Efficient machine learning systems
I'm an assistant professor of computer science at Rutgers University. My group studies how to train and serve large language models efficiently and evaluate them reliably. We currently focus on mixture-of-experts models and reinforcement learning for post-training.
Academic background
Previously, I was a Senior Project Scientist in the Machine Learning Department at CMU, working with Eric Xing. I earned my PhD in Computer Science from UW-Madison, advised by Dimitris Papailiopoulos.
Research focus
Research themesLLM infrastructure
Training, serving, and evaluating large models under real compute and memory constraints.
Federated and private ML
Learning across institutions when data is sensitive, distributed, or unevenly sampled.
Efficient optimization
Reducing computation and communication through compression, low-rank methods, and model fusion.
Selected publications
Full publication listK2-Horizon: A Frontier Fleet of Open Source Language Models
K2 Team (including Hongyi Wang), arXiv technical report, 2026.
Details
Abstract
K2-Horizon spans six open language models, from a 0.9B dense model to a mixture-of-experts model with 375B total parameters and 23B active per token. Four models share a 22-trillion-token training corpus, allowing researchers to compare dense and sparse architectures on the same data. The team released intermediate checkpoints, training logs, data pipelines, and code for training and evaluation.
Citation
K2 Team (including Hongyi Wang), arXiv technical report, 2026.
BibTeX
@misc{k2team2026k2horizonfrontierfleetopen,
title={{K2-Horizon}: A Frontier Fleet of Open Source Language Models},
author={{K2 Team} and Zhengzhong Liu and Haonan Li and Xuezhe Ma and Alexander Moreno and
Subham Sekhar Sahoo and Rupesh Kumar Srivastava and Mikhail Yurochkin and
Hadi Abdine and Yash Akhauri and Adharsh Babu and David Bellamy and Jalaj Bhandari and
Dani Bouch and Wail Bouhedja and Weili Cao and Ahmad Chamma and Po-Chun Chang and
Junlin Chen and Lingjie Chen and Zhoujun Cheng and Kyle Chickering and
Ryandito Diandaru and Evan Dufraisse and Chaitanya Dwivedi and Bilal El Bouardi and
Desai Fan and Richard Fan and Chengqian Gao and Rifo Ahmad Genadi and
Jonathan Geuter and Charles Guille-Escuret and Willis Guo and Dhawal Gupta and
Seungwook Han and Tingxu Han and Shibo Hao and Besher Hassan and Guowei He and
Ming Shan Hee and Joel Hestness and Yu Huang and Yuan Huang and Haolong Jia and
Linghao Jin and Junu Kim and Lingjing Kong and Nurkhan Laiyk and Andrej Leban and
Liqun Ma and John Maggs and Amr Mohamed and Mukhesh Narra and Omkar Pangarkar and
Aldo Pareja and Khiem Pham and Varad Pimpalkhute and Nikhil Ranjan and
Elizaveta Rebrova and Hector Ren and Shaurya Rohatgi and Guokan Shang and
Jianshu She and Chufan Shi and Aaryamonvikram Singh and Daria Soboleva and
Kartik Sreenivasan and Suqi Sun and Yuekai Sun and Bowen Tan and Liping Tang and
Shengkun Tang and Muzi Tao and Mallikarjuna Tupakula and Micah Villmow and
Hongyi Wang and Huijuan Wang and Renxi Wang and Yongxin Wang and Yuqi Wang and
Zhenting Wang and Shicheng Wen and Yingquan Wu and Anze Xie and Andrew Xing and
Matthew Yang and Shuanghai Yu and Kerem Zaman and Zenan Zhai and Hongli Zhan and
Xuezhou Zhang and Anshun Asher Zheng and Zhe Zhou and Richard Zhuang and Eric P. Xing},
year={2026},
eprint={2611.21003},
archivePrefix={arXiv},
primaryClass={cs.AI},
url={https://arxiv.org/abs/2611.21003}
}
AIDO Cell: A General-Purpose Simulator for Cell Biology
GenBio AI Team, AIDO Cell 1.0 technical report, 2026. Hongyi Wang is a member of the contributing team.
Details
Abstract
AIDO Cell introduces a general-purpose cell biology simulator built on a world model that maintains a coherent cell state across sequential experiments. It supports genetic and molecular perturbations, multimodal readouts spanning genome regulation through cell morphology, and in-context molecular design. Version 1.0 presents prototype virtual cells for the K-562 and Hep-G2 cell lines and positions the system as a composable unit toward a complete digital organism.
Citation
GenBio AI Team, AIDO Cell 1.0 technical report, 2026. Hongyi Wang is a member of the contributing team.
BibTeX
@techreport{genbio2026aidocell,
title={AIDO Cell: A General-Purpose Simulator for Cell Biology},
author={{GenBio AI Team}},
institution={GenBio AI},
year={2026},
month={August},
url={https://genbio.ai/research/AIDO%20Cell%20V1%20-%20Technical%20Report%20-%2018%20Aug%202026.pdf}
}
LLM360: Towards Fully Transparent Open-Source LLMs
Z. Liu, A. Qiao, W. Neiswanger, H. Wang, B. Tan, T. Tao, J. Li, Y. Wang, S. Sun, O. Pangarkar, R. Fan, Y. Gu, V. Miller, Y. Zhuang, G. He, H. Li, F. Koto, L. Tang, N. Ranjan, Z. Shen, R. Iriondo, C. Mu, Z. Hu, M. Schulze, P. Nakov, T. Baldwin, E. P. Xing, COLM 2024 [arXiv]
Details
Citation
Z. Liu, A. Qiao, W. Neiswanger, H. Wang, B. Tan, T. Tao, J. Li, Y. Wang, S. Sun, O. Pangarkar, R. Fan, Y. Gu, V. Miller, Y. Zhuang, G. He, H. Li, F. Koto, L. Tang, N. Ranjan, Z. Shen, R. Iriondo, C. Mu, Z. Hu, M. Schulze, P. Nakov, T. Baldwin, E. P. Xing, COLM 2024 [arXiv]
Cuttlefish: Low-rank Model Training without All The Tuning
H. Wang, S. Agarwal, P. U-chupala, Y. Tanaka, E. P. Xing, D. Papailiopoulos, MLSys 2023 [link] [arXiv]
News
All updatesK2-Horizon technical report released
The K2 Team released six open language models together with the data, checkpoints, and code used to train them.
Invited to serve as Area Chair for ICML 2027
I have been invited to serve as an Area Chair for the International Conference on Machine Learning (ICML) 2027.
Serving as Area Chair for ICLR 2027
I will be serving as an Area Chair for ICLR 2027.
AIDO Cell 1.0 technical report released
The GenBio AI Team released AIDO Cell 1.0, a general-purpose simulator for persistent, multiscale, and multimodal cell biology experiments.
RAISL group
Full group page
Research systems for capable, efficient, and trustworthy machine learning.
Teaching
Academic service
Area Chair: ICML 2027 (invited), ICLR 2027, NeurIPS 2026, ACL ARR 2026 May, CPAL 2026, MLSys 2025
PC Member: DAC 2024, EuroSys 2024, SOSP 2023 (light PC), MLSys 2023-2026, SIGKDD 2022, AAAI 2021-2022
Reviewer (Journals): JMLR, TMLR, IEEE TNNLS, IEEE IoT-J, IEEE/ACM Transactions on Networking
Reviewer (Conferences): SC 2026, COLM 2026, ICML 2019-2026, NeurIPS 2019-2025, CVPR 2021-2023, ICCV 2021-2022, ICLR 2021-2025, AAAI 2021-2024, SIGKDD 2022-2023
