View from MSRA Shanghai Lab

System and Engineering Group

MSR Asia-Shanghai

下载

2024年8月

LLM2CLIP is a novel approach that embraces the power of LLMs to unlock CLIP’s potential. By fine-tuning the LLM in the caption space with contrastive learning, we extract its textual capabilities into the output embeddings, significantly improving the output layer’s…

Github for LLM2CLIP

2024年5月

MInference 1.0 leverages the dynamic sparse nature of LLMs’ attention, which exhibits some static patterns, to speed up the pre-filling for long-context LLMs. It first determines offline which sparse pattern each head belongs to, then approximates the sparse index online…

Github for MInference: Accelerating Pre-filling for Long-context LLMs via Dynamic Sparse Attention