AIBullisharXiv – CS AI · Mar 127/10
🧠
Taking Shortcuts for Categorical VQA Using Super Neurons
Researchers introduce Super Neurons (SNs), a new method that probes raw activations in Vision Language Models to improve classification performance while achieving up to 5.10x speedup. Unlike Sparse Attention Vectors, SNs can identify discriminative neurons in shallow layers, enabling extreme early exiting from the first layer at the first generated token.