Charlie Blake from Graphcore’s research team discusses their AI Papers of the Month for January 2024. Graphcore research has been collating and sharing a review of the most consequential AI papers internally, every month, for a number of years. Now – for the first time – the research team is making this valuable resource public, to help the wider AI community keep up-to-date with the most exciting breakthroughs. Papers of the Month for January 2024 (with some work from December 2023) includes: Bad Students Make Great Teachers: Active Learning Accelerates Large-Scale Visual Understanding https://arxiv.org/abs/2312.05328Authors: Talfan Evans, Shreya Pathak, Hamza Merzic, et al. (Google DeepMind, UCL) Beyond Chinchilla-Optimal: Accounting for Inference in Language Model Scaling Lawshttps://arxiv.org/abs/2401.00448Authors: Nikhil Sardana and Jonathan Frankle (MosaicML) Analyzing and Improving the Training Dynamics of Diffusion Modelshttps://arxiv.org/abs/2312.02696Authors: Tero Karras et al. (Nvidia, Aalto University) Solving olympiad geometry without human demonstrationshttps://www.nature.com/articles/s41586-023-06747-5Authors: Trieu H. Trinh, Yuhuai Wu, Quoc V. Le, He He and Thang Luong (Google DeepMind, New York University) To read about January’s Papers of the Month, visit the Graphcore blog.https://www.graphcore.ai/posts/great-teachers-and-beyond-chinchilla-papers-of-the-month-jan-2024

Ver todos los episodios