相关论文: Drive-JEPA: Video JEPA Meets Multimodal Trajectory…

Recently, deep-learning based approaches have achieved impressive performance for autonomous driving. However, end-to-end vision-based methods typically have limited interpretability, making the behaviors of the deep networks difficult to…

End-to-end autonomous driving has been recently seen rapid development, exerting a profound influence on both industry and academia. However, the existing work places excessive focus on ego-vehicle status as their sole learning objectives…

We present V-JEPA 2.1, a family of self-supervised models that learn dense, high-quality visual representations for both images and videos while retaining strong global scene understanding. The approach combines four key components. First,…

We introduce VL-JEPA, a vision-language model built on a Joint Embedding Predictive Architecture (JEPA). Instead of autoregressively generating tokens as in classical VLMs, VL-JEPA predicts continuous embeddings of the target texts. By…

Trajectory similarity computation is an essential technique for analyzing moving patterns of spatial data across various applications such as traffic management, wildlife tracking, and location-based services. Modern methods often apply…

The representation of urban trajectory data plays a critical role in effectively analyzing spatial movement patterns. Despite considerable progress, the challenge of designing trajectory representations that can capture diverse and…

A major challenge for modern AI is to learn to understand the world and learn to act largely by observation. This paper explores a self-supervised approach that combines internet-scale video data with a small amount of interaction data…

Vision-Language Models (VLMs) have demonstrated significant potential for end-to-end autonomous driving. However, the field still lacks a practical platform that enables dynamic model updates, rapid validation, fair comparison, and…

Vision-Language-Action models have shown great promise for autonomous driving, yet they suffer from degraded perception after unfreezing the visual encoder and struggle with accumulated instability in long-term planning. To address these…

The well-established modular autonomous driving system is decoupled into different standalone tasks, e.g. perception, prediction and planning, suffering from information loss and error accumulation across modules. In contrast, end-to-end…

End-to-end motion planning models equipped with deep neural networks have shown great potential for enabling full autonomous driving. However, the oversized neural networks render them impractical for deployment on resource-constrained…

Traditional methods for autonomous driving are implemented with many building blocks from perception, planning and control, making them difficult to generalize to varied scenarios due to complex assumptions and interdependencies. Recently,…

Recent advances in self-supervised visual representation learning have demonstrated the effectiveness of predictive latent-space objectives for learning transferable features. In particular, Image-based Joint-Embedding Predictive…

Visual Speech Recognition (VSR) tasks are generally recognized to have a lower theoretical performance ceiling than Automatic Speech Recognition (ASR), owing to the inherent limitations of conveying semantic information visually. To…

This paper focuses on multimodal alignment within the realm of Artificial Intelligence, particularly in text and image modalities. The semantic gap between the textual and visual modality poses a discrepancy problem towards the…

End-to-end autonomous driving aims to generate safe and plausible planning policies from raw sensor input. Driving world models have shown great potential in learning rich representations by predicting the future evolution of a driving…

Research interest in end-to-end autonomous driving has surged owing to its fully differentiable design integrating modular tasks, i.e. perception, prediction and planing, which enables optimization in pursuit of the ultimate goal. Despite…

As autonomous driving technology matures, end-to-end methodologies have emerged as a leading strategy, promising seamless integration from perception to control via deep learning. However, existing systems grapple with challenges such as…

Robotic imitation learning is often treated as reproducing demonstrated actions, but actions are inherently embodiment-specific. When demonstrations come from humans or robots with different morphology, kinematics, or action spaces, this…

End-to-end autonomous driving has substantially progressed by directly predicting future trajectories from raw perception inputs, which bypasses traditional modular pipelines. However, mainstream methods trained via imitation learning…