The following Media Lab researchers participated in NeurIPS 2022, the thirty-sixth hybrid conference on Neural Information Processing Systems whose purpose is to foster the exchange of research advances in Artificial Intelligence and Machine Learning.

This year's conference was held in New Orleans, USA.

Runner-up Award: Scalable Collaborative Learning via Representation Sharing

Frédéric Berdoz, Abhishek Singh, Martin Jaggi, Ramesh Raskar
Decentralized and Trustworthy ML in Web3: Methodologies, Platforms, and Applications Workshop
Read the paper here

Differentially Private CutMix for Split Learning with Vision Transformer

Praneeth Vepakomma
Read the paper here

Graph2step: A System for Knowledge Driven Procedural Step Generation (Work in progress abstract)

Pedro Colon-Hernandez

Improving Dermatology Classifiers across Populations using Images Generated by Large Diffusion Models

Matt Groh
Read the paper here

Identifying the Context Shift between Test Benchmarks and Production Data

Matt Groh
Read the paper here

Metric Elicitation; Moving from Theory to Practice

Safinah Ali
Read the paper here

Keynote speech: Progress on AI and ML to help deliver, personalize, and guide interventions in depression 

Rosalind Picard
Empowering Communities: A Participatory Approach to AI for Mental Health Workshop

Contrastive Learning of Electrodermal Activity Representations for Stress Detection

Katie Matton, Rob Lewis, Rosalind Picard (and John Guttag of SCC)
Read the paper here

(107) ForestBench: Equitable Benchmarks for Monitoring, Reporting, and Verification of Nature-Based Solutions with Machine Learning

Tackling Climate Change with Machine Learning Workshop
Björn Lütjens, Dava Newman
Read the paper here