on the same data (ablation)TV2TV 8B-MoT · Sports pairwise human evalwin rate (%): 54.0% vs. 34.7%Improved
train on interleaved sports captions instead of Think2V on the same data (ablation)TV2TV 8B-MoT · Sports pairwise human evalwin rate (%): 53.3% vs. 41.3%Improved
compare TV2TV on sports to Cosmos2 variantsTV2TV 8B-MoT · Sports pairwise human eval, visual qualityvisual qualityImproved
compare TV2TV on sports to WAN 2.2 5BTV2TV 8B-MoT · Sports pairwise human eval, visual qualityvisual qualityHurt
compare TV2TV on sports to MAGI-1 variantsTV2TV 8B-MoT · Sports pairwise human eval, visual qualityvisual qualityNo clear effect

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