Check out our CVPR 2025 paper on reasoning about unexpected events in videos! 🦢

Congrats to Shenran Wang, Changbing Yang, Michael l Parkhill, Chad Quinn, Christopher Hammerly and Jian Zhu - their paper "Developing multilingual speech synthesis system for Ojibwe, Mi’kmaq, and Maliseet" won the best theme paper runner-up at #naacl2025! 👏🎉 aclanthology.org/2025.naacl-sho…

🚨 Talk Alert! We’re excited to host Shashata Sawmya (MIT) on May 29 @ 11AM (ICCS 246) for a deep dive into mechanistic interpretability in LLMs — from emergent features to UTune. Don’t miss it! 🧠 #NLP #LLMs #AI #Interpretability #UBC

*SEM 2025: Direct submissions deadline is now EXTENDED to June 13, 2025! *SEM will be co-located with EMNLP in Suzhou, China. It will be a hybrid event, virtual attendance possible (more info on this will be posted later). Full CFP: starsem2025.github.io/cfp #NLP #NLProc

Great food, even better company. UBC NLP’s potluck brought together flavors and stories from around the world 🌎 Thanks to everyone who joined and shared a dish!

We are excited to host Hideaki Joko from Informagus - Information Retrieval Research Group for a talk titled "Let’s FACE the Evaluation of Conversations that Go with the Flow". Join us on Tuesday June 3 at 11 am at ICICS x860! UBC Language Sciences Institute CAIDA_UBC

Simple example for how errors can creep into our papers through LLM use: I had a statistic for 2020. I googled the same statistic for 2023. AI overview tells me the statistic for 2023 & provides a link to support the claim. The link is to a 2023 article citing the 2020 statistic.

Correction: the talk will happen at ICICS 146. See you soon!

🗓️ Save the date! It's official: The VLMs4All Workshop at #CVPR2025 will be held on June 12th! Get ready for a full day of speakers, posters, and a panel discussion on making VLMs more geo-diverse and culturally aware 🌐 Check out the schedule below!

Starting in 10 minutes - we have an exciting line up of talks, posters, and a panel! Join us at room 104E. 🌍

Some of us are in Nashville for #CVPR2025! 🎸 Today we are at the VLMs4All - CVPR 2025 Workshop workshop about building geo-diverse VLMs (room 104E, all day), where our GlobalRG benchmark is one of the shared tasks - Mehar Bhatia will present the results. 1/3

Come see our poster!

I just published "This book will not be used to train LLMs": lostinautomatictranslation.com/blog/this-book…

If you're up early enough, I'll be speaking there at 8:40 today 😃