Related papers: Concept-Based Dictionary Learning for Inference-Ti…

Vision Language Action (VLA) models represent a transformative shift in robotics, with the aim of unifying visual perception, natural language understanding, and embodied control within a single learning framework. This review presents a…

One promise that Vision-Language-Action (VLA) models hold over traditional imitation learning for robotics is to leverage the broad generalization capabilities of large Vision-Language Models (VLMs) to produce versatile, "generalist" robot…

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'…

Concept Bottleneck Models (CBMs) provide interpretable prediction by introducing an intermediate Concept Bottleneck Layer (CBL), which encodes human-understandable concepts to explain models' decision. Recent works proposed to utilize Large…

Vision-Language-Action Models (VLAs) have shown remarkable progress towards embodied intelligence. While their architecture partially resembles that of Large Language Models (LLMs), VLAs exhibit higher complexity due to their multi-modal…

As the capabilities of Vision Language Models (VLMs) continue to improve, they are increasingly targeted by jailbreak attacks. Existing defense methods face two major limitations: (1) they struggle to ensure safety without compromising the…

Large Vision-Language Models (LVLMs) demonstrate exceptional performance across multimodal tasks, yet remain vulnerable to jailbreak attacks that bypass built-in safety mechanisms to elicit restricted content generation. Existing black-box…

Vision-Language Models (VLMs) are now a core part of modern AI. Recent work proposed several visual jailbreak attacks using single/ holistic images. However, contemporary VLMs demonstrate strong robustness against such attacks due to…

Safety hazard identification and prevention are the key elements of proactive safety management. Previous research has extensively explored the applications of computer vision to automatically identify hazards from image clips collected…

Recently in robotics, Vision-Language-Action (VLA) models have emerged as a transformative approach, enabling robots to execute complex tasks by integrating visual and linguistic inputs within an end-to-end learning framework. Despite their…

Large Language Models (LLMs) are increasingly vulnerable to sophisticated multi-turn manipulation attacks, where adversaries strategically build context through seemingly benign conversational turns to circumvent safety measures and elicit…

Multi-turn jailbreak attacks have proven effective against text-only large language models (LLMs), where malicious content is gradually introduced to bypass safety alignment. However, effectively extending such attacks to large…

Large Language Models (LLMs) are increasingly deployed for code generation in high-stakes software development, yet their limited transparency in security reasoning and brittleness to evolving vulnerability patterns raise critical…

The reliance on language in Vision-Language-Action (VLA) models introduces ambiguity, cognitive overhead, and difficulties in precise object identification and sequential task execution, particularly in environments with multiple visually…

The use of Vision-Language Models (VLMs) in automated driving applications is becoming increasingly common, with the aim of leveraging their reasoning and generalisation capabilities to handle long tail scenarios. However, these models…

In the past few years, Language Models (LMs) have shown par-human capabilities in several domains. Despite their practical applications and exceeding user consumption, they are susceptible to jailbreaks when malicious input exploits the…

Large Vision-Language Models (LVLMs) have achieved impressive performance across multimodal understanding and reasoning tasks, yet their internal safety mechanisms remain opaque and poorly controlled. In this work, we present a…

Detecting anomalous hazards in visual data, particularly in video streams, is a critical challenge in autonomous driving. Existing models often struggle with unpredictable, out-of-label hazards due to their reliance on predefined object…

Vision-language-action (VLA) models have emerged as the next generation of models in robotics. However, despite leveraging powerful pre-trained Vision-Language Models (VLMs), existing end-to-end VLA systems often lose key capabilities…

Vision-language models (VLMs) are vulnerable to adversarial image perturbations. Existing works based on adversarial training against task-specific adversarial examples are computationally expensive and often fail to generalize to unseen…