🚀Check out our #NAACL2024 paper on continual pre-training of language models (LMs)!

In the real world, LMs need to unlearn/overwrite outdated information with updated ones.

To evaluate the temporal adaptation capabilities of LMs, we introduce the temporally evolving QA

🎉 Happy to present our recent research work, ObjectCompose: an automated approach to introduce diverse #background changes to #real -images.

Project🔗: lnkd.in/dFJwk9zi
Paper📑: lnkd.in/dx5ZmXDc
Code💻: lnkd.in/dCDN2gWQ

#Robustness #FoundationModels

📢📢 I am looking for a student researcher to work with me and my colleagues at Google AI Research on instruction-based text embedding representations and evaluation. Please apply (google.com/about/careers/…) and reach out to me ([email protected]) if interested.