OpenReview
.net
OpenReview
.net
Login
OpenReview
.net
Login
Tsai-chuan Wu
Researcher, Advanced Micro Devices
Researcher, Together AI
Joined
October 2019
Names
Tsai-chuan Wu
(Preferred)
,
Robert Wu
,
Caiquan Wu
,
Rupert Wu
,
Robert CQ Wu
Emails
****@outlook.com
(Confirmed)
,
****@mail.utoronto.ca
(Confirmed)
,
****@cs.toronto.edu
(Confirmed)
,
****@utoronto.ca
(Confirmed)
,
****@together.ai
(Confirmed)
,
****@gmail.com
(Confirmed)
,
****@alumni.utoronto.ca
(Confirmed)
,
****@amd.com
(Confirmed)
Personal Links
Homepage
Google Scholar
ORCID
LinkedIn
Career & Education History
Researcher
Advanced Micro Devices
(amd.com)
2026
–
Present
Researcher
Together AI
(together.ai)
2025
–
2026
MS student
Computer Science,
Department of Computer Science, University of Toronto
(cs.toronto.edu)
2022
–
2024
Undergrad student
Computer Science,
University of Toronto
(toronto.edu)
2017
–
2022
Advisors, Relations & Conflicts
Manager
Sina Rafati
2026
–
Present
Manager
Sharon Zhou
2026
–
Present
Coworker
Burak Uzkent
2026
–
Present
Manager
Ben Athiwaratkun
2025
–
2026
Manager
Ce Zhang
2025
–
2026
Coauthor
Xiaoxia Wu
2025
–
2026
Coauthor
Zhongzhu Zhou
2025
–
2025
Coworker
David Glukhov
2022
–
2024
Coworker
Yubo Gao
2022
–
2024
MSc Advisor
Vardan Papyan
2022
–
2024
Mentor
George Alexandru Adam
2021
–
2024
Coauthor
Rohan Jain
2021
–
2022
Coauthor
Nayan Saxena
2021
–
2022
Expertise
Language Modelling
2022
–
Present
Machine Learning Systems
2022
–
Present
Deep Learning Theory
2021
–
Present
Automated Machine Learning
2021
–
2022
Publications
Kitty: Accurate and Efficient 2-bit KV Cache Quantization with Dynamic Channel-wise Precision Boost
Haojun Xia
,
Xiaoxia Wu
,
Jisen Li
,
Tsai-chuan Wu
,
Junxiong Wang
,
Jue WANG
,
Chenxi Li
,
Aman Singhal
,
Alay Dilipbhai Shah
,
Alpay Ariyak
,
Donglin Zhuang
,
Zhongzhu Zhou
,
Ben Athiwaratkun
,
Zhen Zheng
,
Shuaiwen Leon Song
MLSys 2026
Readers:
Everyone
Opportunistic Expert Activation: Batch-Aware Expert Routing for Faster Decode Without Retraining
Costin-Andrei Oncescu
,
Qingyang Wu
,
Wai Tong Chung
,
Robert Wu
,
Bryan Gopal
,
Junxiong Wang
,
Tri Dao
,
Ben Athiwaratkun
CoRR 2025
Readers:
Everyone
Kitty: Accurate and Efficient 2-bit KV Cache Quantization with Dynamic Channel-wise Precision Boost
Haojun Xia
,
Xiaoxia Wu
,
Jisen Li
,
Robert Wu
,
Junxiong Wang
,
Jue Wang
,
Chenxi Li
,
Aman Singhal
,
Alay Dilipbhai Shah
,
Alpay Ariyak
,
Donglin Zhuang
,
Zhongzhu Zhou
,
Ben Athiwaratkun
,
Zhen Zheng
,
Shuaiwen Leon Song
CoRR 2025
Readers:
Everyone
Imitate Optimal Policy: Prevail and Induce Action Collapse in Policy Gradient
Zhongzhu Zhou
,
Yibo Yang
,
Ziyan Chen
,
Fengxiang Bie
,
Haojun Xia
,
Xiaoxia Wu
,
Robert Wu
,
Ben Athiwaratkun
,
Bernard Ghanem
,
Shuaiwen Leon Song
Submitted to ICLR 2026
Readers:
Everyone
Imitate Optimal Policy: Prevail and Induce Action Collapse in Policy Gradient
Zhongzhu Zhou
,
Yibo Yang
,
Ziyan Chen
,
Fengxiang Bie
,
Haojun Xia
,
Xiaoxia Wu
,
Robert Wu
,
Ben Athiwaratkun
,
Bernard Ghanem
,
Shuaiwen Leon Song
CoRR 2025
Readers:
Everyone
SEE-2-SOUND: Zero-Shot Spatial Environment-to-Spatial Sound
Rishit Dagli
,
Shivesh Prakash
,
Robert Wu
,
Houman Khosravani
Crossref
Readers:
Everyone
SEE-2-SOUND: Zero-Shot Spatial Environment-to-Spatial Sound
Rishit Dagli
,
Shivesh Prakash
,
Robert Wu
,
Houman Khosravani
ICML 2024 FM-Wild Workshop Poster
Readers:
Everyone
Linguistic Collapse: Neural Collapse in (Large) Language Models
Robert Wu
,
Vardan Papyan
NeurIPS 2024 poster
Readers:
Everyone
Linguistic Collapse: Neural Collapse in (Large) Language Models
Robert Wu
,
Vardan Papyan
CoRR 2024
Readers:
Everyone
View all 17 publications
Co-Authors
Alay Dilipbhai Shah
Alpay Ariyak
Aman Singhal
Ben Athiwaratkun
Bernard Ghanem
Bryan Gopal
Chenxi Li
Costin-Andrei Oncescu
Donglin Zhuang
Fengxiang Bie
Haojun Xia
Houman Khosravani
Jisen Li
Jue WANG
Jue Wang
Junxiong Wang
Nayan Saxena
Qingyang Wu
Rishit Dagli
Rohan Jain
Shivesh Prakash
Shuaiwen Leon Song
Tri Dao
Vardan Papyan
Wai Tong Chung
View all 30 co-authors