Great piece by Matteo Wong in the The Atlantic quoting Dr. Ife Adebara, who did her PhD with me at UBC Linguistics (UBC Linguistics). Also quotes a number of fiends and colleagues, including David Adelani 🇳🇬 #COLM2025, looking for postdocs, Bonaventure F. P. Dossou Antonis Anastasopoulos alexandra birch Sara Hooker Holy Lovenia @mehakdh1.

🚨 Check out our latest pre-print: EmbSum: Leveraging the Summarization Capabilities of Large Language Models for Content-Based Recommendations. University of British Columbia Meta MBZUAI Monash University Paper: arxiv.org/abs/2405.11441

#NAACL2024 let's connect! I presented two papers at this year's NAACL! 🚀How many languages does ChatGPT 'know': aclanthology.org/2024.findings-… 🚀Relationship between machine translation and diacritics (the tilde on ã): aclanthology.org/2024.naacl-lon… 👏Muhammad AbdulMageed Ife Adebara, Khai, and Qisheng

Thank you Margaretta Colangelo for sharing our work!

Introducing the LTSM-bundle Package! 🌟Thrilled to launch our open-source tool 🔧Assess various crucial designs to train Large Time Series Models (LTSMs), and identity the best training practices 🔗 Paper: arxiv.org/abs/2406.14045 🔗 GitHub: github.com/daochenzha/ltsm

We're at Bangkok presenting seven papers at #ACL2024. These works are the outcome of collaborations between University of British Columbia, MBZUAI, AI at Meta, Google DeepMind, and Invertible AI. Here's a list with presentation spots: 12 August 2024: 📜LLM Performance Predictors are good initializers

Today's poster session at the Chamber of Commerce, Yifei Sun will present our RecSys paper. We would be happy to speak with you about our work and research on LLM for recommendation if you are attending RecSys'24. AI at Meta University of British Columbia UBC School of Information UBC NLP Group MBZUAI Monash University ACM RecSys

🎉🎉Excited to introduce “🦌 Gazelle: An Instruction Dataset for Arabic Writing Assistance”, to appear at EMNLP 2024 (Findings). 📎 Gazelle is manually curated, instruction-style dataset crafted in both English and Arabic, specifically designed to advance the development of

📢Excited to present "Taylor Unswift" poster at #EMNLP24 in Miami! Join us on Nov 13 (Wed), 10:30–12:00, at Main #778. "Taylor Unswift" aims to solve the dilemma of secured weight release for LLM developers and users. 🔗Paper: arxiv.org/pdf/2410.05331 🔗Code:

️‍Today we announce 🌴 Palm, our largest community project to date. Thrilled to share “🌴 Palm: A Culturally Inclusive and Linguistically Diverse Dataset for Arabic LLMs.” 🌍️‍ This large-scale, community-driven effort has been in the works for over a year and unites 44