Qingyi Si's picture

Qingyi Si

QingyiSi

·

PhoebusSi

AI & ML interests

Large Language Models; Visual Question Answering; Visual & Language

Recent Activity

upvoted a paper 8 days ago

VideoReasonBench: Can MLLMs Perform Vision-Centric Complex Video Reasoning?

liked a dataset over 1 year ago

pleisto/wikipedia-cn-20230720-filtered

liked a dataset over 1 year ago

Skywork/SkyPile-150B

View all activity

Organizations

models 2

QingyiSi/Alpaca-CoT

Updated Jun 25, 2023 • 35

QingyiSi/text_imgcode_pair

Updated Jun 8, 2023

datasets 7

QingyiSi/Alpaca-CoT

Preview • Updated Sep 14, 2023 • 16.7k • 730

QingyiSi/docker_data

Updated Sep 7, 2023 • 7

QingyiSi/llava_data

Preview • Updated May 27, 2023 • 5 • 1

QingyiSi/OKVQA-imageBase64

Updated May 26, 2023 • 8

QingyiSi/VQA-VS

Preview • Updated May 26, 2023 • 5

QingyiSi/Thinking-while-Observing

Updated May 25, 2023 • 24 • 2

QingyiSi/mmC4-fewer-faces

Viewer • Updated Apr 24, 2023 • 22.8k • 23 • 3