Publications

Listed reverse-chronologically. * denotes equal contribution.

2026

1. 
   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. 
   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. 
   ICML'26 · 2026 · Accepted

   Capturing and Mitigating Gradient Aggregation Errors for Fault-Tolerant Distributed Training

   Z. Tang*, J. Huang*, Zichen Tang*, X. Kang, Y. Wang, P. Dong, S. Shi, X. Chu, B. Li

   * equal contribution
4. 
   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
5. 
   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
6. 
   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

2024

1. 
   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 list also on Google Scholar.