Related papers: Automating Steering for Safe Multimodal Large Lang…

Multimodal Large Language Models (MLLMs) have enabled transformative advancements across diverse applications but remain susceptible to safety threats, especially jailbreak attacks that induce harmful outputs. To systematically evaluate and…

The rapid development of Multimodal Large Reasoning Models (MLRMs) has demonstrated broad application potential, yet their safety and reliability remain critical concerns that require systematic exploration. To address this gap, we conduct…

Safety evaluation and red-teaming of large language models remain predominantly text-centric, and existing frameworks lack the infrastructure to systematically test whether alignment generalizes to audio, image, and video inputs. We present…

Activation steering has emerged as a cost-effective paradigm for modifying large language model (LLM) behaviors. Existing methods typically intervene at the block level, steering the bundled activations of selected attention heads,…

In recent years, large language models have had a very impressive performance, which largely contributed to the development and application of artificial intelligence, and the parameters and performance of the models are still growing…

Decision-making and motion planning constitute critical components for ensuring the safety and efficiency of autonomous vehicles (AVs). Existing methodologies typically adopt two paradigms: decision then planning or generation then scoring.…

Recent advances in Large Language Models (LLMs) - particularly model scaling and test-time techniques - have greatly enhanced the reasoning capabilities of language models at the expense of higher inference costs. To lower inference costs,…

The safety alignment ability of Vision-Language Models (VLMs) is prone to be degraded by the integration of the vision module compared to its LLM backbone. We investigate this phenomenon, dubbed as ''safety alignment degradation'' in this…

Activation steering is a practical post-training model alignment technique to enhance the utility of Large Language Models (LLMs). Prior to deploying a model as a service, developers can steer a pre-trained model toward specific behavioral…

Autonomous vehicles (AVs) are poised to redefine transportation by enhancing road safety, minimizing human error, and optimizing traffic efficiency. The success of AVs depends on their ability to interpret complex, dynamic environments…

The rapid advancement of Large Language Models (LLMs) and Large Vision-Language Models (LVLMs) has enhanced our ability to process and generate human language and visual information. However, these models often struggle with complex,…

Using Large Language Models (LLMs) in real-world applications presents significant challenges, particularly in balancing computational efficiency with model performance. Optimizing acceleration after fine-tuning and during inference is…

The rapid development and deployment of large language models (LLMs) have introduced a new frontier in artificial intelligence, marked by unprecedented capabilities in natural language understanding and generation. However, the increasing…

How should one judge whether a given large language model (LLM) can reliably perform economic reasoning? Most existing LLM benchmarks focus on specific applications and fail to present the model with a rich variety of economic tasks. A…

Fine-tuning Large Language Models (LLMs) has emerged as a common practice for tailoring models to individual needs and preferences. The choice of datasets for fine-tuning can be diverse, introducing safety concerns regarding the potential…

Artificial intelligence (AI) plays a crucial role in autonomous driving (AD) research, propelling its development towards intelligence and efficiency. Currently, the development of AD technology follows two main technical paths:…

Multimodal Large Language Models (MLLMs) pose critical safety challenges, as they are susceptible not only to adversarial attacks such as jailbreaking but also to inadvertently generating harmful content for benign users. While internal…

Large Language Models (LLMs) continue to exhibit vulnerabilities to jailbreaking attacks: carefully crafted malicious inputs intended to circumvent safety guardrails and elicit harmful responses. As such, we present AutoAdv, a novel…

Controlling the behavior of large language models (LLMs) at inference time is essential for aligning outputs with human abilities and safety requirements. \emph{Activation steering} provides a lightweight alternative to prompt engineering…

Machine learning (ML) components are increasingly integrated into software products, yet their complexity and inherent uncertainty often lead to unintended and hazardous consequences, both for individuals and society at large. Despite these…