AI RESEARCH
Pix2Fact: When Vision Is Not Enough -- Benchmarking Fine-Grained VQA with Web Verification on High-Resolution Real-World Scenes
arXiv CS.LG
•
ArXi:2602.00593v2 Announce Type: replace-cross Despite progress on general tasks, vision-language models (VLMs) still struggle with challenges that demand both fine-grained visual grounding and external knowledge, a synergy overlooked by existing benchmarks that evaluate these abilities in isolation. To fill this void, we