Crowdsource, Crawl, or Generate? Creating SEA-VL, a Multicultural Vision-Language Dataset for Southeast Asia Paper • 2503.07920 • Published Mar 10 • 97
SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills Paper • 2504.07079 • Published 15 days ago • 11
VisualPuzzles: Decoupling Multimodal Reasoning Evaluation from Domain Knowledge Paper • 2504.10342 • Published 10 days ago • 10
Pangea: A Fully Open Multilingual Multimodal LLM for 39 Languages Paper • 2410.16153 • Published Oct 21, 2024 • 45
Harnessing Webpage UIs for Text-Rich Visual Understanding Paper • 2410.13824 • Published Oct 17, 2024 • 32
OpenDevin: An Open Platform for AI Software Developers as Generalist Agents Paper • 2407.16741 • Published Jul 23, 2024 • 72