Related papers: Box-QAymo: Box-Referring VQA Dataset for Autonomou…

Visual question answering (VQA) refers to the problem where, given an image and a natural language question about the image, a correct natural language answer has to be generated. A VQA model has to demonstrate both the visual understanding…

Multimodal Large Language Models (MLLMs) have become a powerful tool for integrating visual and textual information. Despite their exceptional performance on visual understanding benchmarks, measuring their ability to reason abstractly…

Vision-Language-Action (VLA) models have recently achieved notable progress in end-to-end autonomous driving by integrating perception, reasoning, and control within a unified multimodal framework. However, they often lack explicit modeling…

MLLMs require high-resolution visual inputs for fine-grained tasks like document understanding and dense scene perception. However, current global resolution scaling paradigms indiscriminately flood the quadratic self-attention mechanism…

The increasing availability of multimodal data across text, tables, and images presents new challenges for developing models capable of complex cross-modal reasoning. Existing methods for Multimodal Multi-hop Question Answering (MMQA) often…

Autonomous driving has long relied on modular "Perception-Decision-Action" pipelines, where hand-crafted interfaces and rule-based components often break down in complex or long-tailed scenarios. Their cascaded design further propagates…

Vision-language models (VLMs) extend the conventional large language models by integrating visual data, enabling richer multimodal reasoning and significantly broadens the practical applications of AI. However, including visual inputs also…

Vision-Language-Action (VLA) models offer significant potential for end-to-end driving, yet their reasoning is often constrained by textual Chains-of-Thought (CoT). This symbolic compression of visual information creates a modality gap…

Vision-Language Models (VLMs) are becoming increasingly powerful, demonstrating strong performance on a variety of tasks that require both visual and textual understanding. Their strong generalisation abilities make them a promising…

The advancement of Large Vision-Language Models (LVLMs) requires precise local region-based reasoning that faithfully grounds the model's logic in actual visual evidence. However, existing datasets face limitations in scalability due to…

Autonomous driving requires reliable perception and safe decision-making in complex scenarios. Recent vision-language models (VLMs) demonstrate reasoning and generalization abilities, opening new possibilities for autonomous driving;…

AI systems' ability to explain their reasoning is critical to their utility and trustworthiness. Deep neural networks have enabled significant progress on many challenging problems such as visual question answering (VQA). However, most of…

Recent advancements in Vision-Language (VL) research have sparked new benchmarks for complex visual reasoning, challenging models' advanced reasoning ability. Traditional Vision-Language Models (VLMs) perform well in visual perception tasks…

A domain shift exists between the large-scale, internet data used to train a Vision-Language Model (VLM) and the raw image streams collected by a robot. Existing adaptation strategies require the definition of a closed-set of classes, which…

Vision Language Models (VLMs) have achieved impressive performance on spatial reasoning benchmarks, yet these evaluations mask critical weaknesses in understanding object interactions. Current benchmarks test high level relationships ('left…

The pursuit of autonomous driving technology hinges on the sophisticated integration of perception, decision-making, and control systems. Traditional approaches, both data-driven and rule-based, have been hindered by their inability to…

To create culturally inclusive vision-language models (VLMs), developing a benchmark that tests their ability to address culturally relevant questions is essential. Existing approaches typically rely on human annotators, making the process…

Large Vision-Language Models (LVLMs) have demonstrated remarkable performance in complex multimodal tasks. However, these models still suffer from hallucinations, particularly when required to implicitly recognize or infer diverse visual…

Language models uncover unprecedented abilities in analyzing driving scenarios, owing to their limitless knowledge accumulated from text-based pre-training. Naturally, they should particularly excel in analyzing rule-based interactions,…

As large language models (LLMs) continue to advance, there is increasing interest in their ability to infer human mental states and demonstrate a human-like Theory of Mind (ToM). Most existing ToM evaluations, however, are centered on…