相关论文: Learning Efficient Guardrails for Compliance

As Large Language Models (LLMs) continue to be increasingly applied across various domains, their widespread adoption necessitates rigorous monitoring to prevent unintended negative consequences and ensure robustness. Furthermore, LLMs must…

Safe learning is central to AI-enabled robots where a single failure may lead to catastrophic results. Barrier-based method is one of the dominant approaches for safe robot learning. However, this method is not scalable, hard to train, and…

Model information can be used to predict future trajectories, so it has huge potential to avoid dangerous region when implementing reinforcement learning (RL) on real-world tasks, like autonomous driving. However, existing studies mostly…

Learning-based methods have improved locomotion skills of quadruped robots through deep reinforcement learning. However, the sim-to-real gap and low sample efficiency still limit the skill transfer. To address this issue, we propose an…

We introduce Guard Vector, a safety task vector computed as the parameter difference between a guardrail model (Guard Model) and a same-architecture pretrained language model. Composing this vector with a target language model yields a…

Recent advances have showcased the extraordinary capabilities of Large Language Model (LLM) agents in tackling web-based information-seeking tasks. However, existing efforts mainly focus on single-fact retrieval and rely on outcome-only…

The acquisition of agentic capabilities has transformed LLMs from "knowledge providers" to "action executors", a trend that while expanding LLMs' capability boundaries, significantly increases their susceptibility to malicious use. Previous…

Charts used for persuasion can easily veer into being outright misleading when, for instance, cherry-picked data is paired with a deceptive caption, as is commonly encountered on social media. The rise of interactive time-series data…

Autonomous vehicles are suited for continuous area patrolling problems. However, finding an optimal patrolling strategy can be challenging for many reasons. Firstly, patrolling environments are often complex and can include unknown…

We develop a method for policy architecture search and adaptation via gradient-free optimization which can learn to perform autonomous driving tasks. By learning from both demonstration and environmental reward we develop a model that can…

Autoscaling has become a baseline expectation for cloud-native big data processing, and the design space has expanded beyond rule-based heuristics to include learned controllers and, most recently, large language model (LLM) agents. Yet…

The rapid evolution to autonomous, agentic AI systems introduces significant risks due to their inherent unpredictability and emergent behaviors; this also renders traditional verification methods inadequate and necessitates a shift towards…

The rapid evolution of embodied agents has accelerated the deployment of household robots in real-world environments. However, unlike structured industrial settings, household spaces introduce unpredictable safety risks, where system…

Agentic AI systems are emerging as powerful tools for automating complex, multi-step tasks across various industries. One such industry is telecommunications, where the growing complexity of next-generation radio access networks (RANs)…

The AI era has ushered in Large Language Models (LLM) to the technological forefront, which has been much of the talk in 2023, and is likely to remain as such for many years to come. LLMs are the AI models that are the power house behind…

Reinforcement Learning (RL) algorithms have found limited success beyond simulated applications, and one main reason is the absence of safety guarantees during the learning process. Real world systems would realistically fail or break…

Car-following is a control process in which a following vehicle (FV) adjusts its acceleration to keep a safe distance from the lead vehicle (LV). Recently, there has been a booming of data-driven models that enable more accurate modeling of…

As benchmarks grow in complexity, many apparent agent failures are not failures of the agent at all - they are failures of the benchmark itself: broken specifications, implicit assumptions, and rigid evaluation scripts that penalize valid…

Large language models (LLMs) are increasingly deployed in cost-sensitive and on-device scenarios, and safety guardrails have advanced mainly in English. However, real-world Chinese malicious queries typically conceal intent via homophones,…

Autonomous vehicle platoons present near- and long-term opportunities to enhance operational efficiencies and save lives. The past 30 years have seen rapid development in the autonomous driving space, enabling new technologies that will…