Beyond Selection: Token Parameterization for Extreme Visual Token Compression Paper • 2609.35232 • Published 21 days ago • 9
Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling Paper • 2607.02980 • Published Jul 3 • 85
Scaling the Long Video Understanding of Multimodal Large Language Models via Visual Memory Mechanism Paper • 2603.29252 • Published Mar 31 • 1