AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Sim, Yet Same: Physics-Aligned Simulator as Zero-Shot Data Scaler in Deformable Worlds

Yunsong Zhou, Hangxu Liu, Xuekun Jiang, Xing Shen, Yuanzhen Zhou, Hui Wang, Baole Fang, Yang Tian, Mulin Yu, Qiaojun Yu, Li Ma, Hengjie Li and 3 more

ECCV 2026 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Zero-shot robustness and transfer

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 trajectory decomposition to the MimicGen-style baseline (ablation)SIM1 data generation · T-shirt foldingpass rate / success rate: pass rate 0% -> 65%, success 0%Mixed
add diffusion-based motion generation (ablation)SIM1 data generation · T-shirt folding in-domainsuccess rate (%): 0 -> 47Improved
add diffusion-based motion generation (ablation)SIM1 data generation · T-shirt folding averageaverage success rate (%): 0 -> 33Improved
add deformation-stable solver (ablation)SIM1 data generation · T-shirt folding in-domainsuccess rate (%): 47 -> 67Improved
add deformation-stable solver (ablation)SIM1 data generation · T-shirt folding averageaverage success rate (%): 33 -> 76Improved
add deformation-stable solver (ablation)SIM1 data generation · T-shirt folding viewpoint shiftsuccess rate (%): 7 -> 47Improved
add deformation-stable solver (ablation)SIM1 data generation · T-shirt folding pass ratepass rate (%): 38 -> 40No clear effect
train on simulation-teleoperated data instead of real datapi0.5 · T-shirt folding in-domainaverage success rate (%): 97 -> 87Hurt
use simulation-generated data instead of real data under domain shiftpi0.5 · spatial, texture, lighting shiftssuccess rate gain (points): +50%, +13%, +47%Improved
use synthetic data instead of real data when training from scratchpi0.5 (from scratch) · T-shirt foldingsuccess rate (%): 0% -> 76%Improved
use synthetic data instead of real data on an unseen polo shirtpi0.5 · real-robot polo shirtsuccess rate (%): 20% -> 70%Improved
scale synthetic data volumepi0.5 and pi0 · T-shirt folding in-domainsuccess rate: 15 synthetic samples per real demo; 5 for texture generalizationImproved

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