Zhiqiu Xu

Zhiqiu Xu / Oscar /

I am a Ph.D. student at University of Pennsylvania, advised by Prof. Mayur Naik. I seek to understand how neural networks work and develop simple methods to improve how we train and use neural networks.

I complete my Master of Science degree from UC Berkeley, advised by Prof. Trevor Darrell , where I work on computer vision and representation learning. Before that, I was an undergraduate student at UC Berkeley, majoring in Computer Science and Applied Mathematics. I also interned at Twitter.

Always open to research collaboration, mentoring, and exciting discussions! Feel free to reach out via email or connect with me on social media below. You have my word that I will respond. (bots excluded, at least until they get nicer)

Email / Google Scholar / Twitter / Github / Wechat / Linkedin

News

(2024/01/16) Our paper Initializing Models with Larger Ones is accepted to ICLR 2024 as a spotlight presentation! Happy birthday to me 🎂
(2023/04/24) Our paper Dropout Reduces Underfitting is accepted to ICML 2023!
(2023/03/31) I will join University of Pennsylvania as a Ph.D. student in Fall 2023!

Research (* equal contribution)

	Delta Activations: A Representation for Finetuned Large Language Models Zhiqiu Xu, Amish Sethi, Mayur Naik, Ser-Nam Lim arXiv 2025 [paper] [code] [project page]
	Generative Modeling of Weights: Generalization or Memorization? Boya Zeng, Yida Yin, Zhiqiu Xu, Zhuang Liu arXiv 2025 [paper] [code] [project page]
	Idiosyncrasies in Large Language Models Mingjie Sun, Yida Yin, Zhiqiu Xu, J. Zico Kolter, Zhuang Liu ICML 2025 [paper] [code]
	A Coefficient Makes SVRG Effective Yida Yin, Zhiqiu Xu, Zhiyuan Li, Trevor Darrell, Zhuang Liu ICLR 2025 [paper] [code]
	Initializing Models with Larger Ones Zhiqiu Xu, Yanjie Chen, Kirill Vishniakov, Yida Yin, Zhiqiang Shen, Trevor Darrell, Lingjie Liu, Zhuang Liu ICLR 2024 (Spotlight) [paper] [code]
	Dropout Reduces Underfitting Zhuang Liu, Zhiqiu Xu, Joseph Jin, Zhiqiang Shen, Trevor Darrell ICML 2023 [paper] [code]
	Anytime Dense Prediction with Confidence Adaptivity Zhuang Liu, Zhiqiu Xu, Hung-ju Wang, Trevor Darrell, Evan Shelhamer ICLR 2022 [paper] [code]

Mentorship

I was closely mentored by Zhuang Liu and Ruiqi Zhong at UC Berkeley. They are primarily reasons why I dived into research. (a pleasant surprise since I wasn't planning for that)

Just like every other field in human society, the flourishing academic community is reliant on passing the torch of knowledge. If you are interested in my research and deep learning related topics and want to chat with me, please don't hesitate to reach out. Here is a list of students I have mentored. One of them said I was a legendary mentor, and let's trust his judgement for this time.

Joseph Jin (Databricks)

Maolin Mao

Yanjie Chen

Boya Zeng (now Ph.D. student at Princeton University)

Amish Sethi

Academic Services

Reviewer for ICLR, ICML, NeurIPS, CVPR, ICCV, ECCV, AAAI, AISTATS.

Miscellaneous

My Chinese name is pronounced as Shoe-Jee-Chyo. I will be very happy if you try to pronounce that in front of me. My name is Xu Zhiqiu. ‘Xu’ (徐) is my family name and conveys a sense of calm or gentle movement. ‘Zhi’ (之) is a classical possessive, and ‘Qiu’ (秋) means autumn.
I play poker. Statistically speaking, I have been quite lucky on that.
Occasionally, I post some vlogs on bilibili. Here's my homepage. I haven't done that for a while. But let me know if you want to see some by commenting.
My profile photo is shot in a studio, I never dress like that in real life.
I proudly named myself as Oscar after watching Shark Tale at 6 years old.

Website design from Jon Barron Borrowed from Ruiqi Zhong