Workspace-Bench 1.0: Benchmarking AI Agents on Workspace Tasks with Large-Scale File Dependencies Paper • 2605.03596 • Published May 5 • 10
Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs Paper • 2601.17058 • Published Jan 22 • 190
InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing Paper • 2603.09877 • Published Mar 10 • 49