Research map / Video / Video generation
Rethinking Video Generation Model for the Embodied World
Yufan Deng, Zilin Pan, Hongyu Zhang, Xiaojie Li, Ruoqing Hu, Yufei Ding, Yiming Zou, Yan Zeng, Daquan Zhou
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 |
|---|---|---|---|
| finetune on 200k RoVid-X clips | Wan2.1-14B · RBench total | score: 0.399 -> 0.446 | Improved |
| finetune on 200k RoVid-X clips | Wan2.2-5B · RBench total | score: 0.380 -> 0.439 | Improved |
| finetune on 200k RoVid-X clips | Wan2.1-14B · RBench Visual Reasoning | score: 0.205 -> 0.298 | Improved |
| finetune on 200k RoVid-X clips | Wan2.2-5B · RBench Spatial | score: 0.313 -> 0.403 | Improved |
| finetune on 200k RoVid-X clips | Wan2.2-5B · RBench Multi-entity | score: 0.142 -> 0.221 | Improved |
| finetune on 200k RoVid-X clips | Wan2.1-14B · RBench Multi-entity | score: 0.282 -> 0.295 | Improved |
| finetune on 200k RoVid-X clips | Wan2.1-14B · RBench Spatial | score: 0.268 -> 0.314 | Improved |
| finetune on 200k RoVid-X clips | Wan2.1-14B · RBench Manipulation | score: 0.344 -> 0.376 | Improved |
| finetune on 200k RoVid-X clips | Wan2.1-14B · RBench Long-horizon | score: 0.335 -> 0.389 | Improved |
| finetune on 200k RoVid-X clips | Wan2.2-5B · RBench Reasoning | score: 0.234 -> 0.284 | Improved |
| finetune on 200k RoVid-X clips | Wan2.1-14B · RBench Single-arm embodiment | score: 0.464 -> 0.526 | Improved |
| finetune on 200k RoVid-X clips | Wan2.1-14B · RBench Humanoid embodiment | score: 0.599 -> 0.628 | Improved |
Closest papers by meaning
- WorldSimBench: Towards Video Generation Models as World Simulators (ICML 2025 · similarity 0.91)
- RoboScape: Physics-informed Embodied World Model (NeurIPS 2025 · similarity 0.90)
- Empowering World Models with Reflection for Embodied Video Prediction (ICML 2025 · similarity 0.90)
- Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models (NeurIPS 2026 · similarity 0.89)
- EnerVerse: Envisioning Embodied Future Space for Robotics Manipulation (NeurIPS 2025 · similarity 0.88)
- ManiTaskGen: A Comprehensive Task Generator for Benchmarking and Improving Vision-Language Agents on Embodied Decision-Making (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.
