Super Study Guide: Transformer 与大语言模型

Afshine Amidi is currently teaching the Transformers & Large Language Models workshop at Stanford and is also leading LLM efforts at Netflix. Previously, he worked on the Gemini team at Google and used NLP techniques to solve complex queries. Before that, he worked at Uber Eats to improve the quality of the search and recommendation systems. On the side, Afshine published a few papers at the intersection of deep learning and computational biology. He holds a Bachelor’s and a Master’s Degree from École Centrale Paris and a Master’s Degree from MIT.

Shervine Amidi is currently teaching the Transformers & Large Language Models workshop at Stanford and is also working on the Gemini team at Google to leverage LLMs for action-based queries. Previously, he worked on applied machine learning problems for recommender systems at Uber Eats where he focused on representation learning to better surface dish recommendations. On the side, Shervine published a few papers at the intersection of deep learning and computational biology. He holds a Bachelor’s and a Master’s Degree from École Centrale Paris and a Master’s Degree from Stanford University.

Tao (Thomas) Yu earned his B.S. in Computer Science from Zhejiang University, and his M.S. in Computer Science from Carnegie Mellon University, and completed the Artificial Intelligence graduate program at Stanford University. Early in his career, he was a core member of Google Bard (now Gemini), leading research and engineering efforts across projects—from BERT and LaMDA to large-scale models powering personal assistants and AI agents. He later joined Meituan as Senior Technical Director of the AI Platform, where he also chaired the Technical Committee and led the Large Model Platform, architecting the company’s enterprise-level large language model ecosystem. Additionally, he co-founded 01.AI and spearheaded post-training and reinforcement learning for large language models. He was recognized in the Forbes China’s 2021 30 Under 30 Technology list.

Binbin Xiong is a Research Scientist in the GenAI unit at Google DeepMind, where he leads and co-leads multiple initiatives in Gemini pretraining data research. His work spans key areas such as data valuation, mixture design, and large-scale pretraining data scaling laws. Previously, Binbin spent several years specializing in applied machine learning and deep learning, with a focus on data-centric modeling and interpretability techniques to enhance Google’s products, including Search, YouTube, Waymo, Ads, and more. Outside of work, Binbin is passionate about bodybuilding and snowboarding. He is a NASM-certified personal trainer and an AASI-certified snowboard coach.