Crowdsource, Crawl, or Generate? Creating SEA-VL, a Multicultural Vision-Language Dataset for Southeast Asia Paper • 2503.07920 • Published Mar 10 • 98
SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills Paper • 2504.07079 • Published Apr 9 • 11
VisualPuzzles: Decoupling Multimodal Reasoning Evaluation from Domain Knowledge Paper • 2504.10342 • Published Apr 14 • 11
VisualPuzzles: Decoupling Multimodal Reasoning Evaluation from Domain Knowledge Paper • 2504.10342 • Published Apr 14 • 11
VisualPuzzles: Decoupling Multimodal Reasoning Evaluation from Domain Knowledge Paper • 2504.10342 • Published Apr 14 • 11 • 2