English
Related papers

Related papers: SteerVLM: Robust Model Control through Lightweight…

200 papers

A fundamental challenge in autonomous driving is the integration of high-level, semantic reasoning for long-tail events with low-level, reactive control for robust driving. While large vision-language models (VLMs) trained on web-scale data…

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

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) are increasingly being used in a broad range of applications, bringing their security and behavioral control to the forefront. While existing approaches for behavioral control or output redirection, like system…

Computer Vision and Pattern Recognition · Computer Science 2025-08-13 Mansi Phute , Ravikumar Balakrishnan

As Vision Language Models (VLMs) are deployed across safety-critical applications, understanding and controlling their behavioral patterns has become increasingly important. Existing behavioral control methods face significant limitations:…

Computer Vision and Pattern Recognition · Computer Science 2025-10-01 Ravikumar Balakrishnan , Mansi Phute

Large language model (LLM) steering has emerged as a promising paradigm for controlling model behavior at inference time through targeted manipulation of hidden states, offering a lightweight alternative to expensive retraining. However,…

Computation and Language · Computer Science 2026-03-03 Haolei Xu , Xinyu Mei , Yuchen Yan , Rui Zhou , Wenqi Zhang , Weiming Lu , Yueting Zhuang , Yongliang Shen

The ability to follow instructions is crucial for numerous real-world applications of language models. In pursuit of deeper insights and more powerful capabilities, we derive instruction-specific vector representations from language models…

Computation and Language · Computer Science 2025-04-15 Alessandro Stolfo , Vidhisha Balachandran , Safoora Yousefi , Eric Horvitz , Besmira Nushi

Activation steering has emerged as a promising approach for efficiently adapting large language models (LLMs) to downstream behaviors. However, most existing steering methods rely on a single static direction per task or concept, making…

With recent progress in joint modeling of visual and textual representations, Vision-Language Pretraining (VLP) has achieved impressive performance on many multimodal downstream tasks. However, the requirement for expensive annotations…

Computer Vision and Pattern Recognition · Computer Science 2022-05-17 Zirui Wang , Jiahui Yu , Adams Wei Yu , Zihang Dai , Yulia Tsvetkov , Yuan Cao

This paper investigates how Large Language Models (LLMs) represent non-English tokens -- a question that remains underexplored despite recent progress. We propose a lightweight intervention method using representation steering, where a…

Computation and Language · Computer Science 2025-08-27 Omar Mahmoud , Buddhika Laknath Semage , Thommen George Karimpanal , Santu Rana

In high-stakes domains, small task-specific vision models are crucial due to their low computational requirements and the availability of numerous methods to explain their results. However, these explanations often reveal that the models do…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Alexander Koebler , Lukas Kuhn , Ingo Thon , Florian Buettner

Vision Language Models (VLMs) achieve strong performance on multimodal tasks but still suffer from hallucination and safety-related failures that persist even at scale. Steering offers a lightweight technique to improve model performance.…

Computer Vision and Pattern Recognition · Computer Science 2026-02-02 Youxu Shi , Suorong Yang , Dong Liu

Vision-language models (VLMs) pretrained on large-scale multimodal datasets encode rich visual and linguistic knowledge, making them a strong foundation for robotics. Rather than training robotic policies from scratch, recent approaches…

Recent vision-language (VL) studies have shown remarkable progress by learning generic representations from massive image-text pairs with transformer models and then fine-tuning on downstream VL tasks. While existing research has been…

Computer Vision and Pattern Recognition · Computer Science 2021-08-11 Jianfeng Wang , Xiaowei Hu , Pengchuan Zhang , Xiujun Li , Lijuan Wang , Lei Zhang , Jianfeng Gao , Zicheng Liu

Precise control over language model generation is vital for ensuring both safety and reliability. Although prompt engineering and steering are commonly used to intervene in model behaviors, the vast number of parameters in models often…

Computation and Language · Computer Science 2025-06-04 Mengru Wang , Ziwen Xu , Shengyu Mao , Shumin Deng , Zhaopeng Tu , Huajun Chen , Ningyu Zhang

Steering vectors (SVs) offer a lightweight way to control large language models (LLMs) at inference time by shifting hidden activations, providing a practical middle ground between prompting and fine-tuning. Yet SVs can be unreliable in…

Computation and Language · Computer Science 2026-02-03 Jiaqian Li , Yanshu Li , Kuan-Hao Huang

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

Despite significant progress in alignment, large language models (LLMs) remain vulnerable to adversarial attacks that elicit harmful behaviors. Activation steering techniques offer a promising inference-time intervention approach, but…

Machine Learning · Computer Science 2026-01-28 Quy-Anh Dang , Chris Ngo

Activation steering methods enable inference-time control of large language model (LLM) behavior without retraining, but current approaches face a fundamental trade-off: sample-efficient methods suboptimally capture steering signals from…

Machine Learning · Computer Science 2026-03-09 Kartik Sharma , Rakshit S. Trivedi

To operate effectively in the real world, robots should integrate multimodal reasoning with precise action generation. However, existing vision-language-action (VLA) models often sacrifice one for the other, narrow their abilities to…

Robotics · Computer Science 2026-03-04 Shuai Yang , Hao Li , Bin Wang , Yilun Chen , Yang Tian , Tai Wang , Hanqing Wang , Feng Zhao , Yiyi Liao , Jiangmiao Pang
‹ Prev 1 2 3 10 Next ›