Applications open to the Phd program in Information Systems at Middle East Technical University Graduate School of Informatics ii.metu.edu.tr/application-re…

If you are interested in doing a fully-funded PhD with me you can get in touch in advance to get feedback on your application and apply to the scholarships. Deadline for applications: May 23rd, 2025.

It was a great experience to visit Baku and participate in the Big Data and AI Forum at ADA University. Thank you very much once again to the organizers for their hospitality and efforts to make AI research accessible and useful to more communities.

Excited to announce the call for papers for the Multilingual Representation Learning workshop #EMNLP2025 sigtyp.github.io/ws2025-mrl.html with Duygu Ataman Catherine Arnett Jiayi Wang Fabian David Schmidt Tyler Chang Hila Gonen and amazing speakers: Alice Oh, Kelly Marchisio, & Pontus Stenetorp

Really thought-provoking new paper on representation learning and the notion of 'semantic compression' by Chen Shani Dan Jurafsky Yann LeCun Ravid Shwartz Ziv

Nice example of using an RCT to measure real-world impact of LLM tech

🧵generative models are sweet, but navigating existing repositories can be overwhelming, particularly when starting a new research project so i built jax-interpolants, a clean & flexible implementation of the stochastic interpolant framework in jax github.com/nmboffi/jax-in…

5 Habits That Are Killing Your Productivity: 1. You don’t wake up early (Marcus Aurelius) 2. You focus on what’s outside your control (Epictetus) 3. You don’t know how to say “no” (Seneca) 4. You’re in the wrong crowd (Marcus Aurelius) 5. You think you’ll live forever (Seneca)

Anyone else who needs group therapy to vent about all the new agent swarms

My NYU Center for Data Science colleague, Carlos Fernandez-Granda, released the 700-page textbook «Probability and Statistics for Data Science», where he condenses 10 years of teaching experience at @NYUniversity. 200 exercises, 102 notebooks, 115 videos! 🥳🥳🥳 ps4ds.net

The submission deadline for the 5th Workshop on Multilingual Representation Learning is coming up! See details below!

Who else is crazy excited to go to Suzhou for EMNLP?

*I-Con: A Unifying Framework for Representation Learning* by Shaden Mark Hamilton et al. They show that many losses (contrastive, supervised, clustering, ...) can be derived from a single loss defined in terms of neighbors distributions. arxiv.org/abs/2504.16929

Excited to hold the first weekly meeting of my research group METU Cognitive Science / ODTÜ Bilişsel Bilimler. Today our visiting researcher Kavsar Huseynova shared insights on how neural reasoning pathways can be traced in LLMs.

What is the current accepted policy for citing papers with very long list of authors? Our overleaf is crashing for bibtex entries with 100+ authors. Thanks!

What are some recommendations for more recent RL textbooks with comprehensive descriptions of applications in LLMs?