About Me

I am a first-year Ph.D. student at the University of Maryland, College Park, advised by Prof. Heng Huang. Previously, I worked as a research assistant at the Natural Language Processing Laboratory of Northeastern University (China), supervised by Prof. Tong Xiao. I received my B.E. degree from Northeastern University of Computer Science and Engineering in 2021.

My current research interests focus on Efficient AI, including:

  • Efficient Backbone/Foundation Model (UMST [ICML2022], EIT [ACL2024], PartialFormer [ACL2024], PCFormer [NeurIPS2024])
  • Efficiently adapting LLMs to broader tasks (Author Attribution [EMNLP2024])
  • Efficient Inference (Multi-Draft Speculative Decoding [ICLR2025])
  • Efficient Training: Post-training for LLM-based MMT [Arxiv]

News

Feb 10 2025
I will join Tencent AI Lab (Seattle) as a research intern this summar.
Jan. 22 2025
One paper accepted for publication at ICLR 2025.
Sep. 25 2024
One paper accepted for publication at NIPS 2024.
Sep. 19 2024
One paper accepted for publication at EMNLP2024 Main Conference.
Aug. 19 2024
Start my PhD study at University of Maryland, College Park.
May. 16 2024
Two papers accepted for publication at ACL2024 (1 Main, 1 Findings).
Oct. 8 2023
One paper accepted for publication at Findings of EMNLP2023.
May. 14 2022
"Learning Multiscale Transformer Models for Sequence Generation" accepted for publication at ICML 2022. (First ICML in NEUNLP)
Sep. 1 2021
Join in NEUNLP lab as a research assistant.
Jun. 25 2021
Graduate from Northeastern University with an average GPA of 4.0.

Pre-prints

NEW 🔥 Asymmetric Conflict and Synergy in Post-training for LLM-based Multilingual Machine Translation [paper]
Arxiv, 2025
Tong Zheng, Yan Wen, Huiwen Bao, Junfeng Guo, Heng Huang.
NEW 🔥 Beyond Decoder-only: Large Language Models Can be Good Encoders for Machine Translation [paper]
Arxiv, 2025
Yingfeng Luo, Tong Zheng, Yongyu Mu, Bei Li, Qinghong Zhang, Yongqi Gao, Ziqiang Xu, Peinan Feng, Xiaoqian Liu, Tong Xiao, Jingbo Zhu.

Publications (* Equal Contribution)

NEW 🔥 Towards Optimal Multi-draft Speculative Decoding.
ICLR2025
Zhengmian Hu*, Tong Zheng*, Vignesh Viswanathan, Ziyi Chen, Ryan A. Rossi, Yihan Wu, Dinesh Manocha, Heng Huang
Predictor-Corrector Enhanced Transformers with Exponential Moving Average Coefficient Learning.
Neurips2024
Bei Li, Tong Zheng, Rui Wang, Jiahao Liu, Qingyan Guo, Junliang Guo, Xu Tan, Tong Xiao, Jingbo Zhu, Jingang Wang, Xunliang Cai
A Bayesian Approach to Harnessing the Power of LLMs in Authorship Attribution.
EMNLP2024 Main
Zhengmian Hu*, Tong Zheng*, Heng Huang
PartialFormer: Modeling Part Instead of Whole. [Paper]
ACL2024 Findings
Tong Zheng*, Bei Li*, Huiwen Bao*, Weiqiao Shan, Tong Xiao, Jingbo Zhu
EIT: Enhanced Interactive Transformer. [Paper]
ACL2024 Main Conference
Tong Zheng*, Bei Li*, Huiwen Bao*, Tong Xiao, Jingbo Zhu
Learning Multiscale Transformer Models for Sequence Generation. [Paper]
ICML 2022
Bei Li*, Tong Zheng*, Yi Jing*, Chengbo Jiao, Tong Xiao, Jingbo Zhu
Incorporating Probing Signals into Multimodal Machine Translation via Visual Question-Answering Pairs. [Paper]
Findings of EMNLP2023
Yuxin Zuo*, Bei Li*, Chuanhao Lv, Tong Zheng, Tong Xiao, Jingbo Zhu
MVS-GCN: A prior brain structure learning-guided multi-view graph convolution network for autism spectrum disorder diagnosis. [Paper]
CIBM 2022
Guangqi Wen, Peng Cao, Huiwen Bao, Wenju Yang, Tong Zheng, Osmar Zaiane

Manuscript

BrainTGL: Temporal Graph representation learning for brain network by Exploiting Graph Temporal Information. [Manuscript]
Finished at August 2021
Tong Zheng

Selected Honors

UMD Dean's Fellowship, 2024-2026.
Adapted from template.