Related papers: Attention Misses Visual Risk: Risk-Adaptive Steeri…

Autonomous driving technology has advanced significantly, yet detecting driving anomalies remains a major challenge due to the long-tailed distribution of driving events. Existing methods primarily rely on single-modal road condition video…

Autonomous Driving Systems (ADSs) are safety-critical, as real-world safety violations can result in significant losses. Rigorous testing is essential before deployment, with simulation testing playing a key role. However, ADSs are…

Accurate accident anticipation remains challenging when driver cognition and dynamic road conditions are underrepresented in predictive models. In this paper, we propose CAMERA (Context-Aware Multi-modal Enhanced Risk Anticipation), a…

Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks, yet they often refuse to answer legitimate queries--a phenomenon known as overrefusal. Overrefusal typically stems from over-conservative…

Multimodal recommender systems (MMRS) leverage images, text, and interaction signals to enrich item representations. However, recent alignment based MMRSs that enforce a unified embedding space often blur modality specific structures and…

The rapid advancement of machine learning (ML) has led to its increasing integration into cyber-physical systems (CPS) across diverse domains. While CPS offer powerful capabilities, incorporating ML components introduces significant safety…

Discovering hazardous scenarios is crucial in testing and further improving driving policies. However, conducting efficient driving policy testing faces two key challenges. On the one hand, the probability of naturally encountering…

Autonomous Underwater Vehicles (AUVs) have advanced significantly in obstacle detection and path planning through sonar, cameras, and learning-based methods. However, safe and efficient navigation in cluttered environments remains…

Ensuring safety in autonomous driving requires precise, real-time risk assessment and adaptive behavior. Prior work on risk estimation either outputs coarse, global scene-level metrics lacking interpretability, proposes indicators without…

Safe navigation in real-time is challenging because engineers need to work with uncertain vehicle dynamics, variable external disturbances, and imperfect controllers. A common safety strategy is to inflate obstacles by hand-defined margins.…

Ensuring the safety of embodied AI agents during task planning is critical for real-world deployment, especially in household environments where dangerous instructions pose significant risks. Existing methods often suffer from either high…

Finding the most likely path to a set of failure states is important to the analysis of safety-critical systems that operate over a sequence of time steps, such as aircraft collision avoidance systems and autonomous cars. In many…

Multimodal Large Language Models (MLLMs) have shown strong performance in multi-image cross-modal retrieval, yet suffer from severe position bias, where predictions are dominated by input order rather than semantic relevance. Through…

Multimodal large language models (MLLMs) have shown impressive reasoning abilities. However, they are also more vulnerable to jailbreak attacks than their LLM predecessors. Although still capable of detecting the unsafe responses, we…

Reliable autonomous driving systems require accurate detection of traffic participants. To this end, multi-modal fusion has emerged as an effective strategy. In particular, 4D radar and LiDAR fusion methods based on multi-frame radar point…

Predicting the motion of other road agents enables autonomous vehicles to perform safe and efficient path planning. This task is very complex, as the behaviour of road agents depends on many factors and the number of possible future…

Improving decision-making capabilities in Autonomous Intelligent Vehicles (AIVs) has been a heated topic in recent years. Despite advancements, training machines to capture regions of interest for comprehensive scene understanding, like…

Large vision-language models (LVLMs) have achieved remarkable progress in vision-language reasoning tasks, yet ensuring their safety remains a critical challenge. Recent input-side defenses detect unsafe images with CLIP and prepend safety…

Multi-modal learning aims to enhance performance by unifying models from various modalities but often faces the "modality imbalance" problem in real data, leading to a bias towards dominant modalities and neglecting others, thereby limiting…

Despite the strong reasoning capabilities of recent large language models (LLMs), achieving reliable performance on challenging tasks often requires post-training or computationally expensive sampling strategies, limiting their practical…