Blogs

How Many Visual Tokens Do We Need in Large Multimodal Models (LMMs)?

Nov 1, 2024

In this blog, we demonstrate the impact of the number of visual tokens on the performance of LMMs and discuss several strategies for reducing visual tokens.

English
Chinese

Bridging the Parallel Decoding of LLMs with the Diffusion Process

Oct 30, 2024

In this blog, we introduce Jacobi Decoding, a parallel decoding algorithm for LLMs and its connection to the diffusion process in terms of high-level concepts.

English
Chinese