相关论文: Disentangled Safety Adapters Enable Efficient Guar…

Multimodal Large Language Models (MLLMs) have serious security vulnerabilities.While safety alignment using multimodal datasets consisting of text and data of additional modalities can effectively enhance MLLM's security, it is costly to…

Mechanisms are designed to perform functions in various fields. Often, there is no unique mechanism that performs a well-defined function. For example, vehicle suspensions are designed to improve driving performance and ride comfort, but…

Adapting LLM agents to domain-specific tool calling remains notably brittle under evolving interfaces. Prompt and schema engineering is easy to deploy but often fragile under distribution shift and strict parsers, while continual…

Systems based on deep neural networks are vulnerable to adversarial attacks. Unrestricted adversarial attacks typically manipulate the semantic content of an image (e.g., color or texture) to create adversarial examples that are both…

In decentralized federated learning (FL), multiple clients collaboratively learn a shared machine learning (ML) model by leveraging their privately held datasets distributed across the network, through interactive exchange of the…

Guardrails have emerged as an alternative to safety alignment for content moderation of large language models (LLMs). Existing model-based guardrails have not been designed for resource-constrained computational portable devices, such as…

Bias mitigation of Language Models has been the topic of many studies with a recent focus on learning separate modules like adapters for on-demand debiasing. Besides optimizing for a modularized debiased model, it is often critical in…

Unseen shifts in environment dynamics, driven by hidden parameters such as friction or gravity, create a challenge for maintaining safety. We address this challenge by proposing Adaptive Shielding, a framework for safe reinforcement…

Sequence generation and prediction form a cornerstone of modern machine learning, with applications spanning natural language processing, program synthesis, and time-series forecasting. These tasks are typically modeled in an autoregressive…

While modern text-to-image models excel at prompt-based generation, they often lack the fine-grained control necessary for specific user requirements like spatial layouts or subject appearances. Multi-condition control addresses this, yet…

Anomalous Sound Detection (ASD) has gained significant interest through the application of various Artificial Intelligence (AI) technologies in industrial settings. Though possessing great potential, ASD systems can hardly be readily…

Object recognition is a key enabler across industry and defense. As technology changes, algorithms must keep pace with new requirements and data. New modalities and higher resolution sensors should allow for increased algorithm robustness.…

Safety post-training can improve the harmfulness and policy compliance of Large Language Models (LLMs), but it may also reduce general utility, a phenomenon often described as the \emph{alignment tax}. We study this trade-off through the…

Autonomous driving decision-making at unsignalized intersections is highly challenging due to complex dynamic interactions and high conflict risks. To achieve proactive safety control, this paper proposes a deep reinforcement learning (DRL)…

Despite recent advances in learning-based controllers for legged robots, deployments in human-centric environments remain limited by safety concerns. Most of these approaches use position-based control, where policies output target joint…

As large language models (LLMs) are overwhelmingly more and more integrated into various applications, ensuring they generate safe responses is a pressing need. Previous studies on alignment have largely focused on general…

Unsupervised Domain Adaptation (UDA) aims to bridge the gap between a source domain, where labelled data are available, and a target domain only represented with unlabelled data. If domain invariant representations have dramatically…

As power systems are undergoing a significant transformation with more uncertainties, less inertia and closer to operation limits, there is increasing risk of large outages. Thus, there is an imperative need to enhance grid emergency…

Despite its significant success, object detection in traffic and transportation scenarios requires time-consuming and laborious efforts in acquiring high-quality labeled data. Therefore, Unsupervised Domain Adaptation (UDA) for object…

AI support of collaborative interactions entails mediating potential misalignment between interlocutor beliefs. Common preference alignment methods like DPO excel in static settings, but struggle in dynamic collaborative tasks where the…