AI Paper Atlas

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

RoCA: Robust Cross-Domain End-to-End Autonomous Driving

Rajeev Yasarla, Shizhong Han, Hsin-Pai Cheng, Apratim Bhattacharyya, Shweta Mahajan, Litian Liu, Yunxiao Shi, Risheek Garrepalli, Hong Cai, Fatih Porikli

ICML 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Cross-domain text and graph transfer · 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 RoCA GP regularization during source trainingORION · Bench2Drive closed-loopDriving Score: 77.74 -> 80.38Improved
add RoCA GP regularization during source trainingSSR · Bench2Drive closed-loopMean ability: 35.38 -> 48.98Improved
add RoCA regularization, zero-shot sim-to-realORION · nuScenes full val (zero-shot)Avg. L2: 0.98 -> 0.68Improved
use RoCA GT adaptation instead of direct finetuningSparseDrive-S · nuScenes Boston to SingaporeAvg. L2: 0.55 -> 0.49Improved
use RoCA unsupervised adaptation instead of GT finetuning (ablation)SparseDrive-S · nuScenes Boston to SingaporeAvg. L2: 0.55 -> 0.71Hurt
add RoCA regularization only (no adaptation) (ablation)VAD-Tiny · nuScenes Boston to SingaporeAvg. Col. (%): 0.43 -> 0.21Improved
select active-learning samples by GP variance instead of random (ablation)RoCA adaptation · Singapore to Boston 15%Avg. L2: 0.552 -> 0.513Improved
use GP uncertainty instead of Deep Ensemble for sampling (ablation)RoCA · S to B 15%Avg. L2: 0.539 -> 0.513Improved
add RoCA unsupervised adaptation to degraded-image model (ablation)SparseDrive-S · nuScenes snow (full val)Avg. L2: 0.857 -> 0.628Improved
add RoCA regularization (unsupervised adaptation) on NAVSIMOrion · NAVSIM v1PDMS: 84.4 -> 87.9Improved
add RoCA on DriveArena zero-shotOrion · DriveArenaPDMS: 71.6 -> 91.2Improved
add RoCA training regularization (ablation)SparseDrive-S · Low-light degradation (full val)Avg. Col. (%): 0.145 -> 0.129Improved

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