43 10 85

Yucheng

liyucheng

https://liyucheng09.github.io

liyucheng09

AI & ML interests

Robust LLMs Evaluation and Efficient LLMs Inference.

Recent Activity

updated a dataset 5 days ago

RealTimeData/bbc_images_alltime

updated a dataset 5 days ago

RealTimeData/bbc_news_alltime

updated a dataset 5 days ago

RealTimeData/code_alltime

View all activity

Organizations

upvoted a paper about 1 month ago

ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows

Paper • 2505.19897 • Published May 26 • 102

upvoted a paper 2 months ago

MMInference: Accelerating Pre-filling for Long-Context VLMs via Modality-Aware Permutation Sparse Attention

Paper • 2504.16083 • Published Apr 22 • 9

upvoted a paper 7 months ago

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

Paper • 2412.10319 • Published Dec 13, 2024 • 10

upvoted a paper 11 months ago

Data Contamination Report from the 2024 CONDA Shared Task

Paper • 2407.21530 • Published Jul 31, 2024 • 10

upvoted an article 12 months ago

Article

MInference 1.0: 10x Faster Million Context Inference with a Single GPU

•

Jul 11, 2024

• 13

upvoted a paper about 1 year ago

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

Paper • 2407.02490 • Published Jul 2, 2024 • 28

upvoted 3 articles about 1 year ago

Article

Unlocking Longer Generation with Key-Value Cache Quantization

•

May 16, 2024

• 49

Article

Mixture of Experts Explained

and 5 others •

Dec 11, 2023

• 711

Article

Fine-tune Llama 3 with ORPO

•

Apr 22, 2024

• 237

Yucheng

AI & ML interests

Recent Activity

Organizations

liyucheng's activity

MInference 1.0: 10x Faster Million Context Inference with a Single GPU

Unlocking Longer Generation with Key-Value Cache Quantization

Mixture of Experts Explained

Fine-tune Llama 3 with ORPO