中文
相关论文

相关论文: The Security Threat of Compressed Projectors in La…

200 篇论文

Large Vision-Language Models (LVLMs) rely on vision encoders and Large Language Models (LLMs) to exhibit remarkable capabilities on various multi-modal tasks in the joint space of vision and language. However, typographic attacks, which…

计算机视觉与模式识别 · 计算机科学 2024-09-20 Hao Cheng , Erjia Xiao , Jindong Gu , Le Yang , Jinhao Duan , Jize Zhang , Jiahang Cao , Kaidi Xu , Renjing Xu

Benefiting from the powerful capabilities of Large Language Models (LLMs), pre-trained visual encoder models connected to an LLMs can realize Vision Language Models (VLMs). However, existing research shows that the visual modality of VLMs…

计算机视觉与模式识别 · 计算机科学 2024-05-24 Zhendong Liu , Yuanbi Nie , Yingshui Tan , Xiangyu Yue , Qiushi Cui , Chongjun Wang , Xiaoyong Zhu , Bo Zheng

Visual token compression is widely adopted to improve the inference efficiency of Large Vision-Language Models (LVLMs), enabling their deployment in latency-sensitive and resource-constrained scenarios. However, existing work has mainly…

密码学与安全 · 计算机科学 2026-01-21 Xiaomei Zhang , Zhaoxi Zhang , Leo Yu Zhang , Yanjun Zhang , Guanhong Tao , Shirui Pan

With the significant development of large models in recent years, Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities across a wide range of multimodal understanding and reasoning tasks. Compared to traditional…

计算机视觉与模式识别 · 计算机科学 2024-07-15 Daizong Liu , Mingyu Yang , Xiaoye Qu , Pan Zhou , Yu Cheng , Wei Hu

Large vision-language models (VLMs) such as GPT-4 have achieved unprecedented performance in response generation, especially with visual inputs, enabling more creative and adaptable interaction than large language models such as ChatGPT.…

计算机视觉与模式识别 · 计算机科学 2023-10-31 Yunqing Zhao , Tianyu Pang , Chao Du , Xiao Yang , Chongxuan Li , Ngai-Man Cheung , Min Lin

The deployment of multimodal large language models (MLLMs) has brought forth a unique vulnerability: susceptibility to malicious attacks through visual inputs. This paper investigates the novel challenge of defending MLLMs against such…

密码学与安全 · 计算机科学 2024-06-18 Renjie Pi , Tianyang Han , Jianshu Zhang , Yueqi Xie , Rui Pan , Qing Lian , Hanze Dong , Jipeng Zhang , Tong Zhang

Despite the excellent performance of vision-language pre-trained models (VLPs) on conventional VQA task, they still suffer from two problems: First, VLPs tend to rely on language biases in datasets and fail to generalize to…

计算机视觉与模式识别 · 计算机科学 2023-10-13 Qingyi Si , Yuanxin Liu , Zheng Lin , Peng Fu , Weiping Wang

The visual projector serves as an essential bridge between the visual encoder and the Large Language Model (LLM) in a Multimodal LLM (MLLM). Typically, MLLMs adopt a simple MLP to preserve all visual contexts via one-to-one transformation.…

计算机视觉与模式识别 · 计算机科学 2024-08-29 Wentong Li , Yuqian Yuan , Jian Liu , Dongqi Tang , Song Wang , Jie Qin , Jianke Zhu , Lei Zhang

Large language models have become increasingly prominent, also signaling a shift towards multimodality as the next frontier in artificial intelligence, where their embeddings are harnessed as prompts to generate textual content.…

计算机视觉与模式识别 · 计算机科学 2024-08-27 Jiachen Sun , Changsheng Wang , Jiongxiao Wang , Yiwei Zhang , Chaowei Xiao

With the rapid advancement of Large Vision-Language Models (LVLMs), ensuring their safety has emerged as a crucial area of research. This survey provides a comprehensive analysis of LVLM safety, covering key aspects such as attacks,…

密码学与安全 · 计算机科学 2025-02-24 Mang Ye , Xuankun Rong , Wenke Huang , Bo Du , Nenghai Yu , Dacheng Tao

