engblogs

Selective classification can improve average accuracy but fail to improve or even hurt accuracy in certain subgroups of the data, highlighting potential failure modes of using selective classification in practice.

Discussing the powerful design choice of Apache Kafka and providing a sneak peek into its functionality.

Introducing RGB-Stacking as a benchmark for vision-based robotic manipulation and exploring how to enable robots to interact with a diverse range of objects.

Exploring the prevalent normalization methods for evaluating multiple choice tasks on autoregressive language models like GPT-3/Neo/J.

Exploring how to enable robots to better understand the interactions of objects with diverse geometries for more generalisable and useful robots.

This technical blogpost provides a list of accepted papers from the Stanford AI Lab that will be presented at the International Conference on Computer Vision (ICCV 2021), with information about the authors, contacts, keywords, and links to papers, videos, and websites.

Predicting gene expression using AI and the Enformer architecture to improve understanding of genetic instructions and their influence on human health and development.

Using AI to predict gene expression and uncovering the instructions within non-coding DNA sequences.

Advancements in nowcasting the next hour of rain using state-of-the-art generative models and machine learning.

This blogpost discusses the research and advancement in Precipitation Nowcasting, specifically focusing on predicting rain within the next 1-2 hours using a state-of-the-art model and AI technology.

Transforming book summaries with human input for enhanced comprehension

Exploring the utility of emergent behaviors from curious exploration and the potential for skill retention in unsupervised reinforcement learning