English
Related papers

Related papers: Automating Steering for Safe Multimodal Large Lang…

200 papers

Activation-based control steers large language models (LLMs) by intervening on their internal representations during inference, and has emerged as an effective paradigm for controlling behaviors such as persona and style. However, existing…

Computation and Language · Computer Science 2026-05-29 Yingdong Shi , Ruiming Zhang , Changming Li , Zhiyu Yang , Kaixing Zhang , Jingyi Yu , Kan Ren

Traditional autonomous driving systems often struggle to connect high-level reasoning with low-level control, leading to suboptimal and sometimes unsafe behaviors. Recent advances in multimodal large language models (MLLMs), which process…

Robotics · Computer Science 2025-06-09 Jiawei Zhang , Xuan Yang , Taiqi Wang , Yu Yao , Aleksandr Petiushko , Bo Li

Autonomous driving has made significant strides through data-driven techniques, achieving robust performance in standardized tasks. However, existing methods frequently overlook user-specific preferences, offering limited scope for…

Robotics · Computer Science 2025-05-13 Chengkai Xu , Jiaqi Liu , Yicheng Guo , Yuhang Zhang , Peng Hang , Jian Sun

Robust alignment guardrails for large language models (LLMs) are becoming increasingly important with their widespread application. In contrast to previous studies, we demonstrate that inference-time activation interventions can bypass…

Computation and Language · Computer Science 2025-08-26 Paul Darm , Annalisa Riccardi

The safety and reliability of Automated Driving Systems (ADSs) must be validated prior to large-scale deployment. Among existing validation approaches, scenario-based testing has been regarded as a promising method to improve testing…

Software Engineering · Computer Science 2026-01-05 Yongqi Zhao , Ji Zhou , Dong Bi , Tomislav Mihalj , Jia Hu , Arno Eichberger

Multi-modal large language models (MLLMs) have made significant progress, yet their safety alignment remains limited. Typically, current open-source MLLMs rely on the alignment inherited from their language module to avoid harmful…

Cryptography and Security · Computer Science 2025-04-15 Yanbo Wang , Jiyang Guan , Jian Liang , Ran He

Activation steering is a promising technique for controlling LLM behavior by adding semantically meaningful vectors directly into a model's hidden states during inference. It is often framed as a precise, interpretable, and potentially…

Machine Learning · Computer Science 2026-02-17 Anton Korznikov , Andrey Galichin , Alexey Dontsov , Oleg Y. Rogov , Ivan Oseledets , Elena Tutubalina

Multimodal large language models (MLLMs) have shown satisfactory effects in many autonomous driving tasks. In this paper, MLLMs are utilized to solve joint semantic scene understanding and risk localization tasks, while only relying on…

Computer Vision and Pattern Recognition · Computer Science 2024-12-30 Jiaqi Fan , Jianhua Wu , Jincheng Gao , Jianhao Yu , Yafei Wang , Hongqing Chu , Bingzhao Gao

Mixture-of-Experts (MoE) architectures in Large Language Models (LLMs) have significantly reduced inference costs through sparse activation. However, this sparse activation paradigm also introduces new safety challenges. Since only a subset…

Cryptography and Security · Computer Science 2026-05-01 Jona te Lintelo , Lichao Wu , Marina Krček , Sengim Karayalçin , Stjepan Picek

Controlling undesirable Large Language Model (LLM) behaviors, such as the generation of unsafe content or failing to adhere to safety guidelines, often relies on costly fine-tuning. Activation steering provides an alternative for…

Computation and Language · Computer Science 2026-03-17 Amr Hegazy , Mostafa Elhoushi , Amr Alanwar

Ensuring the safety of Autonomous Driving Systems (ADS) requires realistic and reproducible test scenarios, yet extracting such scenarios from multimodal crash reports remains a major challenge. Large Language Models (LLMs) often…

Software Engineering · Computer Science 2025-11-26 Siwei Luo , Yang Zhang , Yao Deng , Linfeng Liang , Xi Zheng

Large Vision-Language Models (LVLMs) exhibit outstanding performance on vision-language tasks but struggle with hallucination problems. Through in-depth analysis of LVLM activation patterns, we reveal two key findings: 1) truthfulness and…

Computer Vision and Pattern Recognition · Computer Science 2026-02-26 Jianghao Yin , Qin Chen , Kedi Chen , Jie Zhou , Xingjiao Wu , Liang He

Vision-Language Models (VLMs) have achieved remarkable progress in multimodal reasoning tasks through enhanced chain-of-thought capabilities. However, this advancement also introduces novel safety risks, as these models become increasingly…

Computer Vision and Pattern Recognition · Computer Science 2025-10-22 Yinan Xia , Yilei Jiang , Yingshui Tan , Xiaoyong Zhu , Xiangyu Yue , Bo Zheng

The generation of corner cases has become increasingly crucial for efficiently testing autonomous vehicles prior to road deployment. However, existing methods struggle to accommodate diverse testing requirements and often lack the ability…

Robotics · Computer Science 2024-09-11 Qiujing Lu , Xuanhan Wang , Yiwei Jiang , Guangming Zhao , Mingyue Ma , Shuo Feng

Multimodal large language models (MLLMs) have shown remarkable capabilities in cross-modal understanding and reasoning, offering new opportunities for intelligent assistive systems, yet existing systems still struggle with risk-aware…

Robotics · Computer Science 2026-04-08 Renjun Gao

Steering methods influence Large Language Model behavior by identifying semantic directions in hidden representations, but are typically realized through inference-time activation interventions that apply a fixed, global modification to the…

Computation and Language · Computer Science 2026-03-04 Chung-En Sun , Ge Yan , Zimo Wang , Tsui-Wei Weng

Vision Language Models (VLMs) can produce unintended and harmful content when exposed to adversarial attacks, particularly because their vision capabilities create new vulnerabilities. Existing defenses, such as input preprocessing,…

Computer Vision and Pattern Recognition · Computer Science 2025-05-05 Han Wang , Gang Wang , Huan Zhang

Steering language models (LMs) by modifying internal activations is a popular approach for controlling text generation. Unsupervised dictionary learning methods, e.g., sparse autoencoders, can be scaled to produce many steering vectors, but…

Computation and Language · Computer Science 2025-06-05 Jiuding Sun , Sidharth Baskaran , Zhengxuan Wu , Michael Sklar , Christopher Potts , Atticus Geiger

Mixture-of-Experts (MoE) in Large Language Models (LLMs) routes each token through a subset of specialized Feed-Forward Networks (FFN), known as experts. We present SteerMoE, a framework to steer MoE models by detecting and controlling…

Computation and Language · Computer Science 2026-02-13 Mohsen Fayyaz , Ali Modarressi , Hanieh Deilamsalehy , Franck Dernoncourt , Ryan Rossi , Trung Bui , Hinrich Schütze , Nanyun Peng

Large Language Models (LLMs) have achieved impressive performance across diverse natural language processing tasks, but their growing power also amplifies potential risks such as jailbreak attacks that circumvent built-in safety mechanisms.…

Artificial Intelligence · Computer Science 2025-10-01 Qinjian Zhao , Jiaqi Wang , Zhiqiang Gao , Zhihao Dou , Belal Abuhaija , Kaizhu Huang