-
10-24
2023
Understanding Modern Deep Learning by Analyzing the Training Dynamics
Speaker: Kaifeng Lyu Princeton University Time: 2023-10-24 14:00-2023-10-24 15:00 Venue: FIT 1-222 Abstract: In the last decade, deep learning has made much exciting progress, but it is still large...
-
10-19
2023
Quantum simulations on an analog-digital trapped-ion quantum system
Speaker: Norbert M. Linke Duke University Time: 2023-10-19 15:30-2023-10-19 16:30 Venue: FIT 1-222 Abstract: Our quantum experiment consists of a chain of 171Yb+ ions with individual Raman beam add...
-
10-18
2023
Algorithms and Protocols for a Trustworthy Cyberspace in the Era of Large Language Models
Speaker: Tianxing He Yulia Tsvetkov in UW on natural language generation Time: 2023-10-18 15:00-2023-10-18 16:00 Venue: FIT 1-222 Abstract: The widening adoption of large language models (LLMs) on ...
-
10-13
2023
Data-Efficient Training of Vision Transformer
Speaker: Boqing Gong Google Time: 2023-10-13 10:00-2023-10-13 12:00 Venue: C19-2 or https://meeting.tencent.com/dm/lhTmYyrGbzVb Abstract: Recently, vision Transformer (ViT) delivered a compelling m...
-
10-10
2023
GFlowNets: Exploratory Probabilistic Inference for Scientific Discovery
Speaker: Dinghuai Zhang Mila Time: 2023-10-10 14:00-2023-10-10 15:00 Venue: FIT 1-222 Abstract: This talk will introduce and discuss generative flow networks (GFlowNets), a learning framework for a...
-
09-28
2023
Converge or Diverge? A Story of Adam
Speaker: Yushun Zhang The Chinese University of Hong Kong Time: 2023-09-28 09:00-2023-09-28 10:00 Venue: Tencent: 952-254-027 Abstract: Adam is one of the most popular algorithms in deep learning, ...