Feather the Throttle: Revisiting Visual Token Pruning for Vision-Language Model Acceleration Paper • 2412.13180 • Published 18 days ago • 12
Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference Paper • 2412.13663 • Published 17 days ago • 116
Flowing from Words to Pixels: A Framework for Cross-Modality Evolution Paper • 2412.15213 • Published 16 days ago • 25