Jacob Andreas
MIT associate professor in EECS and CSAIL studying language learning and how neural models represent meaning
- Associate Professor, Massachusetts Institute of Technology (EECS and CSAIL)1
Jacob Andreas is an associate professor at MIT in EECS and CSAIL. Andreas's research aims to understand the computational foundations of language learning and to build systems that communicate with people and learn from human guidance in natural language. One line of the work asks what features and strategies black-box models learn: Andreas co-authored a study of in-context learning in transformers using linear models, and MILAN, a procedure that labels neurons in vision models with natural-language descriptions.123
Work
What learning algorithm is in-context learning? Investigations with linear models (external site: arxiv.org)Published research
Co-author of the ICLR 2023 paper, which tests the hypothesis that transformer in-context learners implicitly implement standard learning algorithms, using linear regression as the test problem.21
Natural Language Descriptions of Deep Visual Features (MILAN) (external site: arxiv.org)Published research
Last-listed author of the ICLR 2022 paper introducing MILAN, a procedure that automatically labels neurons in deep vision networks with natural-language descriptions.31
This profile covers public professional work only, from the sources below. It is not an endorsement or a ranking. To correct or remove it, use the correction form.