NeurIPS 2024: Impossible GenAI Questions With Zirui Wang скачать в хорошем качестве

NeurIPS 2024: Impossible GenAI Questions With Zirui Wang

What happens when AI researchers ask each other the toughest, most mind-bending questions they can think of? In this NeurIPS 2024 series, researchers attempt to answer the unanswerable. In this video, Zirui Wang, Student Researcher at Princeton Computer Science, takes his turn. Questions: 00:23 How to better handle non-uniform grid data at scale to build generative models? 00:54 When can we go home and let machine learning models adjust all our hyperparameters for us? 01:43 What’s a belief about model training that you’ve held onto for years but are starting to question? 02:34 What's the best way to train a foundation model for sequential decision-making? How can we gather and use massive amounts of data to train it? 03:31 What do you think will be superseded first – the transformer architecture or PyTorch? Follow us & stay updated: ► Vist our website: https://buff.ly/NxcmKGi ► Follow us on Linkedin:   / neptuneai   ► Follow us on Twitter:   / neptune_ai   ► Check our Github: https://github.com/neptune-ai Connect with Zirui on Linkedin:   / zwcolin   #genai #generativeai #llm #llms #neurips