Wenqi Zhang

icon indicating a website link https://zwq2018.github.io/

icon company Zhejiang University icon location Hangzhou icon location I am a final-year Ph.D candidate at Zhejiang University. My research interests include LLMs and VLMs. My personal pages: https://zwq2018.github.io

Results 6 issues of Wenqi Zhang

about training use gpu or cpu

4 comment

hello ,i have a question for this : if i train with gpu ,the training process will get stuck ,i do not know why, but if i train with cpu...

bug
improvements

video

https://github.com/zwq2018/Agent-Pro/assets/44236100/95fcde18-ffbb-48da-8917-81e1af74b0c3

Update a chart understanding paper

We add a chart and table understanding method: Multi-modal Self-instruct. This strategy synthesizes a large number of diverse abstract charts through code-based LLM, including tables, maps, instrument dials, and high-quality...

Update README.md

Add multimodal reasoning papers

Add Embodied Reasoner

Hello, thank you for maintaining this awesome repository!I’d like to sincerely recommend Embodied Reasoner, a model that extends O1-style reasoning to interactive embodied tasks.It is capable of processing lengthy, image-action...

Add Embodied Reasoner

Hello, thank you for maintaining this awesome repository!I’d like to sincerely recommend Embodied Reasoner, a model that extends O1-style reasoning to interactive embodied tasks.It is capable of processing lengthy, image-action...