相关论文: SignReasoner: Compositional Reasoning for Complex …

Automatic Traffic Sign Recognition is paramount in modern transportation systems, motivating several research endeavors to focus on performance improvement by utilizing large-scale datasets. As the appearance of traffic signs varies across…

Grounding large language models (LLMs) in domain-specific tasks like post-hoc dash-cam driving video analysis is challenging due to their general-purpose training and lack of structured inductive biases. As vision is often the sole modality…

The interpretability of deep learning models has raised extended attention these years. It will be beneficial if we can learn an interpretable structure from deep learning models. In this paper, we focus on Recurrent Neural Networks~(RNNs)…

Few-shot learning (FSL) aims to recognize new concepts using a limited number of visual samples. Existing approaches attempt to incorporate semantic information into the limited visual data for category understanding. However, these methods…

Sign language recognition could significantly improve the user experience for d/Deaf people with the general consumer technology, such as IoT devices or videoconferencing. However, current sign language recognition architectures are usually…

Ensuring safe, comfortable, and efficient planning is crucial for autonomous driving systems. While end-to-end models trained on large datasets perform well in standard driving scenarios, they struggle with complex low-frequency events.…

Lane topology extraction involves detecting lanes and traffic elements and determining their relationships, a key perception task for mapless autonomous driving. This task requires complex reasoning, such as determining whether it is…

Visual question answering (VQA) is a challenging multi-modal task that requires not only the semantic understanding of both images and questions, but also the sound perception of a step-by-step reasoning process that would lead to the…

Modeling the logical architecture is an often underestimated development step to gain an early insight into the fundamental functional properties of an automotive system. An architectural description supports developers in making design…

Chain-of-thought has been proven essential for enhancing the complex reasoning abilities of Large Language Models (LLMs), but it also leads to high computational costs. Recent advances have explored the method to route queries among…

Compositional generalization remains a foundational weakness of modern neural networks, limiting their robustness and applicability in domains requiring out-of-distribution reasoning. A central, yet unverified, assumption in neuro-symbolic…

Large Language Models (LLMs) prompted to generate chain-of-thought (CoT) exhibit impressive reasoning capabilities. Recent attempts at prompt decomposition toward solving complex, multi-step reasoning problems depend on the ability of the…

Current roadside perception systems mainly focus on instance-level perception, which fall short in enabling interaction via natural language and reasoning about traffic behaviors in context. To bridge this gap, we introduce RoadSceneVQA, a…

The provision of natural language explanations for the predictions of deep-learning-based vehicle controllers is critical as it enhances transparency and easy audit. In this work, a state-of-the-art (SOTA) prediction and explanation model…

Assembly code analysis and comprehension play critical roles in applications like reverse engineering, yet they face substantial challenges due to low information density and a lack of explicit syntactic structures. While traditional masked…

We propose MRU (Multi-Range Reasoning Units), a new fast compositional encoder for machine comprehension (MC). Our proposed MRU encoders are characterized by multi-ranged gating, executing a series of parameterized contract-and-expand…

Real-world autonomous driving must adhere to complex human social rules that extend beyond legally codified traffic regulations. Many of these semantic constraints, such as yielding to emergency vehicles, complying with traffic officers'…

Understanding mid-level road semantics, which capture the structural and contextual cues that link low-level perception to high-level planning, is essential for reliable autonomous driving and digital map construction. However, existing…

Vision-Language Models (VLMs) offer a promising approach to end-to-end autonomous driving due to their human-like reasoning capabilities. However, troublesome gaps remains between current VLMs and real-world autonomous driving applications.…

Human cognition excels at symbolic reasoning, deducing abstract rules from limited samples. This has been explained using symbolic and connectionist approaches, inspiring the development of a neuro-symbolic architecture that combines both…