To sign up for this social, please register on this Luma page: https://lu.ma/rmyoy2vw

Join folks from teams like Cohere for AI, Data Provenance Initiative and Encord working on data-specific AI problems for a Data-Centric AI social!

Data quality has been one of the biggest drivers of AI advancements to date, from large scale data collection efforts such as ImageNet and Common Crawl, to innovations in targeted data curation such as human feedback and preference gathering for RLHF. A number of data-specific AI challenges have also gained visibility in the past year, in part due to to new opportunities for multimodal data, data mixtures and other data-driven research directions, as well as in response to public backlash surrounding to the reuse of online data for model pretraining, which has raised global discourse around the provenance, governance, and copyright considerations.

This social convenes researchers and practitioners focused on a broad range of data topics, spotlighting key organizations working in this space such as the Data Provenance Initiative and Cohere for AI. Following brief opening remarks, there will be a participant-driven unconference, and finally a mixer. The purpose of this social is to discuss shared challenges and opportunities for further dialogue and collaboration following ICLR.