Related papers: CORA: Conformal Risk-Controlled Agents for Safegua…
Vision-Language-Action (VLA) models have demonstrated remarkable capabilities in generalizing across diverse robotic manipulation tasks. However, deploying these models in unstructured environments remains challenging due to the critical…
Autonomous Vehicles (AVs) aim to improve traffic safety and efficiency by reducing human error. However, ensuring AVs reliability and safety is a challenging task when rare, high-risk traffic scenarios are considered. These 'Corner Cases'…
The advancement of Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) has catalyzed the development of mobile graphic user interface (GUI) AI agents, which is designed to autonomously perform tasks on mobile devices.…
Nowadays, user authentication is one of the important topics in information security. Text based strong password schemes could provide with certain degree of security. However, the fact that strong passwords being difficult to memorize…
Computer-Use Agents (CUAs) with full system access enable powerful task automation but pose significant security and privacy risks due to their ability to manipulate files, access user data, and execute arbitrary commands. While prior work…
Open-source native GUI agents still lag behind closed-source systems on long-horizon navigation tasks. This gap stems from two limitations: a shortage of high-quality, action-aligned reasoning data, and the direct adoption of generic…
Ensuring the safety of vulnerable road users (VRUs), including pedestrians, cyclists, electric scooter riders, and motorcyclists, remains a major challenge for advanced driver assistance systems (ADAS) and connected and automated vehicles…
Vision-language model based graphical user interface (GUI) agents have shown strong interaction capabilities. However, they often behave unfaithfully, relying on memorized shortcuts rather than grounding actions in displayed screen evidence…
Vision language models (VLMs) extend the reasoning capabilities of large language models (LLMs) to cross-modal settings, yet remain highly vulnerable to multimodal jailbreak attacks. Existing defenses predominantly rely on safety…
A critical limitation in large-scale multi-agent systems is the cascading of errors. And without intermediate verification, downstream agents exacerbate upstream inaccuracies, resulting in significant quality degradation. To bridge this…
Real time model based control of high dimensional nonlinear systems presents severe computational challenges. Conventional reduced order model control relies heavily on expert tuning or parameter adaptation and seldom offers mechanisms for…
People are spending an enormous amount of time on digital devices through graphical user interfaces (GUIs), e.g., computer or smartphone screens. Large language models (LLMs) such as ChatGPT can assist people in tasks like writing emails,…
Security-critical system requirements are increasingly enforced through mandatory access control systems. These systems are controlled by security policies, highly sensitive system components, which emphasizes the paramount importance of…
The current "notice and consent" paradigm is broken: consent dialogues are often manipulative, and users cannot realistically read or understand every privacy policy. While recent LLM-based tools empower users seeking active control, many…
In the context of Visual Question Answering (VQA) and Agentic AI, calibration refers to how closely an AI system's confidence in its answers reflects their actual correctness. This aspect becomes especially important when such systems…
When fine-tuning pre-trained Language Models (LMs) to exhibit desired behaviors, maintaining control over risk is critical for ensuring both safety and trustworthiness. Most existing safety alignment methods, such as Safe RLHF and SACPO,…
Current LLM-based conversational recommender systems (CRS) primarily optimize recommendation accuracy and user satisfaction. We identify an underexplored vulnerability in which recommendation outputs may negatively impact users by violating…
In recent years, Multimodal Large Language Models (MLLMs) have been extensively utilized for multimodal reasoning tasks, including Graphical User Interface (GUI) automation. Unlike general offline multimodal tasks, GUI automation is…
Large Language Models (LLMs) have achieved tremendous success in various tasks, yet concerns about their safety and security have emerged. In particular, they pose risks of generating harmful content and are vulnerable to jailbreaking…
Vision-Language-Action (VLA)-based driving systems represent a significant paradigm shift in autonomous driving since, by combining traffic scene understanding, linguistic interpretation, and action generation, these systems enable more…