Xiaoxia Wu

Principal Researcher, Together.AI

Joined

February 2019

Names

Xiaoxia Wu (Preferred)

Emails

****@math.utexas.edu (Confirmed)

****@ttic.edu (Confirmed)

****@uchicago.edu (Confirmed)

****@gmail.com (Confirmed)

****@microsoft.com (Confirmed)

****@together.ai (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

Principal Researcher

Together.AI (together.ai)

2024 – Present

Researcher

Microsoft (microsoft.com)

2021 – 2024

Postdoc

University of Chicago (uchicago.edu)

2020 – 2021

PhD student

University of Texas, Austin (utexas.edu)

2014 – 2020

Advisors, Relations & Conflicts

Postdoc Advisor

Rebecca Willett

2020 – 2021

PhD Advisor

Leon Bottou

2017 – 2020

PhD Advisor

Rachel Ward

2016 – 2020

Coworker

Simon Shaolei Du

2018 – 2019

Expertise

Optimization

2016 – Present

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
V1: Unifying Generation and Self-Verification for Parallel Reasoners
Harman Singh, Xiuyu Li, Kusha Sareen, Monishwaran Maheswaran, Sijun Tan, Xiaoxia Wu, Junxiong Wang, Alpay Ariyak, Qingyang Wu, Samir Khaki, Rishabh Tiwari, Long Lian, Yucheng Lu, Boyi Li, Alane Suhr, Ben Athiwaratkun, Kurt Keutzer
- SPOT
- Readers: Everyone
Search Your NVFP4 Scales!
Tanmaey Gupta, Hayden Prairie, Xiaoxia Wu, Reyna Abhyankar, Qingyang Wu, Austin Silveria, Pragaash Ponnusamy, Jue WANG, Ben Athiwaratkun, Shuaiwen Leon Song, Tri Dao, Daniel Y Fu, Christopher De Sa
- MLSys 2026
- Readers: Everyone
Understanding and Steering the Cognitive Behaviors of Reasoning Models at Test-Time
Zhenyu Zhang, Xiaoxia Wu, Zhongzhu Zhou, Qingyang Wu, Yineng Zhang, Pragaash Ponnusamy, Harikaran Subbaraj, Jue WANG, Shuaiwen Leon Song, Ben Athiwaratkun
- NeurIPS 2025 ER Workshop Spotlight
- Readers: Everyone
CARE: Covariance-Aware and Rank-Enhanced Decomposition for Enabling Multi-Head Latent Attention
Zhongzhu Zhou, Fengxiang Bie, Ziyan Chen, Zhenyu Zhang, Yibo Yang, Junxiong Wang, Ben Athiwaratkun, Xiaoxia Wu, Shuaiwen Leon Song
- ICLR 2026 Poster
- 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
Understanding and Steering the Cognitive Behaviors of Reasoning Models at Test-Time
Zhenyu Zhang, Xiaoxia Wu, Zhongzhu Zhou, Qingyang Wu, Yineng Zhang, Pragaash Ponnusamy, Harikaran Subbaraj, Jue WANG, Shuaiwen Leon Song, Ben Athiwaratkun
- ICLR 2026 Conference Desk Rejected Submission
- Readers: Everyone
Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encoding
Zhenyu Zhang, Runjin Chen, Shiwei Liu, Zhewei Yao, Olatunji Ruwase, Beidi Chen, Xiaoxia Wu, Zhangyang Wang
- NeurIPS 2024 poster
- Readers: Everyone
DeepSpeed4Science Initiative: Enabling Large-Scale Scientific Discovery through Sophisticated AI System Technologies
Shuaiwen Leon Song, Bonnie Kruft, Minjia Zhang, Conglong Li, Shiyang Chen, Chengming Zhang, Masahiro Tanaka, Xiaoxia Wu, Mohammed AlQuraishi, Gustaf Ahdritz, Christina Floristean, Rick L. Stevens, Venkatram Vishwanath, Arvind Ramanathan, Sam Foreman, Kyle Hippe, Prasanna Balaprakash, Yuxiong He
- NeurIPS2023-AI4Science Poster
- Readers: Everyone
ZeRO++: Extremely Efficient Collective Communication for Large Model Training
Guanhua Wang, Heyang Qin, Sam Ade Jacobs, Xiaoxia Wu, Connor Holmes, Zhewei Yao, Samyam Rajbhandari, Olatunji Ruwase, Feng Yan, Lei Yang, Yuxiong He
- ICLR 2024 poster
- Readers: Everyone

View all 20 publications

Co-Authors

View all 83 co-authors