Research map / Video / Video generation
Many-for-Many: Unify the Training of Multiple Video and Image Generation and Manipulation Tasks
Ruibin Li, Tao Yang, Yangming Shi, Weiguo Feng, Shilei Wen, BINGYUE PENG, Lei Zhang
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 multi-task (many-for-many) training data to T2V training (ablation) | MfM T2V model · VBench T2V | dynamic degree: 0.402 -> 0.819 | Improved |
| add multi-task training (ablation) | MfM T2V model · VBench T2V | multiple objects: 0.887 -> 0.782 | Hurt |
| add multi-task training (ablation) | MfM T2V model · VBench T2V | spatial relationship: 0.882 -> 0.802 | Hurt |
| add multi-task training (ablation) | MfM T2V model · VBench T2V | aesthetic quality: 0.628 -> 0.645 | Improved |
| add multi-task training (ablation) | MfM T2V model · VBench T2V | imaging quality: 0.641 -> 0.662 | Improved |
| add multi-task training (ablation) | MfM T2V model · VBench T2V | appearance style: 0.250 -> 0.251 | No clear effect |
| add multi-task training (ablation) | MfM T2V model · VBench T2V | temporal style: 0.221 -> 0.247 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- colormnet — ColorMNet: A Memory-based Deep Spatial-Temporal Feature Propagation Network for Video Colorization (ECCV 2024) · better on 1 of 1 shared result
- ProPainter — ProPainter: Improving Propagation and Transformer for Video Inpainting (ICCV 2023) · better on 1 of 1 shared result
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
- VideoVLA: Video Generators Can Be Generalizable Robot Manipulators (NeurIPS 2025 · similarity 0.89)
- EC-Diffuser: Multi-Object Manipulation via Entity-Centric Behavior Generation (ICLR 2025 · similarity 0.88)
- Vivid-ZOO: Multi-View Video Generation with Diffusion Model (NeurIPS 2024 · similarity 0.88)
- Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation (ICLR 2024 · similarity 0.88)
- Towards Precise Scaling Laws for Video Diffusion Transformers (CVPR 2025 · similarity 0.88)
- LongScape: Advancing Long-Horizon Embodied World Models with Context-Aware MoE (NeurIPS 2026 · similarity 0.88)
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.
