Showing 2024Show all
3 papers · 1 filter
cs.CV2024
Slicing Vision Transformer for Flexible Inference
Yitian Zhang, Huseyin Coskun, Xu Ma +6
Vision Transformers (ViT) is known for its scalability. In this work, we target to scale down a ViT to fit in an environment with dynamic-changing resource constraints. We observe…
cs.AI2024
SoupLM: Model Integration in Large Language and Multi-Modal Models
Yue Bai, Zichen Zhang, Jiasen Lu +1
Training large language models (LLMs) and multimodal LLMs necessitates significant computing resources, and existing publicly available LLMs are typically pre-trained on diverse, p…
cs.CV2024
Accessing Vision Foundation Models via ImageNet-1K
Yitian Zhang, Xu Ma, Yue Bai +2
Vision foundation models are renowned for the generalization ability due to massive training data. Nevertheless, they demand tremendous training resources, and the training data is…