Machine Learning and Friends Lunch
Machine Learning and Friends Lunch: Andrew Wu, Marabou 2.0: A Versatile Formal Analyzer of Neural Networks
Join Andrew Wu for a presentation on version 2.0 of Marabou, a toolkit for formally verifying user-defined properties on deep neural networks.
Machine Learning and Friends Lunch: Yixin Wang, Causal Inference with Unstructured Data
Causal inference traditionally involves analyzing tabular data where variables like treatment, outcome, covariates, and colliders are manually labeled by humans
Machine Learning and Friends Lunch: Xiaolong Wang, Learning Humanoid Robots
The Machine Learning and Friends Lunch series continues with Xiaolong Wang's "Learning Humanoid Robots."
Machine Learning and Friends Lunch: Boqing Gong, From Domain Adaptation to VideoPrism: A Decade-Long Quest for Out-of-Domain Visual Generalization
This talk explores the challenges of out-of domain (OOD) generalization in computer vision, encompassing tasks like domain adaptation.
Machine Learning and Friends Lunch: Chen Sun, Grounding Deep Generative Models in the Physical World
Machine Learning and Friends Lunch
Machine Learning and Friends Lunch: Xinya Du, Synergizing Knowledge and Large Language Models
In this talk, Xinya Du will discuss his research on synergizing LMs and knowledge.
Machine Learning and Friends Lunch: Agustinus Kristiadi, Probabilistic Inference and Decision-Making With and For Foundation Models
Agustinus Kristiadi is a postdoctoral fellow at the Vector Institute and
previously obtained his PhD from the University of Tuebingen in Germany.
Machine Learning and Friends Lunch: Claudia Shi, Novel Problems, Classic Solutions: Understanding LLMs Through the Lens of Statistics
In this talk, Shi will present two recent projects that use statistical methods to deepen our understanding of LLMs.
Machine Learning and Friends Lunch: Silvia Sellán (Columbia University), Stochastic Computer Graphics
Silvia Sellán (Columbia University) will advocate for a perspective shift that allows us to design algorithms directly for safety-critical applications.
Machine Learning and Friends Lunch: Alex Wong, The Know-How of Multimodal Depth Perception
Training deep neural networks requires tens of thousands to millions of examples, so curating multimodal vision datasets amounts to numerous man-hours.