相关论文: DriveXQA: Cross-modal Visual Question Answering fo…

Complex Visual Question Answering (Complex VQA) tasks, which demand sophisticated multi-modal reasoning and external knowledge integration, present significant challenges for existing large vision-language models (LVLMs) often limited by…

Existing Multimodal Large Language Models (MLLMs) and Visual Language Pretrained Models (VLPMs) have shown remarkable performances in the general Visual Question Answering (VQA). However, these models struggle with VQA questions that…

Visual impairment affects hundreds of millions of people worldwide, severely limiting their ability to navigate urban environments safely and independently. While wearable assistive devices offer a promising platform for real-time hazard…

Human drivers possess spatial and causal intelligence, enabling them to perceive driving scenarios, anticipate hazards, and react to dynamic environments. In contrast, autonomous vehicles lack these abilities, making it challenging to…

Partial perception deficits can compromise autonomous vehicle safety by disrupting environmental understanding. Existing protocols typically default to entirely risk-avoidant actions such as immediate stops, which are detrimental to…

Graph Visual Question Answering (GVQA) for autonomous driving organizes reasoning into ordered stages, namely Perception, Prediction, and Planning, where planning decisions should remain consistent with the model's own perception. We…

Large-scale Vision Language Models (LVLMs) exhibit advanced capabilities in tasks that require visual information, including object detection. These capabilities have promising applications in various industrial domains, such as autonomous…

We present M$^3$-VQA, a novel knowledge-based Visual Question Answering (VQA) benchmark, to enhance the evaluation of multimodal large language models (MLLMs) in fine-grained multimodal entity understanding and complex multi-hop reasoning.…

We introduce LingoQA, a novel dataset and benchmark for visual question answering in autonomous driving. The dataset contains 28K unique short video scenarios, and 419K annotations. Evaluating state-of-the-art vision-language models on our…

Deep learning models for autonomous driving, encompassing perception, planning, and control, depend on vast datasets to achieve their high performance. However, their generalization often suffers due to domain-specific data distributions,…

Vision Large Language Models (VLLMs) have demonstrated impressive capabilities in general visual tasks such as image captioning and visual question answering. However, their effectiveness in specialized, safety-critical domains like…

Recent advances in multimodal question answering have primarily focused on combining heterogeneous modalities or fine-tuning multimodal large language models. While these approaches have shown strong performance, they often rely on a…

Autonomous cars need geometric accuracy and semantic understanding to navigate complex environments, yet most stacks handle them separately. We present XYZ-Drive, a single vision-language model that reads a front-camera frame, a 25m…

We study how vision-language models (VLMs) trained on web-scale data can be integrated into end-to-end driving systems to boost generalization and enable interactivity with human users. While recent approaches adapt VLMs to driving via…

Learning contextual and spatial environmental representations enhances autonomous vehicle's hazard anticipation and decision-making in complex scenarios. Recent perception systems enhance spatial understanding with sensor fusion but often…

Large Vision-Language Models (LVLMs) show promise for scientific applications, yet open-source models still struggle with Scientific Visual Question Answering (SVQA), namely answering questions about figures from scientific papers. A key…

Multimodal large language models (MLLMs) excel at 2D visual understanding but remain limited in their ability to reason about 3D space. In this work, we leverage large-scale high-quality 3D scene data with open-set annotations to introduce…

Multimodal large language models (MLLMs) have achieved rapid progress, yet their scaling behavior remains less clearly characterized and often less predictable than that of text-only LLMs. Increasing model size and task diversity often…

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…

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,…