Page Not Found
Page not found. Your pixels are in another canvas.
Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
关于我
北京智源人工智能研究院 AI 框架研究员。关注本地大模型、Torch-FL 与高效推理。
About
AI Framework Researcher at BAAI, working on local LLMs, Torch-FL, and efficient inference.
联系
邮箱、GitHub、LinkedIn 与 ORCID。
Contact
Email, GitHub, LinkedIn, and ORCID.
Posts
一点NLP论文写作资料的整理
Published:
portfolio
publications
DSMER: A Deep Semantic Matching Based Framework for Named Entity Recognition
Published in ECIR 2021, 2021
A two-phase NER framework that matches candidate spans to entity types with prior knowledge. ECIR 2021 (CCF C).
Recommended citation: Lyu, Yufeng, and Jiang Zhong. "DSMER: A Deep Semantic Matching Based Framework for Named Entity Recognition." In European Conference on Information Retrieval, pp. 419–432. 2021. /files/ECIR_2021.pdf
ICDT: Incremental Context Guided Deliberation Transformer for Image Captioning
Published in PRICAI 2022, 2022
A two-pass deliberation Transformer with an incremental context encoder for image captioning. PRICAI 2022 (CCF C).
Recommended citation: Lai, Xinyi, Yufeng Lyu, Jiang Zhong, Chen Wang, Qizhu Dai, and Gang Li. "ICDT: Incremental Context Guided Deliberation Transformer for Image Captioning." In Pacific Rim International Conference on Artificial Intelligence, pp. 444–458. 2022. /files/PRICAI_2022.pdf
Klotski: Efficient Mixture-of-Expert Inference via Expert-Aware Multi-Batch Pipeline
Published in ASPLOS 2025, 2025
Expert-aware multi-batch pipelining for MoE inference, with up to 85.12× throughput improvement. ASPLOS 2025.
Recommended citation: Fang, Zhiyuan, Yuegui Huang, Zicong Hong, Yufeng Lyu, Wuhui Chen, Yue Yu, Fan Yu, and Zibin Zheng. "Klotski: Efficient Mixture-of-Expert Inference via Expert-Aware Multi-Batch Pipeline." In Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2, pp. 574–588. 2025. https://arxiv.org/abs/2502.06888
Fate: Fast Edge Inference of Mixture-of-Experts Models via Cross-Layer Gate
Published in The ACM Web Conference (WWW), 2026
Cross-layer gating for faster MoE inference on edge devices. The ACM Web Conference (WWW), 2026.
Recommended citation: Fang, Zhiyuan, Xingfan Yu, Yuegui Huang, Zicong Hong, Yufeng Lyu, Wuhui Chen, Yue Yu, and Fan Yu. "Fate: Fast Edge Inference of Mixture-of-Experts Models via Cross-Layer Gate." In Proceedings of the ACM Web Conference 2026, pp. 5537–5546. https://arxiv.org/abs/2502.12224
talks
From digital logic to computer organization
Published:
A bridge lecture from digital logic to computer organization at Chongqing University.
How to start a graduation project
Published:
A tutorial for undergraduate students writing a computer science graduation thesis.
How to read an NLP paper
Published:
Admission training for new graduate students on searching, collecting, and reading NLP papers.
Life as a computer science graduate student
Published:
An informal talk on what CS graduate school is actually like.
CS graduate admissions, overseas applications, and internships
Published:
Sharing session on CS graduate admissions, studying abroad, and internships.
An introduction to nested named entity recognition
Published:
A short introduction to nested NER, a subtask of named entity recognition.
LLM systems mini-lectures
Published:
Short original lectures on LLM distributed training, mixed precision, instruction tuning, and related systems topics.
Torch-FL: Ending the Fragmentation Nightmare of Heterogeneous AI Chips
Published:
FlagOS livestream on Torch-FL, a unified PyTorch plugin that hides vendor differences across Chinese AI accelerators.
Torch-FL: A Virtual Device Layer for PyTorch
Published:
Tutorial talk at PyTorch Conference China 2026 on turning PrivateUse1 into a reusable virtual device layer for multi-chip PyTorch.
teaching
Teaching Assistant, Computer Organization and Integrated Hardware Design
Undergraduate course, Chongqing University, Department of Computer Science, 2017
TA for Computer Organization and Integrated Hardware Design.
Online Teaching of Computer Organization
Undergraduate course, Chongqing University, Department of Computer Science, 2020
Recorded Computer Organization labs during COVID-19.
Guest Lecturer, LLM Development and Innovation Program
Guest lecture, Shanghai Jiao Tong University, Student Innovation Centre, 2022
Guest lecturer at SJTU Student Innovation Centre, Summer 2022 and 2023.
Invited Guest Lecturer, LLM Training and Deployment Optimization with MindSpore
Faculty workshop, National Advanced Faculty Development Workshop on CS Education, 2024
Invited lecture on training and deploying LLMs with MindSpore.