Related papers: DVGT-2: Vision-Geometry-Action Model for Autonomou…

In this paper, we propose a novel approach for solving the Visual Question Answering (VQA) task in autonomous driving by integrating Vision-Language Models (VLMs) with continual learning. In autonomous driving, VQA plays a vital role in…

Recent studies on Vision-Language-Action (VLA) models have shifted from the end-to-end action-generation paradigm toward a pipeline involving task planning followed by action generation, demonstrating improved performance on various…

Accurate 3D object detection from point clouds has become a crucial component in autonomous driving. However, the volumetric representations and the projection methods in previous works fail to establish the relationships between the local…

Large vision-language models (VLMs) have shown promising capabilities in scene understanding, enhancing the explainability of driving behaviors and interactivity with users. Existing methods primarily fine-tune VLMs on on-board multi-view…

End-to-end autonomous driving via Vision-Language-Action (VLA) models demands a precarious balance between high-fidelity trajectory planning and efficient inference. Existing paradigms typically fall short: autoregressive (AR) VLAs are…

Autonomous driving, particularly navigating complex and unanticipated scenarios, demands sophisticated reasoning and planning capabilities. While Multi-modal Large Language Models (MLLMs) offer a promising avenue for this, their use has…

Ensuring reliable autonomous operation when visual input is degraded remains a key challenge in intelligent vehicles and robotics. We present DepthVision, a multimodal framework that enables Vision--Language Models (VLMs) to exploit LiDAR…

Autonomous driving requires reasoning about how the environment evolves and planning actions accordingly. Existing world-model-based approaches typically predict future scenes first and plan afterwards, resulting in open-loop imagination…

Vision Language Models (VLMs) bridge visual perception and linguistic reasoning. In Autonomous Driving (AD), this synergy has enabled Vision Language Action (VLA) models, which translate high-level multimodal understanding into driving…

Vision-Language-Action (VLA) models in autonomous driving systems have recently demonstrated transformative potential by integrating multimodal perception with decision-making capabilities. However, the interpretability and coherence of the…

The grand vision of enabling persistent, large-scale 3D visual geometry understanding is shackled by the irreconcilable demands of scalability and long-term stability. While offline models like VGGT achieve inspiring geometry capability,…

In contrast to extensive studies on general vision, pre-training for scalable visual autonomous driving remains seldom explored. Visual autonomous driving applications require features encompassing semantics, 3D geometry, and temporal…

Autonomous navigation in unknown environments is challenging and demands the consideration of both geometric and semantic information in order to parse the navigability of the environment. In this work, we propose a novel space modeling…

Recent developments in generative models and large-scale datasets have substantially advanced 3D world generation, facilitating a broad range of domains including spatial intelligence, embodied intelligence, and autonomous driving. While…

Vision-Language-Action (VLA) models have recently demonstrated strong performance across embodied tasks. Modern VLAs commonly employ diffusion action experts to efficiently generate high-precision continuous action chunks, while…

Vehicle-to-everything (V2X) cooperation has emerged as a promising paradigm to overcome the perception limitations of classical autonomous driving by leveraging information from both ego-vehicle and infrastructure sensors. However,…

Recent studies have explored leveraging the world knowledge and cognitive capabilities of Vision-Language Models (VLMs) to address the long-tail problem in end-to-end autonomous driving. However, existing methods typically formulate…

Vision-Language-Action (VLA) models have emerged as a promising approach for enabling robots to follow language instructions and predict corresponding actions. However, current VLA models mainly rely on 2D visual inputs, neglecting the rich…

Vision-language navigation (VLN) requires intelligent agents to navigate environments by interpreting linguistic instructions alongside visual observations, serving as a cornerstone task in Embodied AI. Current VLN research for unmanned…

Realtime 4D reconstruction for dynamic scenes remains a crucial challenge for autonomous driving perception. Most existing methods rely on depth estimation through self-supervision or multi-modality sensor fusion. In this paper, we propose…