中文
相关论文

相关论文: Evaluating Reasoning Faithfulness in Medical Visio…

200 篇论文

Vision-language models (VLMs) have shown impressive zero- and few-shot performance on real-world visual question answering (VQA) benchmarks, alluding to their capabilities as visual reasoning engines. However, the benchmarks being used…

计算与语言 · 计算机科学 2024-09-04 Aishik Nagar , Shantanu Jaiswal , Cheston Tan

Vision language models (VLMs) have achieved impressive performance across a variety of computer vision tasks. However, the multimodal reasoning capability has not been fully explored in existing models. In this paper, we propose a…

计算机视觉与模式识别 · 计算机科学 2025-12-08 Xintong Zhang , Zhi Gao , Bofei Zhang , Pengxiang Li , Xiaowen Zhang , Yang Liu , Tao Yuan , Yuwei Wu , Yunde Jia , Song-Chun Zhu , Qing Li

Vision-language models (VLMs) have demonstrated impressive performance by effectively integrating visual and textual information to solve complex tasks. However, it is not clear how these models reason over the visual and textual data…

人工智能 · 计算机科学 2025-04-15 Pouya Pezeshkpour , Moin Aminnaseri , Estevam Hruschka

The robustness of Vision Language Models (VLMs) is commonly assessed through output-level invariance, implicitly assuming that stable predictions reflect stable multimodal processing. In this work, we argue that this assumption is…

Large Vision-Language Models (LVLMs) achieve strong performance on visual question answering benchmarks, yet often rely on spurious correlations rather than genuine causal reasoning. Existing evaluations primarily assess the correctness of…

人工智能 · 计算机科学 2026-02-25 Dhita Putri Pratama , Soyeon Caren Han , Yihao Ding

Most production-level deployments for Visual Question Answering (VQA) tasks are still build as processing pipelines of independent steps including image pre-processing, object- and text detection, Optical Character Recognition (OCR) and…

计算机视觉与模式识别 · 计算机科学 2024-08-29 Bianca Lamm , Janis Keuper

Medical vision-language models (VLMs) combine computer vision (CV) and natural language processing (NLP) to analyze visual and textual medical data. Our paper reviews recent advancements in developing VLMs specialized for healthcare,…

计算机视觉与模式识别 · 计算机科学 2024-12-02 Iryna Hartsock , Ghulam Rasool

Vision Language Models (VLMs) have demonstrated strong reasoning capabilities in Visual Question Answering (VQA) tasks; however, their ability to perform Theory of Mind (ToM) tasks, such as inferring human intentions, beliefs, and mental…

计算机视觉与模式识别 · 计算机科学 2025-04-25 Ximing Wen , Mallika Mainali , Anik Sen

Visual Question Answering (VQA) holds great potential for assisting Blind and Low Vision (BLV) users, yet real-world usage remains challenging. Due to visual impairments, BLV users often take blurry or poorly framed photos and face…

计算机视觉与模式识别 · 计算机科学 2025-09-09 Wanyin Cheng , Zanxi Ruan

Natural language explanation in visual question answer (VQA-NLE) aims to explain the decision-making process of models by generating natural language sentences to increase users' trust in the black-box systems. Existing post-hoc methods…

计算与语言 · 计算机科学 2023-12-22 Chengen Lai , Shengli Song , Shiqi Meng , Jingyang Li , Sitong Yan , Guangneng Hu

Reasoning in vision-language models (VLMs) has recently attracted significant attention due to its broad applicability across diverse downstream tasks. However, it remains unclear whether the superior performance of VLMs stems from genuine…

计算机视觉与模式识别 · 计算机科学 2026-04-20 Yige Xu , Yongjie Wang , Zizhuo Wu , Kaisong Song , Jun Lin , Zhiqi Shen

Vision-Language Models (VLMs) have recently demonstrated incredible strides on diverse vision language tasks. We dig into vision-based deductive reasoning, a more sophisticated but less explored realm, and find previously unexposed…

人工智能 · 计算机科学 2024-10-02 Yizhe Zhang , He Bai , Ruixiang Zhang , Jiatao Gu , Shuangfei Zhai , Josh Susskind , Navdeep Jaitly

Purpose: Vision-language models (VLMs) have shown promising performance in surgical visual question answering (VQA). However, existing surgical VQA datasets often contain linguistic shortcuts, where question phrasing implicitly constrains…

计算机视觉与模式识别 · 计算机科学 2026-05-06 Jongmin Shin , Ka Young Kim , Eunki Cho , Seong Tae Kim , Namkee Oh

Recent advancements in multimodal techniques open exciting possibilities for models excelling in diverse tasks involving text, audio, and image processing. Models like GPT-4V, blending computer vision and language modeling, excel in complex…

计算与语言 · 计算机科学 2023-10-20 Xiang Zhang , Senyu Li , Zijun Wu , Ning Shi

Visual Question Answering (VQA) attracts much attention from both industry and academia. As a multi-modality task, it is challenging since it requires not only visual and textual understanding, but also the ability to align cross-modality…

计算机视觉与模式识别 · 计算机科学 2022-01-27 Peixi Xiong , Quanzeng You , Pei Yu , Zicheng Liu , Ying Wu

Vision-language models (VLMs) achieve strong multimodal performance but remain prone to relation hallucination, which requires accurate reasoning over inter-object interactions. We study the impact of visual perturbations, specifically…

计算机视觉与模式识别 · 计算机科学 2026-05-12 Philip Wootaek Shin , Ajay Narayanan Sridhar , Sivani Devarapalli , Rui Zhang , Jack Sampson , Vijaykrishnan Narayanan

Multimodal Large Language Models (MLLMs) have shown remarkable capability in assisting disease diagnosis in medical visual question answering (VQA). However, their outputs remain vulnerable to hallucinations (i.e., responses that contradict…

计算机视觉与模式识别 · 计算机科学 2026-01-27 Mengyuan Jin , Zehui Liao , Yong Xia

Recent advancements in Vision-Language Models (VLMs) have significantly impacted various industries. In agriculture, these multimodal capabilities hold great promise for applications such as precision farming, crop monitoring, pest…

Vision-Language Models (VLMs) have achieved remarkable progress in complex visual understanding across scientific and reasoning tasks. While performance benchmarking has advanced our understanding of these capabilities, the critical…

人工智能 · 计算机科学 2026-01-27 Asif Azad , Mohammad Sadat Hossain , MD Sadik Hossain Shanto , M Saifur Rahman , Md Rizwan Parvez

The increasing availability of multimodal data across text, tables, and images presents new challenges for developing models capable of complex cross-modal reasoning. Existing methods for Multimodal Multi-hop Question Answering (MMQA) often…

计算机视觉与模式识别 · 计算机科学 2025-04-14 Qi Zhi Lim , Chin Poo Lee , Kian Ming Lim , Kalaiarasi Sonai Muthu Anbananthen