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

An elusive goal in navigation research is to build an intelligent agent that can understand multimodal instructions including natural language and image, and perform useful navigation. To achieve this, we study a widely useful category of…

Transformers and vision-language models (VLMs) have emerged as dominant architectures in computer vision and multimodal AI, offering state-of-the-art performance in tasks such as image classification, object detection, visual question…

Vision--Language--Action (VLA) models bridge multimodal reasoning with physical control, but adapting them to new tasks with scarce demonstrations remains unreliable. While fine-tuned VLA policies often produce semantically plausible…

Emerging generative world models and vision-language-action (VLA) systems are rapidly reshaping automated driving by enabling scalable simulation, long-horizon forecasting, and capability-rich decision making. Across these directions,…

In recent years, autonomous driving algorithms using low-cost vehicle-mounted cameras have attracted increasing endeavors from both academia and industry. There are multiple fronts to these endeavors, including object detection on roads,…

Vision Language Models (VLMs) excel at visual question answering (VQA) but remain limited to snapshot vision, reasoning from static images. In contrast, embodied agents require ambulatory vision, actively moving to obtain more informative…

We present SceneVGGT, a spatio-temporal 3D scene understanding framework that combines SLAM with semantic mapping for autonomous and assistive navigation. Built on VGGT, our method scales to long video streams via a sliding-window pipeline.…

Vision-Language-Action (VLA) models have advanced autonomous driving, but existing benchmarks still lack scenario diversity, reliable action-level annotation, and evaluation protocols aligned with human preferences. To address these…

Vision-Language-Action models have emerged as a promising paradigm for robotic manipulation by unifying perception, language grounding, and action generation. However, they often struggle in scenarios requiring precise spatial…

The joint optimization of the sensor trajectory and 3D map is a crucial characteristic of bundle adjustment (BA), essential for autonomous driving. This paper presents $\nu$-DBA, a novel framework implementing geometric dense bundle…

Existing Driving VLAs predict trajectories while largely ignoring their visual tokens -- a phenomenon we trace not to insufficient training but to a structurally ill-posed task formulation. We show that trajectory recovery, when viewed…

Visual imitation learning frameworks allow robots to learn manipulation skills from expert demonstrations. While existing approaches mainly focus on policy design, they often neglect the structure and capacity of visual encoders, limiting…

Reconstructing dynamic 4D scenes is challenging, as it requires robust disentanglement of dynamic objects from the static background. While 3D foundation models like VGGT provide accurate 3D geometry, their performance drops markedly when…

3D reconstruction from multi-view images is a core challenge in computer vision. Recently, feed-forward methods have emerged as efficient and robust alternatives to traditional per-scene optimization techniques. Among them, state-of-the-art…

In this work, we study how vision-language models (VLMs) can be utilized to enhance the safety for the autonomous driving system, including perception, situational understanding, and path planning. However, existing research has largely…

Scene understanding and risk-aware attentions are crucial for human drivers to make safe and effective driving decisions. To imitate this cognitive ability in urban autonomous driving while ensuring the transparency and interpretability, we…

The end-to-end learning ability of self-driving vehicles has achieved significant milestones over the last decade owing to rapid advances in deep learning and computer vision algorithms. However, as autonomous driving technology is a…

Autonomous driving has progressed from modular pipelines toward end-to-end unification, and Vision-Language-Action (VLA) models are a natural extension of this journey beyond Vision-to-Action (VA). In practice, driving VLAs have often…

Scaling Vision-Language-Action (VLA) models on large-scale data offers a promising path to achieving a more generalized driving intelligence. However, VLA models are limited by a ``supervision deficit'': the vast model capacity is…

The advancement of autonomous driving technologies necessitates increasingly sophisticated methods for understanding and predicting real-world scenarios. Vision language models (VLMs) are emerging as revolutionary tools with significant…