AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

A Mechanistic Analysis of Sim-and-Real Co-Training in Generative Robot Policies

Yu Lei, Minghuan Liu, Abhiram Maddukuri, Zhenyu Jiang, Yuke Zhu

ICML 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Mixture and distillation for domain shift · 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
combine classifier-free guidance with adversarial domain alignment (CFG-ADDA, lambda=-0.5)sim-and-real co-training · Real-world manipulation avgsuccess count: 15.3/30 -> 21/30Improved
set CFG-ADDA guidance scale lambda to -0.5 instead of 0 (ablation)CFG-ADDA · Real-world manipulation avgsuccess count: 18.6/30 -> 21/30Improved
add optimal-transport regularizationco-training · Real-world manipulation avgsuccess count: 15.3/30 -> 14.3/30No clear effect
add adversarial domain adaptation (ADDA)co-training · Real-world manipulation avgsuccess count: 15.3/30 -> 14.3/30No clear effect
add classifier-free guidance (lambda=0)co-training · Real-world manipulation avgsuccess count: 15.3/30 -> 15.3/30No clear effect
add co-training with simulation datareal-only policy · Real-world manipulation avgsuccess count: 8.6/30 -> 15.3/30Improved
add OT/ADDA alignment methods under balanced mixing ratiosco-training · sim-and-sim visual-physicssuccess rateImproved
add OT/ADDA alignment under unbalanced mixing ratiosco-training · sim-and-sim visual-physicssuccess rateHurt
add CFG under unbalanced mixingco-training · sim-and-sim visual-physicssuccess rateImproved
remove gradient reversal layer to promote domain-discriminative features (ablation)co-training with ADDA · sim-and-sim vis-physsuccess rateHurt
vary mixing ratio w in toy example with misaligned representations (ablation)co-training toy diffusion model · toy L2 lossL2 lossNo clear effect
structured representation alignment vs mixing ratio effect (ablation)toy co-training · toy L2 loss ANOVAvariance explained: around 50% vs 20%Improved

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