Efficient_UG
Collection
Resources for “Understanding and Harnessing Sparsity in Unified Multimodal Models”, including the paper and efficient BAGEL-MoE checkpoints. • 3 items • Updated • 1
Efficient and adaptive foundation models across language and multimodal intelligence.
Drop-Then-Recovery: How Redundant Are Vision-Language-Action Models?
Demystifying When Pruning Works via Representation Hierarchies