AI Paper Atlas

Research map / Video / Video generation

CoF-T2I: Video Models as Pure Visual Reasoners for Text-to-Image Generation

Chengzhuo Tong, Mingkun Chang, Shenglong Zhang, Yuran Wang, Cheng Liang, Zhizheng Zhao, Bohan Zeng, Yang Shi, Ruichuan An, Yifan Dai, Ziming Zhao, Guanbin Li and 3 more

ICML 2026 · Video › Video generation · approach: Compositional text-to-video diffusion · 0 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 with CoF trajectories (CoF-T2I) vs base video modelWan2.1-T2V-14B · GenEvaloverall: 0.55 -> 0.86Improved
fine-tune with CoF trajectories vs base video modelWan2.1-T2V-14B · Imagine-Benchoverall: 5.939 -> 7.468Improved
add intermediate frame supervision (full CoF vs target-only SFT) (ablation)CoF-T2I · GenEvaloverall: 0.81 -> 0.86Improved
add intermediate frame supervision (full CoF vs target-only SFT) (ablation)CoF-T2I · Imagine-Benchoverall: 6.755 -> 7.468Improved
add target-only SFT on CoF-Evol-Instruct final frames (ablation)Wan2.1-T2V-14B · GenEvaloverall: 0.55 -> 0.81Improved
add independent frame-wise VAE encoding (ablation)CoF-T2I · GenEvaloverall: 0.83 -> 0.86Improved
add a refinement step (Frame 1 to Frame 2) (ablation)CoF-T2I · GenEvaloverall: 0.56 -> 0.79Improved
add a refinement step (Frame 2 to Frame 3) (ablation)CoF-T2I · GenEvaloverall: 0.79 -> 0.86Improved
add a refinement step (Frame 1 to Frame 3) (ablation)CoF-T2I · Imagine-Benchoverall: 6.015 -> 7.468Improved
apply CoF-T2I recipe to 1.3B backbone (ablation)Wan2.1-T2V-1.3B · GenEvaloverall: 0.22 -> 0.79Improved
apply CoF-T2I recipe to 14B backboneWan2.1-T2V-14B · GenEvaloverall: 0.55 -> 0.86Improved
use pure visual CoF reasoning instead of textual planning (BAGEL-Think)CoF-T2I · GenEvaloverall: 0.82 -> 0.86Improved

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