AI Paper Atlas

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

DADP: Domain Adaptive Diffusion Policy

Pengcheng Wang, Qinghang Liu, Haotian Lin, Yiheng Li, Guojian Zhan, Masayoshi Tomizuka, Yixiao Wang

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
increase context lag delta t from 1 to infinity (ablation)domain encoder · Walker2dlinear probe accuracy: 27.9% -> 99.3%Improved
increase context lag delta t from 1 to infinity (ablation)domain encoder · HalfCheetahlinear probe accuracy: 68.6% -> 99.9%Improved
increase context lag delta t from 1 to infinity (ablation)domain encoder · Hopperlinear probe accuracy: 9.0% -> 26.4%Improved
increase context lag delta t from 1 to infinity (ablation)domain encoder · Walker2dreconstruction loss: 476.1 -> 3.2Improved
use better representation (delta t = inf instead of 1) in conditional policy (ablation)conditional diffusion policy · Walker2d Seenreturn: 2093 -> 3394Improved
condition policy on delta t = inf representation vs no representation (ablation)diffusion policy · Walker2d Seenreturn: 3722 -> 3394Hurt
bias prior with mixed Gaussian (Mixed DDIM, no prediction target) vs conditioning (ablation)diffusion policy · HalfCheetah Unseenreturn: 2744 -> 3012Improved
add representation shift to the diffusion prediction target (w/ Predict) (ablation)Mixed DDIM · Walker2d Seenreturn: 3356 -> 3991Improved
add representation shift to prediction target (ablation)Mixed DDIM · HalfCheetah masterymastery: 84% -> 96%Improved
learned unsupervised lagged representation vs supervised representation (ablation)DADP · Walker2d Seenreturn: 3991 vs 4014No clear effect
DADP vs Meta-DT on Walker2ddomain-adaptive policy · Walker2d Seenreturn: 1304 -> 3999Improved
DADP vs Prompt-DT on Door (Adroit) Seendomain-adaptive policy · Door Seenreturn: 2116 -> 1428Hurt

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