English
Related papers

Related papers: Layer-wise Alignment: Examining Safety Alignment A…

200 papers

The development of Vision-Language-Action (VLA) models has been significantly accelerated by pre-trained Vision-Language Models (VLMs). However, most existing end-to-end VLAs treat the VLM primarily as a multimodal encoder, directly mapping…

Robotics · Computer Science 2026-04-29 Yi Chen , Yuying Ge , Hui Zhou , Mingyu Ding , Yixiao Ge , Xihui Liu

Autonomous driving systems often infer pedestrian yielding behavior from geometric and kinematic cues alone, limiting their ability to reason about visual scene context and age-dependent behavioral variability. This limitation can produce…

Systems and Control · Electrical Eng. & Systems 2026-04-28 Qingwen Pu , Kun Xie , Yuxiang Liu

Safe autonomous systems in complex environments require robust road anomaly segmentation to identify unknown obstacles. However, existing approaches often rely on pixel-level statistics to determine whether a region appears anomalous. This…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Zhuolin He , Jiacheng Tang , Jian Pu , Xiangyang Xue

Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in multimodal understanding and generation, yet their vulnerability to adversarial attacks raises significant robustness concerns. While existing effective…

Computer Vision and Pattern Recognition · Computer Science 2026-02-05 Hefei Mei , Zirui Wang , Shen You , Minjing Dong , Chang Xu

Recent advances in fine-tuning Vision-Language Models (VLMs) have witnessed the success of prompt tuning and adapter tuning, while the classic model fine-tuning on inherent parameters seems to be overlooked. It is believed that fine-tuning…

Computer Vision and Pattern Recognition · Computer Science 2024-11-20 Ming Li , Jike Zhong , Chenxin Li , Liuzhuozheng Li , Nie Lin , Masashi Sugiyama

Vision-Language-Action (VLA) models inherit strong priors from pretrained Vision-Language Models (VLMs), but naive fine-tuning often disrupts these representations and harms generalization. Existing fixes -- freezing modules or applying…

Computer Vision and Pattern Recognition · Computer Science 2025-11-26 Chengyue Huang , Mellon M. Zhang , Robert Azarcon , Glen Chou , Zsolt Kira

Large Vision-Language Models (LVLMs) demonstrate exceptional performance across multimodal tasks, yet remain vulnerable to jailbreak attacks that bypass built-in safety mechanisms to elicit restricted content generation. Existing black-box…

Computation and Language · Computer Science 2025-06-23 Lei Jiang , Zixun Zhang , Zizhou Wang , Xiaobing Sun , Zhen Li , Liangli Zhen , Xiaohua Xu

Instruction-following Vision Large Language Models (VLLMs) have achieved significant progress recently on a variety of tasks. These approaches merge strong pre-trained vision models and large language models (LLMs). Since these components…

Machine Learning · Computer Science 2024-02-20 Yiyang Zhou , Chenhang Cui , Rafael Rafailov , Chelsea Finn , Huaxiu Yao

Recent advancements in large language models (LLMs) have accelerated progress toward artificial general intelligence, yet their potential to generate harmful content poses critical safety challenges. Existing alignment methods often…

Computation and Language · Computer Science 2025-10-08 Kehua Feng , Keyan Ding , Yuhao Wang , Menghan Li , Fanjunduo Wei , Xinda Wang , Qiang Zhang , Huajun Chen

The deployment of large language models (LLMs) raises significant ethical and safety concerns. While LLM alignment techniques are adopted to improve model safety and trustworthiness, adversaries can exploit these techniques to undermine…

Cryptography and Security · Computer Science 2026-04-10 Rui Zhang , Hongwei Li , Yun Shen , Xinyue Shen , Wenbo Jiang , Guowen Xu , Yang Liu , Michael Backes , Yang Zhang

Vision-Language Models (VLMs) demonstrate impressive capabilities across multimodal tasks, yet exhibit systematic spatial reasoning failures, achieving only 49% (CLIP) to 54% (BLIP-2) accuracy on basic directional relationships. For safe…

Computer Vision and Pattern Recognition · Computer Science 2026-01-21 Muhammad Imran , Yugyung Lee

In this paper, we introduce a novel technique for content safety and prompt injection classification for Large Language Models. Our technique, Layer Enhanced Classification (LEC), trains a Penalized Logistic Regression (PLR) classifier on…

Computation and Language · Computer Science 2024-12-19 Mason Sawtell , Tula Masterman , Sandi Besen , Jim Brown

Multimodal large language models (MLLMs) typically extract visual features from the final layers of a pretrained Vision Transformer (ViT). This widespread deep-layer bias, however, is largely driven by empirical convention rather than…

Computer Vision and Pattern Recognition · Computer Science 2025-10-13 Haoran Chen , Junyan Lin , Xinghao Chen , Yue Fan , Jianfeng Dong , Xin Jin , Hui Su , Jinlan Fu , Xiaoyu Shen

Multi-modal large language models (MLLMs) are expected to support multi-turn queries of interchanging image and text modalities in production. However, the current MLLMs trained with visual-question-answering (VQA) datasets could suffer…

Computation and Language · Computer Science 2024-11-06 Shengzhi Li , Rongyu Lin , Shichao Pei

Vision-Language Models (VLMs) extend large language models with visual reasoning, but their multimodal design also introduces new, underexplored vulnerabilities. Existing multimodal red-teaming methods largely rely on brittle templates,…

Cryptography and Security · Computer Science 2026-05-27 Qilin Liao , Anamika Lochab , Ruqi Zhang

A dominant assumption in Multimodal Language Model (MLLM) research is that its performance is largely inherited from the LLM backbone, given its immense parameter scale and remarkable capabilities. This has created a void in the…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Junha Song , Sangdoo Yun , Dongyoon Han , Jaegul Choo , Byeongho Heo

Hallucinations remain a persistent challenge for vision-language models (VLMs), which often describe nonexistent objects or fabricate facts. Existing detection methods typically operate after text generation, making intervention both costly…

Computer Vision and Pattern Recognition · Computer Science 2026-03-06 Sai Akhil Kogilathota , Sripadha Vallabha E G , Luzhe Sun , Jiawei Zhou

Aligning large VLMs with human preferences is a challenging task, as methods like RLHF and DPO often overfit to textual information or exacerbate hallucinations. Although augmenting negative image samples partially addresses these pitfalls,…

Computer Vision and Pattern Recognition · Computer Science 2025-05-28 Fatemeh Pesaran Zadeh , Yoojin Oh , Gunhee Kim

Vision-language pre-training (VLP) methods are blossoming recently, and its crucial goal is to jointly learn visual and textual features via a transformer-based architecture, demonstrating promising improvements on a variety of…

Computer Vision and Pattern Recognition · Computer Science 2023-09-01 Weihan Wang , Zhen Yang , Bin Xu , Juanzi Li , Yankui Sun

Most existing vision-language pre-training (VLP) approaches adopt cross-modal masked language modeling (CMLM) to learn vision-language associations. However, we find that CMLM is insufficient for this purpose according to our observations:…

Computer Vision and Pattern Recognition · Computer Science 2023-09-06 Yunhao Gou , Tom Ko , Hansi Yang , James Kwok , Yu Zhang , Mingxuan Wang
‹ Prev 1 8 9 10 Next ›