Ziyang
People also call him Robin.
Wu

Email: zywu at berkeley dot edu/ zw287 at cornell dot edu (old)
Google Scholar


Bio

I am a third-year Ph.D. student advised by Prof. Yi Ma at UC Berkeley. I obtained my MS degree at Cornell University advised by Prof. Bharath Hariharan and Prof. Madeleine Udell. I graduated summa cum laude and received my BS degrees from Cornell University in Computer Science and in Operations Research. I also spent one year working as a researcher advised by Prof. Harry Shum at International Digital Economy Academy (IDEA) in Shenzhen, China. My primary research interests lie in machine learning and computer vision.


Publications

(* indicates equal contribution)

Preprints

Token Statistics Transformer: Linear-Time Attention via Variational Rate Reduction
Ziyang Wu , Tianjiao Ding, Druv Pai, Jingyuan Zhang, Weida Wang, Yaodong Yu, Yi Ma, Benjamin Haeffele
[link(soon)]

Conferences & Journals

When Do We Not Need Larger Vision Models?
Baifeng Shi, Ziyang Wu , Maolin Mao, Xin Wang, Trevor Darrell
European Conference on Computer Vision (ECCV), 2024
[arxiv]

LLoCO: Learning Long Contexts Offline
Sijun Tan, Xiuyu Li, Shishir Patil, Ziyang Wu , Tianjun Zhang, Kurt Keutzer, Joseph E. Gonzalez, Raluca Ada Popa
Empirical Methods in Natural Language Processing (EMNLP), 2024
[arxiv]

Masked Completion via Structured Diffusion with White-Box Transformers
Druv Pai, Ziyang Wu , Tianzhe Chu, Sam Buchanan, Yaodong Yu, Yi Ma
International Conference on Learning Representations (ICLR), 2024
[link]

Emergence of Segmentation with Minimalistic White-Box Transformers
Yaodong Yu, Tianzhe Chu, Shengbang Tong, Ziyang Wu , Druv Pai, Sam Buchanan, Yi Ma
Conference on Parsimony and Learning (CPAL), 2024
[arxiv]

White-Box Transformers via Sparse Rate Reduction
Yaodong Yu, Sam Buchanan, Druv Pai, Tianzhe Chu, Ziyang Wu , Shengbang Tong, Benjamin D Haeffele, Yi Ma
Conference on Neural Information Processing Systems (NeurIPS), 2023
[arxiv]

Incremental Learning of Structured Memory via Closed-Loop Transcription
Shengbang Tong, Xili Dai, Ziyang Wu , Mingyang Li, Brent Yi, Yi Ma
International Conference on Learning Representations (ICLR), 2023
[arxiv]

Closed-Loop Data Transcription to an LDR via Minimaxing Rate Reduction
Xili Dai*, Shengbang Tong*, Mingyang Li*, Ziyang Wu* , Kwan Ho Ryan Chan, Pengyuan Zhai, Yaodong Yu, Michael Psenka, Xiaojun Yuan, Heung-Yeung Shum, Yi Ma
MDPI Entropy, 2022
[link] [arxiv]

Efficient Maximal Coding Rate Reduction by Variational Forms
Christina Baek*, Ziyang Wu*, Kwan Ho Ryan Chan, Tianjiao Ding, Yi Ma, Benjamin Haeffele
Conference of Computer Vision and Pattern Recognition (CVPR), 2022
[link]

How Low Can We Go: Trading Memory for Error in Low-Precision Training
Chengrun Yang*, Ziyang Wu* , Jerry Chee, Christopher De Sa, Madeleine Udell
International Conference on Learning Representations (ICLR), 2022
[link] [arxiv] [code]

Incremental Learning via Rate Reduction
Ziyang Wu* , Christina Baek*, Chong You, Yi Ma
Conference of Computer Vision and Pattern Recognition (CVPR), 2021
ICML Workshop on Theory and Foundation of Continual Learning, 2021 (Oral Presentation)
[arxiv]

Can We Characterize Tasks Without Labels or Features
Bram Wallace*, Ziyang Wu* , Bharath Hariharan
Conference of Computer Vision and Pattern Recognition (CVPR), 2021
[link] [code]

TenIPS: Inverse Propensity Sampling for Tensor Completion
Chengrun Yang, Lijun Ding, Ziyang Wu , Madeleine Udell
NeurIPS 2020 Workshop on Optimization for Machine Learning (OPT), 2020 (Oral Presentation)
International Conference on Artificial Intelligence and Statistics (AISTATS), 2021
[arxiv]

AutoML Pipeline Selection: Efficiently Navigating the Combinatorial Space
Chengrun Yang, Jicong Fan, Ziyang Wu , Madeleine Udell
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2020
[link] [code]


Talks

Maximizing Rate Reduction: Principle and Applications
International Digital Economy Academy (IDEA), Oct. 2021

Incremental Learning via Rate Reduction
ICML Workshop on Theory and Foundation of Continual Learning, Jul. 2021
[link]


Teaching

CS 4700 (Fall 2018, Fall 2019, Fall 2020): Foundations of Artificial Intelligence (Teaching Assistant)

CS 2800 (Fall 2016, Spring 2021): Discrete Structures (Teaching Assistant)

CS 4670/5670 (Spring 2020): Introduction to Computer Vision (Teaching Assistant)

CS 4820 (Fall 2017, Summer 2020): Introduction to Algorithms (Teaching Assistant)

CS 3110 (Spring 2017): Data Structures and Functional Programming (Teaching Assistant)


Acknowledgement

Thanks Haozhi Qi for sharing this html template.