Research map / Video / Video generation
Dual-IPO: Dual-Iterative Preference Optimization for Text-to-Video Generation
Xiaomeng Yang, Mengping Yang, GONG JIA, Luozheng Qin, Zhiyu Tan, Hao Li
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 |
|---|---|---|---|
| update the critic via SRPO during iterations (ablation) | Dual-IPO · VBench (iteration 3 to 4) | VBench score: 82.33 (no update) -> 82.91 | Improved |
| use SRPO loss instead of plain DPO loss for critic (ablation) | SRPO · VBench | VBench score: 82.83 -> 82.91 | Improved |
| add preference certainty estimator (PCE) (ablation) | SRPO · VBench | VBench score: 82.69 -> 82.91 | Improved |
| add real video data SFT to preference optimization (ablation) | Dual-IPO · VBench | Total score: 81.17 -> 81.69 | Improved |
| fine-tune on real video data only, without preference optimization (ablation) | CogVideoX-2B · VBench | Total score: 80.91 -> 80.63 | Hurt |
| use KTO instead of DPO (ablation) | Dual-IPO · VBench | Total score: 82.42 -> 82.47 | No clear effect |
| add more Dual-IPO iterations (1 to 3) (ablation) | CogVideoX-2B · VBench | Total score: 81.69 -> 82.42 -> 82.74 | Improved |
| one extra iteration beyond the reported ones (ablation) | Wan-1.3B · VBench | Total score: 88.32 -> 88.33 | No clear effect |
| use custom reward model instead of VideoScore/VideoAlign/VideoReward for DPO (ablation) | CogVideoX-2B Diffusion-DPO · VBench | VBench score: 80.87 / 81.27 / 81.31 -> 81.54 | Improved |
| scale reward model from 13B to 40B (ablation) | Dual-IPO reward model · VBench | Total score: 82.42 -> 82.52 | Improved |
| apply Dual-IPO to CogVideoX-5B | CogVideoX-5B · VBench | Total score: 81.61 -> 84.63 | Improved |
| apply Dual-IPO to Wan-1.3B | Wan-1.3B · VBench | Total score: 84.26 -> 86.28 | Improved |
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-2B — CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer (ICLR 2025) · better on 3 of 3 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
- Improving Video Generation with Human Feedback (NeurIPS 2025 · similarity 0.89)
- VideoDPO: Omni-Preference Alignment for Video Diffusion Generation (CVPR 2025 · similarity 0.88)
- Hierarchical Fine-grained Preference Optimization for Physically Plausible Video Generation (NeurIPS 2025 · similarity 0.88)
- T2V-Turbo: Breaking the Quality Bottleneck of Video Consistency Model with Mixed Reward Feedback (NeurIPS 2024 · similarity 0.87)
- InstructVideo: Instructing Video Diffusion Models with Human Feedback (CVPR 2024 · similarity 0.87)
- Align-A-Video: Deterministic Reward Tuning of Image Diffusion Models for Consistent Video Editing (CVPR 2025 · similarity 0.86)
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.
