This page lists my talks in conferences or seminars: (starting from Aug 1 2025)

Upcoming:

• 茶思屋科技网站学术星光直播节目 -- 在线线性规划算法加速大语言模型推理 -- 线上(直播), Dec-16-2025, 19:00-20:30

Past:

• APORS Youth Forum 2025 -- LLM Serving Optimization with Variable Prefill and Decode Lengths

• Huawei & HKUST Workshop -- Attention-FFN Disaggregation (AFD) – Stable Condition and Deployment Optimization

• 第二届大湾区人工智能数理基础论坛暨广东省人工智能数理基础重点实验室第三次年会(学术报告) -- 面向多目标大语言模型推理的在线对偶下降分配算法 

• 第二届数学与人工智能科学大会(自由报告) -- Efficient and Robust Large Language Model (LLM) Inference Optimization

• Pioneering AI for Scientific Discoveries: Zhongguancun x HKUST Innovations -- Efficient and Robust Large Language Model (LLM) Inference Optimization 

• 中国运筹学会数据科学与运筹智能分会2025年学术年会(大会报告) -- Efficient and Robust Large Language Model (LLM) Inference Optimization

• 上海交通大学安泰经济与管理学院 (Seminar Talk) -- Efficient and Robust Large Language Model (LLM) Inference Optimization