Motion Control for Enhanced Complex Action Video Generation Paper • 2411.08328 • Published 14 days ago • 2
RegionBLIP: A Unified Multi-modal Pre-training Framework for Holistic and Regional Comprehension Paper • 2308.02299 • Published Aug 3, 2023
InfMLLM: A Unified Framework for Visual-Language Tasks Paper • 2311.06791 • Published Nov 12, 2023 • 3