5 papers
AD-E2E-JEPA: A Joint-Embedding Predictive Architecture For End-to-End Autonomous Driving
Haoran Zhu, Wancong Zhang, Yann LeCun +1
Autonomous driving requires \textit{world models} that can understand the physical world, reason and plan, and operate safely. In this paper, we first systematically evaluate exist…
Self-Supervised JEPA-based World Models for LiDAR Occupancy Completion and Forecasting
Haoran Zhu, Anna Choromanska
Autonomous driving, as an agent operating in the physical world, requires the fundamental capability to build \textit{world models} that capture how the environment evolves spatiot…
Self-Supervised Representation Learning with Joint Embedding Predictive Architecture for Automotive LiDAR Object Detection
Haoran Zhu, Zhenyuan Dong, Kristi Topollai +2
Recently, self-supervised representation learning relying on vast amounts of unlabeled data has been explored as a pre-training method for autonomous driving. However, directly app…
TAME: Task Agnostic Continual Learning using Multiple Experts
Haoran Zhu, Maryam Majzoubi, Arihant Jain +1
The goal of lifelong learning is to continuously learn from non-stationary distributions, where the non-stationarity is typically imposed by a sequence of distinct tasks. Prior wor…
ERASE-Net: Efficient Segmentation Networks for Automotive Radar Signals
Shihong Fang, Haoran Zhu, Devansh Bisla +4
Among various sensors for assisted and autonomous driving systems, automotive radar has been considered as a robust and low-cost solution even in adverse weather or lighting condit…