Zichen Tang

First-year PhD, Computer Science and Engineering
Hong Kong University of Science and Technology

I am a first-year PhD student in Computer Science and Engineering at the Hong Kong University of Science and Technology, advised by Prof. Bo Li.

Before HKUST, I completed an MPhil in Data Science and Analytics at HKUST (Guangzhou) under Prof. Xiaowen Chu and Prof. Sihong Xie, working on communication-efficient distributed and federated learning. I received my BEng in Computer Science from HKUST with a double major in Mathematics.

email · google scholar · github · cv (pdf)

Research

Federated / Distributed Training · Data-centric LLM Training · LLM Safety

News

  • 2026-05 Recognized as an ICML 2026 Gold Reviewer.
  • 2026-05 Paper Capturing and Mitigating Gradient Aggregation Errors for Fault-Tolerant Distributed Training accepted at ICML 2026.
  • 2026-03 Preprint released: Is Your LLM-as-a-Recommender Agent Trustable? LLMs' Recommendation is Easily Hacked by Biases (Preferences).
  • 2026-02 Started TAing COMP3511 (Operating Systems) at HKUST.
  • 2026-01 Paper Ghost in the Cloud: Your Geo-Distributed LLM Training is Easily Manipulated accepted at ICLR 2026.
  • 2026-01 Paper DreamDDP: Accelerating Data Parallel Distributed LLM Training with Layer-wise Scheduled Partial Synchronization accepted at MLSys 2026.
  • 2025-09 Began my PhD in Computer Science and Engineering at HKUST.

Selected Publications

  1. Overview of BiasTrojan: context-aware and contrastive bias injection with counterfeited reasoning, evaluation, and deployment attacks
    ICML'26 Workshop · 2026
    BiasTrojan: LLM Judgers Are Easily Distorted by Few Hundreds of Contrastive Biased Training Data
    Zichen Tang, Z. Tang, Q. Wang, G. Pan, Y. Yang, W. He, S. Shi, X. Chu, B. Li
  2. KnownContext overview: knowledge rewriting, atomic data rewriting, a rewriting taxonomy, and the evaluation protocol
    ICML'26 Workshop · 2026
    Enhancing Knowledge Injection with Surrounding Backgrounds in Continual Training LLMs
    Zichen Tang, Z. Tang, Y. Hou, P. Dong, X. Liu, S. Shi, X. Chu, B. Li
  3. Overview of the data-synthesis pipeline with quality calibration and bias evaluation
    arXiv preprint · 2026 · Preprint
    Is Your LLM-as-a-Recommender Agent Trustable? LLMs' Recommendation is Easily Hacked by Biases (Preferences)
    Zichen Tang*, Z. Zhang*, Q. Wang, Z. Tang, B. Li, X. Chu
    * equal contribution
    arxiv
  4. Ghost in the Cloud overview: trigger-based jailbreak injection, two defenses, and the deployment attack
    ICLR'26 · 2026 · Accepted
    Ghost in the Cloud: Your Geo-Distributed Large Language Models Training is Easily Manipulated
    Zichen Tang*, Z. Tang*, G. Pan, B. Liu, X. He, K. Lai, X. Chu, B. Li
    * equal contribution
  5. DreamDDP system overview: profiler-driven schedule pipeline with layer-wise partial synchronization
    MLSys'26 · 2026 · Accepted
    DreamDDP: Accelerating Data Parallel Distributed LLM Training with Layer-wise Scheduled Partial Synchronization
    Z. Tang*, Zichen Tang*, J. Huang, X. Pan, R. Yan, Y. Wang, A. C. Zhou, S. Shi, X. Chu, B. Li
    * equal contribution
    arxiv
  6. Per-round timeline: adaptive bandwidth-aware compression saves communication time over uniform compression
    ICPP'24 · 2024 · Published
    Bandwidth-Aware and Overlap-Weighted Compression for Communication-Efficient Federated Learning
    Zichen Tang, J. Huang, R. Yan, Y. Wang, Z. Tang, S. Shi, A. C. Zhou, X. Chu
    arxiv

→ full publication list