Vision-Language Models (VLMs) extend the capabilities of Large Language Models (LLMs) by incorporating visual information, yet they remain vulnerable to jailbreak attacks, especially when processing noisy or corrupted images. Although…

计算机视觉与模式识别 · 计算机科学 2025-08-05 Jiawei Wang , Yushen Zuo , Yuanjun Chai , Zhendong Liu , Yicheng Fu , Yichun Feng , Kin-Man Lam

Large visual-language models (LVLMs) integrate aligned large language models (LLMs) with visual modules to process multimodal inputs. However, the safety mechanisms developed for text-based LLMs do not naturally extend to visual modalities,…

计算机视觉与模式识别 · 计算机科学 2025-07-29 Shen Li , Liuyi Yao , Wujia Niu , Lan Zhang , Yaliang Li

3D Vision-Language Models (VLMs), such as PointLLM and GPT4Point, have shown strong reasoning and generalization abilities in 3D understanding tasks. However, their adversarial robustness remains largely unexplored. Prior work in 2D VLMs…

计算机视觉与模式识别 · 计算机科学 2026-01-13 Chao Liu , Ngai-Man Cheung

Multi-modal Large Language Models (MLLMs) excel in vision-language tasks but remain vulnerable to visual adversarial perturbations that can induce hallucinations, manipulate responses, or bypass safety mechanisms. Existing methods seek to…

计算机视觉与模式识别 · 计算机科学 2025-02-04 Hashmat Shadab Malik , Fahad Shamshad , Muzammal Naseer , Karthik Nandakumar , Fahad Khan , Salman Khan

Recently, driven by advancements in Multimodal Large Language Models (MLLMs), Vision Language Action Models (VLAMs) are being proposed to achieve better performance in open-vocabulary scenarios for robotic manipulation tasks. Since…

计算机视觉与模式识别 · 计算机科学 2025-11-06 Hao Cheng , Erjia Xiao , Yichi Wang , Chengyuan Yu , Mengshu Sun , Qiang Zhang , Jiahang Cao , Yijie Guo , Ning Liu , Kaidi Xu , Jize Zhang , Chao Shen , Philip Torr , Jindong Gu , Renjing Xu

Compressed vision-language models (VLMs) are widely used to reduce memory and compute costs, making them a suitable choice for real-world deployment. However, compressing these models raises concerns about whether internal computations and…

人工智能 · 计算机科学 2026-03-27 Veeraraju Elluru , Arth Singh , Roberto Aguero , Ajay Agarwal , Debojyoti Das , Hreetam Paul

Current vision large language models (VLLMs) exhibit remarkable capabilities yet are prone to generate harmful content and are vulnerable to even the simplest jailbreaking attacks. Our initial analysis finds that this is due to the presence…

机器学习 · 计算机科学 2024-06-19 Yongshuo Zong , Ondrej Bohdal , Tingyang Yu , Yongxin Yang , Timothy Hospedales

Vision Language Models (VLMs) offer the exciting possibility of processing text as rendered images, bypassing the need for tokenizing the text into long token sequences. Since VLM image encoders map fixed-size images to a fixed number of…

计算机视觉与模式识别 · 计算机科学 2026-05-11 Roy Xie , Dan Friedman , Donghan Yu , Bowen Pan , Christopher Fifty , Jang-Hyun Kim , Xianzhi Du , Zhe Gan , Vivek Rathod , Bhuwan Dhingra

Recent advances in vision-language models (VLMs) have shown great promise in connecting images and text, but extending these models to long videos remains challenging due to the rapid growth in token counts. Models that compress videos by…

计算机视觉与模式识别 · 计算机科学 2025-05-19 Keunwoo Peter Yu , Achal Dave , Rares Ambrus , Jean Mercat

Large Vision-Language Models (LVLMs) have shown remarkable capabilities across a wide range of multimodal tasks. However, their integration of visual inputs introduces expanded attack surfaces, thereby exposing them to novel security…

计算与语言 · 计算机科学 2025-05-29 Juan Ren , Mark Dras , Usman Naseem
‹ 上一页 1 2 3 10 下一页 ›