CORTEXA
← Browse
arxivcs.CV2026-07-05

Geographic Diversity Beats Data Volume for Cross-Domain Generalization in Zero-Label JEPA Driving World Models

Santosh Jaiswal

Self-supervised latent world models can assign a surprise score to driving scenarios without any human labels. A natural follow-up question is whether such a model, trained on driving data from one geographic region, can generalize its notion of complexity to unseen cities and sensor configurations. We study this question through a controlled transfer experiment: we train JEPA-based world models on nuPlan data (Pittsburgh, Boston, Singapore) and evaluate zero-shot on held-out Argoverse 2 validation scenarios from Miami and Austin. We find that models trained on geographically diverse data generalize significantly better than models trained on equal amounts of single-geography data. In a matched-scale ablation at 63,000 scenarios per condition (n=3 seeds each), combined training reduces mean surprise score by 16.5% relative to nuPlan-only training (0.228 +/- 0.015 vs 0.273 +/- 0.008). Notably, training on 200,000 AV2-only scenarios (3x more data from one geography) still produces higher surprise (0.264) than the combined 63K model, suggesting that geographic diversity is a stronger predictor of cross-domain generalization than raw data volume.

View free PDFSource page

Related papers

arxivcs.CVcs.AI2026-07-23

HyWorldVLA: A Vision-Language-Action Model with Hybrid World Modeling for Autonomous Driving

Quanfu Yu, Xian Wu, Hao Xu, Liulong Ma

Vision-Language-Action (VLA) models augmented with world modeling represent a promising paradigm for end-to-end autonomous driving. While pixel-level future prediction enables fine-grained spatiotemporal reasoning, it compromises robustness in noisy driving scenarios. Conversely,…

View free PDFSource page
arxivcs.CV2026-07-22

RIM: A Retrieval-In-Matching Framework for Cross-Domain Global Visual Localization of UAVs

Xin Li, Siyuan Duan, Shang Wang, Zhimin Mao, Bingliang Hu, Geng Zhang

Global visual localization of unmanned aerial vehicles (UAVs) using remote-sensing reference maps has attracted increasing attention. However, acquisition-time and imaging-platform differences between UAV and reference imagery induce substantial cross-domain appearance and viewpo…

View free PDFSource page
arxivcs.CV2026-07-23

AUCH-Net: Action Unit-Based Consistency-Aware Hypergraph Network for Cross-Domain Few-Shot Facial Expression Recognition

Xinhan Qiu, Yan Yan, Rui Zhu, Si Chen, Hanzi Wang

Recently, cross-domain few-shot facial expression recognition (CF-FER) has received considerable attention. However, the performance of existing CF-FER methods is still unsatisfactory due to inferior transferable feature learning under large domain discrepancy and limited target…

View free PDFSource page
arxivcs.CVcs.AI2026-07-22

A Systematic Benchmark of Intensity Normalisation Methods for 3D Knee MRI Segmentation and Cross-Domain Generalisability

Oliver Mills, Philip Conaghan, Samuel Relton

Robust out-of-the-box performance is essential for the clinical deployment of deep learning models in medical imaging. An important but underexplored factor affecting model generalisability is intensity normalisation, particularly for magnetic resonance imaging (MRI), where image…

View free PDFSource page
arxivcs.CV2026-07-23

Streaming Multi-Agent Autoregressive Diffusion Model with World State Registers

Sicheng Mo, Yuheng Li, Ziyang Leng, Krishna Kumar Singh, Bolei Zhou

Multi-agent interactive world models should not only generate consistent observations, but also maintain world states that persist across agents and evolve across views. Existing autoregressive video diffusion pipelines carry forward observation history as conditioning context, w…

View free PDFSource page