I am a computer systems researcher. I am currently working at a stealth startup developing innovative LLM infrastructure. I received my Ph.D. from the Institute for Interdisciplinary Information Science (IIIS) at Tsinghua University, where I was advised by Prof. Mingyu Gao. Prior to joining Tsinghua, I earned my bachelor's degree from the ACM Honors Class at Shanghai Jiao Tong University.
My research interests span diverse areas within computer systems. I am currently focusing on efficient, scalable and reliable infrastructure for the full lifecycle of AI agents. My Ph.D. research specialized in memory-centric architecture design, exploring innovative approaches such as near-data processing, memory pooling, and memory disaggregation to optimize system performance and energy efficiency.
Open Source
- Weaver — an agentic finetuning API: fine-tune LLMs with integrated agent-framework and RL support, without managing the distributed training infrastructure.
Code / Homepage / Doc - NexRL — an ultra-loosely-coupled LLM post-training framework for reinforcement learning at scale.
Code / Blog - Nex-N1 — agentic models trained via a unified ecosystem for large-scale environment construction.
Model / Paper - Nex-N2 — an agentic model built for real-world productivity: coding, tool use, and complex task execution.
Model
Publications
- PlexRL: Cluster-Level Orchestration of Serviceized LLM Execution for RLVR
Yiqi Zhang, Fangzheng Jiao, Tian Tang, Boyu Tian, Hangyu Wang, Qiaoling Chen, Guoteng Wang, Zhen Jiang, Peng Sun, Ping Zhang, Xiaohe Hu, Ziming Liu, Menghao Zhang, Yanmin Jia, Yang You, Siyuan Feng
arXiv 2026 Paper - CONCUR: High-Throughput Agentic Batch Inference of LLM via Congestion-Based Concurrency Control
Qiaoling Chen, Zhisheng Ye, Tian Tang, Peng Sun, Boyu Tian, Guoteng Wang, Shenggui Li, Yonggang Wen, Zhenhua Han, Tianwei Zhang
arXiv 2026 Paper - Twilight: Adaptive Attention Sparsity with Hierarchical Top-p Pruning
Chaofan Lin, Jiaming Tang, Shuo Yang, Hanshuo Wang, Tian Tang, Boyu Tian, Ion Stoica, Song Han, Mingyu Gao
NeurIPS 2025 (Spotlight) Paper - Nex-N1: Agentic Models Trained via a Unified Ecosystem for Large-Scale Environment Construction
Nex-AGI Team (including Boyu Tian)
arXiv 2025 Paper - Expert-as-a-Service: Towards Efficient, Scalable, and Robust Large-scale MoE Serving
Ziming Liu, Boyu Tian, Guoteng Wang, Zhen Jiang, Peng Sun, Zhenhua Han, Tian Tang, Xiaohe Hu, Yanmin Jia, Yan Zhang, He Liu, Mingjun Zhang, Yiqi Zhang, Qiaoling Chen, Shenggan Cheng, Mingyu Gao, Yang You, Siyuan Feng
arXiv 2025 Paper - MemTunnel: A CXL-Based Rack-Scale Host Memory Pooling Architecture for Cloud Service
Tianchan Guan, Yijin Guan, Zhaoyang Du, Jiacheng Ma, Boyu Tian, Zhao Wang, Teng Ma, Zheng Liu, Yang Kong, Yuan Xie, Mingyu Gao, Guangyu Sun, Hongzhong Zheng, Dimin Niu
TPDS 2025 Paper - ANSMET: Approximate Nearest Neighbor Search with Near-Memory Processing and Hybrid Early Termination
Yiwei Li, Yuxin Jin, Boyu Tian, Huanchen Zhang, Mingyu Gao
ISCA 2025 PDF - Stream-Based Data Placement for Near-Data Processing with Extended Memory
Yiwei Li, Boyu Tian, Yi Ren, Mingyu Gao
MICRO 2024 PDF - Trimma: Trimming Metadata Storage and Latency for Hybrid Memory Systems
Yiwei Li, Boyu Tian, Mingyu Gao
PACT 2024 PDF - NDPBridge: Enabling Cross-Bank Coordination in Near-DRAM-Bank Processing Architectures
Boyu Tian, Yiwei Li, Li Jiang, Shuangyu Cai, Mingyu Gao
ISCA 2024 PDF - PimPam: Efficient Graph Pattern Matching on Real Processing-in-Memory Hardware
Shuangyu Cai, Boyu Tian, Mingyu Gao
SIGMOD 2024 PDF - ABNDP: Co-optimizing Data Access and Load Balance in Near-Data Processing
Boyu Tian, Qihang Chen, Mingyu Gao
ASPLOS 2023 PDF / Talk - FINGERS: Exploiting Fine-Grained Parallelism in Graph Mining Accelerators
Qihang Chen, Boyu Tian, Mingyu Gao
ASPLOS 2022 PDF / Talk - DHS: Adaptive Memory Layout Organization of Sketch Slots for Fast and Accurate Data Stream Processing
Bohan Zhao, Xiang Li, Boyu Tian, Zhiyu Mei, Wenfei Wu
KDD 2021 PDF
Experiences
- Zhipu AI · Mar 2024 – Aug 2024
Research intern in AI Academy. Mentor: Dr. Guanyu Feng. - Alibaba DAMO Academy · Jun 2023 – Jan 2024
Research intern in Computing Technology Lab. Mentor: Dr. Dimin Niu. - Huawei Hisilicon · Oct 2019 – Dec 2019
Research intern in Turing Department. Mentors: Dr. Lin Li and Dr. Heng Liao. - Duke University · Jul 2019 – Sep 2019
Research intern, working with Prof. Yiran Chen.
Education
- Tsinghua University · Sep 2020 – Jun 2025
Ph.D. in IIIS, advised by Prof. Mingyu Gao. - Shanghai Jiao Tong University · Sep 2016 – Jun 2020
B.Eng. in Computer Science at ACM Honors Class, Zhiyuan College, advised by Prof. Chao Li.
Miscellaneous
I enjoy playing basketball in my spare time. I was the basketball team captain of IIIS, ACM Class and Zhiyuan College.