How Does Vision-Language Adaptation Impact the Safety of Vision Language Models? Paper • 2410.07571 • Published Oct 10, 2024 • 2
The Coverage Principle: A Framework for Understanding Compositional Generalization Paper • 2505.20278 • Published 11 days ago • 7
TokenButler Collection TokenButler -- Predict token importance for all heads across the transformer in the first layer itself. Enable fine-grained token sparsity! • 6 items • Updated Mar 11 • 3