{"type":"link","version":"1.0","title":"Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?","author_name":"AI Archs","author_url":"https://ai-arch.pages.dev","provider_name":"AI Archs","provider_url":"https://ai-arch.pages.dev","url":"https://ai-arch.pages.dev/n/arxiv2302.11713","thumbnail_url":"https://ai-arch.pages.dev/og/arxiv2302.11713.png","thumbnail_width":1200,"thumbnail_height":630}