https://arxiv.org/abs/2412.00447 ATP-LLaVA: Adaptive Token Pruning for Large Vision Language ModelsLarge Vision Language Models (LVLMs) have achieved significant success across multi-modal tasks. However, the computational cost of processing long visual tokens can be prohibitively expensive on resource-limited devices. Previous methods have identified rarxiv.org Pruning은 모델에 쓸모 없는 파라미터를 버리기 위해 하..