publications

\* indicates equal contribution

2026

2026

  1. ICLR 2026
    Tactic: Adaptive Sparse Attention with Clustering and Distribution Fitting for Long-Context LLMs
    Kan Zhu* , Tian Tang* , Qinyu Xu* , Yile Gu , and 6 more authors
    International Conference on Learning Representations, 2026
    PDF
  2. ICLR 2026
    Local Linear Attention: An Optimal Interpolation of Linear and Softmax Attention for Test-Time Regression
    Yifei Zuo , Yutong Yin , Zhichen Zeng, Ang Li , and 2 more authors
    International Conference on Learning Representations, 2026
    PDF
  3. arXiv
    DisagMoE: Computation-Communication Overlapped MoE Training via Disaggregated AF-Pipe Parallelism
    Zhichen Zeng, Chi-Chih Chang , Jiayi Wang , Zezhou Wang , and 9 more authors
    arXiv preprint, 2026
    PDF
  4. arXiv
    Parallax: Parameterized Local Linear Attention for Language Modeling
    Yifei Zuo , Dhruv Pai , Zhichen Zeng, Alec Dewulf , and 2 more authors
    arXiv preprint, 2026
    PDF
  5. ISCA 2026
    DICE: Enabling Efficient General-Purpose SIMT Execution with Statically Scheduled Coarse-Grained Reconfigurable Arrays
    Jiayi Wang , Ang Da Lu , Zhichen Zeng, and Ang Li
    IEEE/ACM Annual International Symposium on Computer Architecture, 2026
    PDF
  6. Tech Report
    Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity
    ByteDance Seed
    ByteDance Technical Report, 2026

2025

2025

  1. NeurIPS 2025
    SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs
    Yizhao Gao* , Zhichen Zeng*, Dayou Du , Shijie Cao , and 4 more authors
    Annual Conference on Neural Information Processing Systems, 2025
    PDF
  2. ISCA 2025
    LUT Tensor Core: Lookup Table Enables Efficient Low-Bit LLM Inference Acceleration
    Zhiwen Mo , Lei Wang , Jianyu Wei , Zhichen Zeng, and 7 more authors
    IEEE/ACM Annual International Symposium on Computer Architecture, 2025
    PDF
  3. MICRO 2025
    MHE-TPE: Multi-Operand High-Radix Encoder for Mixed-Precision Fixed-Point Tensor Processing Engines
    Qizhe Wu , Jinyi Zhou , Zhanhe Hu , Zhichen Zeng, and 9 more authors
    IEEE/ACM International Symposium on Microarchitecture, 2025
  4. HPCA 2025
    Exploring the Performance Improvement of Tensor Processing Engines through Transformation in the Bit-weight Dimension of MACs
    Qizhe Wu , Huawen Liang , Yuchen Gui , Zhichen Zeng, and 6 more authors
    IEEE International Symposium on High-Performance Computer Architecture, 2025
    PDF
  5. NeurIPS Workshop
    SRT: Accelerating Reinforcement Learning via Speculative Rollout with Tree-Structured Cache
    Chi-Chih Chang , Siqi Zhu , Zhichen Zeng, Haibin Lin , and 4 more authors
    NeurIPS 2025 Workshop, 2025
    PDF

2024

2024

  1. PLDI 2024
    Allo: A Programming Model for Composable Accelerator Design
    Hongzheng Chen* , Niansong Zhang* , Shaojie Xiang , Zhichen Zeng, and 2 more authors
    ACM SIGPLAN Conference on Programming Language Design and Implementation, 2024
    PDF Code
  2. ICCD 2024
    EN-T: Optimizing Tensor Computing Engines Performance via Encoder-Based Methodology
    Qizhe Wu , Yuchen Gui , Zhichen Zeng, Xiaotian Wang , and 2 more authors
    IEEE International Conference on Computer Design, 2024
    PDF
  3. J. Phys. D
    Highly Stable and Fast Response Photodetector Based on Double Perovskite Cs2AgBiCl6 Crystals
    Zhengyu Han* , Mengjia Dai* , Zhichen Zeng*, Chunhui Ye , and 4 more authors
    Journal of Physics D: Applied Physics, 2024
    PDF