Related papers: Causal Scene Narration with Runtime Safety Supervi…

We present the first systematic study of faithfulness in Vision-Language-Action (VLA) driving models, analyzing 300 Alpamayo-R1-10B inferences across 100 diverse PhysicalAI-AV scenarios. Our main finding is that output natural-language…

Autonomous driving systems face significant challenges in achieving human-like adaptability, robustness, and interpretability in complex, open-world environments. These challenges stem from fragmented architectures, limited generalization…

Autonomous Cyber-Physical Systems must often operate under uncertainties like sensor degradation and shifts in the operating conditions, which increases its operational risk. Dynamic Assurance of these systems requires designing runtime…

Recent advances in deep learning have enabled the development of autonomous systems that use deep neural networks for perception. Formal verification of these systems is challenging due to the size and complexity of the perception DNNs as…

Recently, numerous algorithms have been developed to tackle the problem of vision-language navigation (VLN), i.e., entailing an agent to navigate 3D environments through following linguistic instructions. However, current VLN agents simply…

Video Anomaly Detection (VAD) remains a fundamental yet formidable task in the video understanding community, with promising applications in areas such as information forensics and public safety protection. Due to the rarity and diversity…

Autonomous driving increasingly relies on Visual Question Answering (VQA) to enable vehicles to understand complex surroundings by analyzing visual inputs and textual queries. Currently, a paramount concern for VQA in this domain is the…

As AVs grow in complexity and diversity, identifying the root causes of operational failures has become increasingly complex. The heterogeneity of system architectures across manufacturers, ranging from end-to-end to modular designs,…

Interpretable autonomous driving planners depend not only on generating explanations, but also on those explanations remaining reliable under real-world sensor degradation. In this paper we present a controlled perturbation study of…

Vision-and-Language Navigation (VLN) aims to develop intelligent agents to navigate in unseen environments only through language and vision supervision. In the recently proposed continuous settings (continuous VLN), the agent must act in a…

Verification and validation of autonomous driving (AD) systems and components is of increasing importance, as such technology increases in real-world prevalence. Safety-critical scenario generation is a key approach to robustify AD policies…

Safety-aligned Large Language Models (LLMs) still show two dominant failure modes: they are easily jailbroken, or they over-refuse harmless inputs that contain sensitive surface signals. We trace both to a common cause: current models…

Visual-language reasoning, driving knowledge, and value alignment are essential for advanced autonomous driving systems. However, existing approaches largely rely on data-driven learning, making it difficult to capture the complex logic…

Robotic real-world reinforcement learning (RL) with vision-language-action (VLA) models is bottlenecked by sparse, handcrafted rewards and inefficient exploration. We introduce VLAC, a general process reward model built upon InternVL and…

End-to-end autonomous driving models based on Vision-Language-Action (VLA) architectures have shown promising results by learning driving policies through behavior cloning on expert demonstrations. However, imitation learning inherently…

Although attention mechanisms have achieved considerable progress in Transformer-based architectures across various Artificial Intelligence (AI) domains, their inner workings remain to be explored. Existing explainable methods have…

While Vision-Language Models (VLMs) offer rich world knowledge for end-to-end autonomous driving, current approaches heavily rely on labor-intensive language annotations (e.g., VQA) to bridge perception and control. This paradigm suffers…

Modern computer vision applications rely on learning-based perception modules parameterized with neural networks for tasks like object detection. These modules frequently have low expected error overall but high error on atypical groups of…

Planning-oriented end-to-end driving models show great promise, yet they fundamentally learn statistical correlations instead of true causal relationships. This vulnerability leads to causal confusion, where models exploit dataset biases as…

The integration of Vision-Language-Action (VLA) models into autonomous driving systems offers a unified framework for interpreting complex scenes and executing control commands. However, the necessity to incorporate historical multi-view…