AI Paper Atlas

Research map / Video / Video generation

From Imagined Futures to Executable Actions: Mixture of Latent Actions for Robot Manipulation

Yajie Li, Bozhou Zhang, Chun Gu, Zipei Ma, Jiahui Zhang, Jiankang Deng, Xiatian Zhu, Li Zhang

ICML 2026 · Video › Video generation · approach: World-model video generation · 0 citations (OpenAlex)

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 changedWhereMeasuredEffect
add MoIDM latent-action interface with flow IDM only (ablation)MoLA · CALVIN ABC-Daverage length: 4.24 -> 4.39Improved
add depth IDM to flow IDM (ablation)MoLA · CALVIN ABC-Daverage length: 4.39 -> 4.46Improved
add semantic IDM to flow + depth (ablation)MoLA · CALVIN ABC-Daverage length: 4.46 -> 4.55Improved
add semantic IDM only (ablation)MoLA · CALVIN ABC-Daverage length: 4.24 -> 4.31Improved
pretrain MoIDM on large robot datasets vs from scratch (ablation)MoLA · CALVIN ABC-D and other benchmarkssuccess rateImproved
fine-tune MoIDM jointly instead of freezing (ablation)MoLA · CALVIN ABC-Dsuccess rateImproved
use DiT flow-matching action head instead of autoregressive Transformer (ablation)MoLA · CALVIN ABC-Dsuccess rateImproved
replace SVD with Wan2.2 5B video backbone (ablation)MoLA · CALVIN ABC-Dsuccess rateImproved
use three specialized IDMs instead of unified alternatives (single RGB IDM, shared multimodal IDM, direct multimodal input) (ablation)MoLA · CALVIN ABC-Dsuccess rateImproved
feed identical or noisy current frames instead of imagined future frames at inference (ablation)MoLA · CALVIN ABC-Dsuccess rateHurt
use MoLA latent actions instead of OpenVLA-OFT+VLA policy · LIBERO-Plusaverage success rate: 79.5 -> 92.7Improved
use MoLA instead of pi0.5 in real worldreal-world manipulation · Real-world UR5eaverage success: 77.5% -> 73.0%Hurt

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