Publications

Listed reverse-chronologically. * denotes equal contribution; † denotes corresponding authors.

2026

  1. Overview of latent multi-hop composition, knowledge-injection rewrites, BRACE, and explicit elicitation
    CL4FMAgents @ NeurIPS'26 Workshop · 2026 · Accepted
    Anchoring the Bridge Across Hops: Unlocking Latent Multi-Hop Reasoning under Knowledge Injection
    Zichen Tang, Zhenheng Tang, Yifan Hou, Hanwen Xing, Xinda Qi, Xiaowen Chu, Bo Li
    openreview
  2. Overview of the data-synthesis pipeline with quality calibration and bias evaluation
    NeurIPS'26 Evaluations and Datasets Track (Poster) · 2026 · Accepted
    Is Your LLM-as-a-Recommender Agent Trustable? LLMs' Recommendation is Easily Hacked by Biases (Preferences)
    Zichen Tang*, Zirui Zhang*, Qian Wang, Zhenheng Tang†, Xiaowen Chu, Bo Li†
    * equal contribution; † corresponding authors
    arxiv
  3. Overview of BiasTrojan: context-aware and contrastive bias injection with counterfeited reasoning, evaluation, and deployment attacks
    NeurIPS'26 (Poster) · 2026 · Accepted
    BiasTrojan: LLM Judgers Are Easily Distorted by Few Hundreds of Contrastive Biased Training Data
    Zichen Tang*, Zhenheng Tang*†, Qian Wang, Gaoning Pan, Yuhan Yang, Wei He, Shaohuai Shi, Xiaowen Chu, Bo Li†
    * equal contribution; † corresponding authors
  4. 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
  5. Silent data-corruption errors causing gradient-aggregation errors across machines
    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
  6. 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
  7. 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

2024

  1. 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 list also on Google Scholar.