AI Paper Atlas

Research map / Video / Video generation

EmbodiedVAE: Disentangled Video VAE for Efficient and Controllable Embodied Manipulation

Jiayi Luo, Hanxin Zhu, Chen Gao, Jiankun Wang, Cong Wang, Tianyu He, Jianxin Li, Zhibo Chen

ECCV 2026 · Video › Video generation · approach: World-model video generation

Read the paper

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 arm-mask supervision during training (ablation)EmbodiedVAE · Agibot-2025 (VAE reconstruction)PSNR: 31.1812 -> 31.6745Improved
add arm-mask supervision during training (ablation)EmbodiedVAE · Bridge (VAE reconstruction)PSNR: 29.6680 -> 30.6957Improved
add arm-mask supervision during training (ablation)EmbodiedVAE · RT-1 (action-conditioned generation, IRASim-L)PSNR: 23.8044 -> 24.7082Improved
add arm-mask supervision during training (ablation)EmbodiedVAE · Bridge (action-conditioned generation, IRASim-L)PSNR: 23.7306 -> 24.2484Improved
add OT-based motion consistency loss (ablation)EmbodiedVAE · Agibot-2025 (VAE reconstruction)PSNR: 31.0213 -> 31.6745Improved
add OT-based motion consistency loss (ablation)EmbodiedVAE · Bridge (VAE reconstruction)PSNR: 29.9769 -> 30.6957Improved
add OT-based motion consistency loss (ablation)EmbodiedVAE · RT-1 (action-conditioned generation, IRASim-L)PSNR: 23.8187 -> 24.7082Improved
add OT-based motion consistency loss (ablation)EmbodiedVAE · Bridge (action-conditioned generation, IRASim-L)PSNR: 23.9726 -> 24.2484Improved
add OT-based motion consistency loss (ablation)EmbodiedVAE · Agibot-2025 (VAE reconstruction)LPIPS: 0.0835 -> 0.0723Improved
add OT-based motion consistency loss (ablation)EmbodiedVAE · Bridge (action-conditioned generation, IRASim-L)LPIPS: 0.1643 -> 0.1409Improved
add arm-mask supervision during training (ablation)EmbodiedVAE · Bridge (action-conditioned generation, IRASim-L)LPIPS: 0.1705 -> 0.1409Improved
use EmbodiedVAE instead of Wan-VAE as the LDM VAEIRASim-L · RT-1 (action-conditioned generation, IRASim-L)PSNR: 22.7334 -> 24.7082Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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