中文
相关论文

相关论文: A Framework for Evaluating Vision-Language Model S…

200 篇论文

This thesis explores a multimodal AI framework for enhancing construction safety through the combined analysis of textual and visual data. In safety-critical environments such as construction sites, accident data often exists in multiple…

人工智能 · 计算机科学 2025-11-21 Islem Sahraoui

Vision-language models (VLMs) often inherit the biases and unsafe associations present within their large-scale training dataset. While recent approaches mitigate unsafe behaviors, their evaluation focuses on how safe the model is on unsafe…

计算机视觉与模式识别 · 计算机科学 2026-01-13 Moreno D'Incà , Elia Peruzzo , Xingqian Xu , Humphrey Shi , Nicu Sebe , Massimiliano Mancini

The increasing integration of Visual Language Models (VLMs) into AI systems necessitates robust model alignment, especially when handling multimodal content that combines text and images. Existing evaluation datasets heavily lean towards…

计算与语言 · 计算机科学 2026-03-05 Gabriel Downer , Sean Craven , Damian Ruck , Jake Thomas

This paper surveys evaluation techniques to enhance the trustworthiness and understanding of Large Language Models (LLMs). As reliance on LLMs grows, ensuring their reliability, fairness, and transparency is crucial. We explore algorithmic…

计算与语言 · 计算机科学 2024-06-05 Nik Bear Brown

Large Language Models (LLMs) have shown promise in tasks like code translation, prompting interest in their potential for automating software vulnerability detection (SVD) and patching (SVP). To further research in this area, establishing a…

软件工程 · 计算机科学 2024-09-18 Arastoo Zibaeirad , Marco Vieira

Consistent high-quality nursing care is essential for patient safety, yet current nursing education depends on subjective, time-intensive instructor feedback in training future nurses, which limits scalability and efficiency in their…

人工智能 · 计算机科学 2025-09-23 Shen Chang , Dennis Liu , Renran Tian , Kristen L. Swartzell , Stacie L. Klingler , Amy M. Nagle , Nan Kong

We propose general visual inspection model using Vision-Language Model~(VLM) with few-shot images of non-defective or defective products, along with explanatory texts that serve as inspection criteria. Although existing VLM exhibit high…

计算机视觉与模式识别 · 计算机科学 2025-02-14 Shiryu Ueno , Yoshikazu Hayashi , Shunsuke Nakatsuka , Yusei Yamada , Hiroaki Aizawa , Kunihito Kato

Safety evaluation of multimodal foundation models often treats vision and language inputs separately, missing risks from joint interpretation where benign content becomes harmful in combination. Existing approaches also fail to distinguish…

The pursuit of leaderboard rankings in Large Language Models (LLMs) has created a fundamental paradox: models excel at standardized tests while failing to demonstrate genuine language understanding and adaptability. Our systematic analysis…

计算与语言 · 计算机科学 2024-12-06 Sourav Banerjee , Ayushi Agarwal , Eishkaran Singh

As Large Language Models (LLMs) continue to revolutionize Natural Language Processing (NLP) applications, critical concerns about their trustworthiness persist, particularly in safety and robustness. To address these challenges, we…

软件工程 · 计算机科学 2025-10-16 Ruoyu Sun , Da Song , Jiayang Song , Yuheng Huang , Lei Ma

Traditional vulnerability detection methods rely heavily on predefined rule matching, which often fails to capture vulnerabilities accurately. With the rise of large language models (LLMs), leveraging their ability to understand code…

密码学与安全 · 计算机科学 2025-11-26 Xiang Li , Yueci Su , Jiahao Liu , Zhiwei Lin , Yuebing Hou , Peiming Gao , Yuanchao Zhang

The reliability of Multimodal Large Language Models (MLLMs) in real-world settings is often undermined by sensitivity to irrelevant or distracting visual context, an aspect not captured by existing evaluation metrics. We introduce the…

计算机视觉与模式识别 · 计算机科学 2025-09-30 Hitesh Laxmichand Patel , Amit Agarwal , Srikant Panda , Hansa Meghwani , Karan Dua , Paul Li , Tao Sheng , Sujith Ravi , Dan Roth

We propose an efficient evaluation protocol for large vision-language models (VLMs). Given their broad knowledge and reasoning capabilities, multiple benchmarks are needed for comprehensive assessment, making evaluation computationally…

计算机视觉与模式识别 · 计算机科学 2025-04-15 Teppei Suzuki , Keisuke Ozawa

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,…

密码学与安全 · 计算机科学 2026-05-27 Qilin Liao , Anamika Lochab , Ruqi Zhang

Vision-language models (VLMs) are increasingly deployed as trusted authorities -- fact-checking images on social media, comparing products, and moderating content. Users implicitly trust that these systems perceive the same visual content…

密码学与安全 · 计算机科学 2026-05-07 Jie Zhang , Pura Peetathawatchai , Florian Tramèr , Avital Shafran

As machine learning (ML) systems increasingly permeate high-stakes settings such as healthcare, transportation, military, and national security, concerns regarding their reliability have emerged. Despite notable progress, the performance of…

机器学习 · 计算机科学 2023-08-01 Anthony Corso , David Karamadian , Romeo Valentin , Mary Cooper , Mykel J. Kochenderfer

Visual Language Models (VLMs) have achieved remarkable progress, yet their reliability under small, meaning-preserving input changes remains poorly understood. We present the first large-scale, systematic study of VLM robustness to benign…

计算机视觉与模式识别 · 计算机科学 2025-11-17 Amir Rosenfeld , Neta Glazer , Ethan Fetaya

Large Language Models (LLMs) are emerging as transformative tools for software vulnerability detection, addressing critical challenges in the security domain. Traditional methods, such as static and dynamic analysis, often falter due to…

密码学与安全 · 计算机科学 2025-02-19 Ze Sheng , Zhicheng Chen , Shuning Gu , Heqing Huang , Guofei Gu , Jeff Huang

While numerous recent benchmarks focus on evaluating generic Vision-Language Models (VLMs), they do not effectively address the specific challenges of geospatial applications. Generic VLM benchmarks are not designed to handle the…

Measuring urban safety perception is an important and complex task that traditionally relies heavily on human resources. This process often involves extensive field surveys, manual data collection, and subjective assessments, which can be…

计算机视觉与模式识别 · 计算机科学 2025-06-03 Jiaxin Zhang , Yunqin Li , Tomohiro Fukuda , Bowen Wang