LatestEval

AI & ML interests

We create LLMs benchmark and update it every half month to make it "uncheatable".

Recent Activity

liyucheng  authored a paper 27 days ago

SCBench: A KV Cache-Centric Analysis of Long-Context Methods

liyucheng  authored a paper 5 months ago

Data Contamination Report from the 2024 CONDA Shared Task

liyucheng  authored a paper 6 months ago

MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention

View all activity

Team members 1