AI Paper Atlas

Research map / Video / Video generation

Reasoning Diffusion for Unpaired Test Time Out-of-distribution Text-Image to Video Generation

Zirui Pan, Xin Wang, Yipeng Zhang, Hong Chen, Kecheng Zheng, Wenwu Zhu

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
add VisionNarrator, AlignFormer and two-stage training to Wan2.1Wan2.1-I2V-14B · ActivityNet (unpaired inputs)CLIP Score (Text): 0.224 -> 0.261Improved
add VisionNarrator, AlignFormer and two-stage training to Wan2.1Wan2.1-I2V-14B · ActivityNet (unpaired inputs)User Rank: 2.692 -> 1.743Improved
add ReasonDiff modules to Wan2.1 on paired inputsWan2.1-I2V-14B · MSR-VTT (paired inputs)Imaging Quality: 0.560 -> 0.571Improved
add ReasonDiff modules to Wan2.1 on image similarityWan2.1-I2V-14B · ActivityNet (unpaired inputs)CLIP Score (Image): 0.518 -> 0.528No clear effect
add the auxiliary latent reconstruction loss (second training stage) (ablation)ReasonDiff · ActivityNet (unpaired inputs)all VBench and CLIP metrics (esp. Motion Smooth)Improved
add per-frame narratives from VisionNarrator instead of single user prompt (ablation)ReasonDiff · ActivityNet (unpaired inputs)Dynamic DegreeImproved
add reasoning-enhanced latents from AlignFormer on top of narratives (ablation)ReasonDiff · ActivityNet (unpaired inputs)Imaging QualityImproved
rewrite the text prompt with an MLLM instead of using VisionNarrator and AlignFormer (ablation)Wan2.1 base model · ActivityNet (unpaired inputs)CLIP Score (Text)Hurt
rewrite prompt and manually choose condition index for Wan2.1 (naive approach) (ablation)Wan2.1 · qualitative unpaired examplesqualitative coherenceHurt

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