Grounding Computer Use Agents on Human Demonstrations Paper • 2511.07332 • Published Nov 10, 2025 • 106
CulturalFrames: Assessing Cultural Expectation Alignment in Text-to-Image Models and Evaluation Metrics Paper • 2506.08835 • Published Jun 10, 2025
UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and Interaction Paper • 2503.15661 • Published Mar 19, 2025 • 2
LIVS: A Pluralistic Alignment Dataset for Inclusive Public Spaces Paper • 2503.01894 • Published Feb 27, 2025 • 2
BigDocs: An Open and Permissively-Licensed Dataset for Training Multimodal Models on Document and Code Tasks Paper • 2412.04626 • Published Dec 5, 2024 • 13
