Research map / Video / Video generation
Video-T1: Test-time Scaling for Video Generation
Fangfu Liu, Hanyang Wang, Yimo Cai, Kaiyan Zhang, Xiaohang Zhan, Yueqi Duan
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add test-time scaling (search with verifiers) | CogVideoX-5B · VBench | Total Score: +3.44% | Improved |
| add test-time scaling | Pyramid-Flow (FLUX) · VBench | Total Score: 81.61 -> 86.51 | Improved |
| add test-time scaling | Pyramid-Flow (SD3) · VBench | Total Score: 81.72 -> 85.31 | Improved |
| add test-time scaling | NOVA · VBench | Total Score: +1.58% | Improved |
| add test-time scaling | CogVideoX-5B · VBench Semantic Score | Semantic Score: 77.04 -> 84.83 | Improved |
| add test-time scaling | Pyramid-Flow (FLUX) · VBench Multiple Objects | Multiple Objects: 61.08 -> 88.93 | Improved |
| use Tree-of-Frames search instead of random linear search | Pyramid-Flow (FLUX) · VBench inference cost | GFLOPs: 5.22 x 10^7 -> 1.62 x 10^7 | Improved |
| use Tree-of-Frames search instead of random linear search | Pyramid-Flow (SD3) · VBench inference cost | GFLOPs: 3.66 x 10^7 -> 1.13 x 10^7 | Improved |
| use Tree-of-Frames search instead of random linear search | NOVA · VBench inference cost | GFLOPs: 4.02 x 10^6 -> 1.41 x 10^6 | Improved |
| ensemble multiple verifiers | video TTS · VBench | Total Score | Improved |
| increase inference budget for hard dimensions (Motion Smoothness, Temporal Flickering) | video TTS · VBench | dimension scores | No 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.
- CogVideoX-5B — CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer (ICLR 2025) · better on 6 of 6 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
- A Recipe for Scaling up Text-to-Video Generation with Text-free Videos (CVPR 2024 · similarity 0.89)
- LinGen: Towards High-Resolution Minute-Length Text-to-Video Generation with Linear Computational Complexity (CVPR 2025 · similarity 0.88)
- VSTAR: Generative Temporal Nursing for Longer Dynamic Video Synthesis (ICLR 2025 · similarity 0.88)
- Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis (CVPR 2024 · similarity 0.87)
- TTS-VAR: A Test-Time Scaling Framework for Visual Auto-Regressive Generation (NeurIPS 2025 · similarity 0.87)
- ByTheWay: Boost Your Text-to-Video Generation Model to Higher Quality in a Training-free Way (CVPR 2025 · similarity 0.87)
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.
