相关论文: CitySpec with Shield: A Secure Intelligent Assista…
The increasing demand for autonomous machines in construction environments necessitates the development of robust object detection algorithms that can perform effectively across various weather and environmental conditions. This paper…
Large language models (LLMs) are increasingly integral as productivity assistants, but existing benchmarks fall short in rigorously evaluating their real-world instruction-following capabilities. Current benchmarks often (i) lack sufficient…
Effective cyber threat recognition and prevention demand comprehensible forecasting systems, as prior approaches commonly offer limited and, ultimately, unconvincing information. We introduce Simplified Plaintext Language (SPLAIN), a…
Semantic segmentation models have reached remarkable performance across various tasks. However, this performance is achieved with extremely large models, using powerful computational resources and without considering training and inference…
We present SaSTL -- a novel Spatial Aggregation Signal Temporal Logic -- for the efficient runtime monitoring of safety and performance requirements in smart cities. We first describe a study of over 1,000 smart city requirements, some of…
Signal Temporal Logic (STL) is an expressive formal language for specifying spatio-temporal requirements over real-valued, real-time signals. It has been widely used for the verification and synthesis of autonomous systems and…
End-to-end spoken language understanding (SLU) predicts intent directly from audio using a single model. It promises to improve the performance of assistant systems by leveraging acoustic information lost in the intermediate textual…
The rapid adoption of Artificial Intelligence(AI) programming assistants such as GitHub Copilot introduces new challenges in how these software tools address human needs. Many existing evaluation frameworks address technical aspects such as…
Safety risks arise as large language model-based agents solve complex tasks with tools, multi-step plans, and inter-agent messages. However, deployer-written policies in natural language are ambiguous and context dependent, so they map…
Large Vision-Language Models (LVLMs) unlock powerful multimodal reasoning but also expand the attack surface, particularly through adversarial inputs that conceal harmful goals in benign prompts. We propose SHIELD, a lightweight,…
We consider the problem of safe control in discrete autonomous agents that use learned components for imperfect perception (or more generally, state estimation) from high-dimensional observations. We propose a shield construction that…
Autonomous agents powered by foundation models have seen widespread adoption across various real-world applications. However, they remain highly vulnerable to malicious instructions and attacks, which can result in severe consequences such…
Today, users ask Large language models (LLMs) as assistants to answer queries that require external knowledge; they ask about the weather in a specific city, about stock prices, and even about where specific locations are within their…
Existing multimodal task-oriented dialog data fails to demonstrate the diverse expressions of user subjective preferences and recommendation acts in the real-life shopping scenario. This paper introduces a new dataset SURE (Multimodal…
Chain-of-Thought reasoning significantly improves the performance of large language models on complex tasks, but incurs high inference latency due to long generation traces. Step-level speculative reasoning aims to mitigate this cost, yet…
Safe Reinforcement learning (Safe RL) aims at learning optimal policies while staying safe. A popular solution to Safe RL is shielding, which uses a logical safety specification to prevent an RL agent from taking unsafe actions. However,…
Text-to-SQL semantic parsing has made significant progress in recent years, with various models demonstrating impressive performance on the challenging Spider benchmark. However, it has also been shown that these models often struggle to…
Spoken keyword spotting (KWS) is the task of identifying a keyword in an audio stream and is widely used in smart devices at the edge in order to activate voice assistants and perform hands-free tasks. The task is daunting as there is a…
Large Language Models (LLMs) are increasingly integrated into real-world applications, from virtual assistants to autonomous agents. However, their flexibility also introduces new attack vectors-particularly Prompt Injection (PI), where…
In the rapidly evolving world of software development, the surge in developers' reliance on AI-driven tools has transformed Integrated Development Environments into powerhouses of advanced features. This transformation, while boosting…