Ana Marasović

It was manifesting, successfully so

Are you referring to the winter in morning and the spring/summer in afternoon lolol

Been less than a year since I started my lab at @utah.edu and we already have a ton of new stuff that I can’t wait to talk about soon.

I’ll start today by sharing that our updated Computer Use Survey blog has been accepted to ICLR Blogposts 2026.
iclr-blogposts.github.io/2026/blog/20...

So happy that I'm covering this paper in the last lecture before the spring break (coincidentally, planning is happening on-the-fly) – it's a perfect wrap of the first part of the class

Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics Do large language models (LLMs) solve reasoning tasks by learning robust generalizable algorithms, or do they memorize training data? To investigate this question, we use arithmetic reasoning as a rep...

Great test for anyone learning mech interp is reading Nikankin et al's "Arithmetic Without Algorithms" which uses activation patching / circuits, probing, logit lens, describing max activating examples.. If you you follow along while reading, you'll realize you know a lot!

arxiv.org/abs/2410.21272

Getting sick in the middle of the semester, like catching a flu, makes every next week of the semester progressively worse. Will I ever catch up 😭

Really clever idea to use AlphaEvolve here! Looking forward to reading more carefully

I know grant writing is supposed to be miserable. Maybe once I've written a few and had them all rejected I will agree. But it's kind of my favorite genre to write currently? It's pure optimism! These are my hopes for the future! My favorite ideas! Untainted by messy and limited results!

I don't know why I thought it's a distraction from research, makes no sense now :)

Somehow before becoming a prof I came away with the impression that grant writing was an annoying task profs have to do, and yes, more rejection sucks, but it is wonderful to start new collaborations with super smart people, brainstorm hard, and think on a larger scale than next few papers

Still too many :')

I enjoyed reading this but there are a lot of presuppositions in the part about folks asking you whether they should leave their PhD, and hope folks aren't generalizing from that.

It's so depressing to see 20-30K papers submitted to every top ML conference

Is your study based on submissions before arXiv moderation?

Mathematicians are really nice to their LLMs; seen in: arxiv.org/abs/2601.01235

New year, new porcupine sighting!

If by correctly described you mean properly use them in text, this was atrocious pre-LLMs 😅

Very LLMy: utah-cs6340-nlp.notion.site

We had the limit before we switched to openreview, so this is kind of new

We need to return word limit to author responses

We are hiring in AI and NLP at Utah! Please apply if interested and share with folks you know are looking for faculty positions, especially if they like to ski, hike, climb, or bike! utah.peopleadmin.com/postings/190...

New Postdocs Will Advance Tutor Chatbots, Bionic Hands, and Understanding of Pollution’s Impact on Reproductive Health - One-U Responsible AI Initiative December 10, 2025 Mingjia Hu Mentors: One-U RAI faculty fellow Chenglu Li, assistant professor, Department of Educational Psychology; One-U RAI faculty fellow Ana Marasović, assistant...

💫 On the heels of announcing 12 new faculty fellows last week, SCI's One-U Responsible AI Initiative is excited to add three new postdoctoral fellows to its team next year: rai.utah.edu/postdocs-dec...

University of Utah team discovers rare computer relic A research team at the University of Utah uncovered a rare piece of computing history.

KSL TV @ksl.com interviewed the members of my research group who recently discovered a rare piece of computing history: an old tape that might contain UNIX V4. ksltv.com/science-tech...

Make it make sense 😂

One-U RAI Welcomes 12 New Faculty Fellows Driving Responsible AI Across Disciplines - One-U Responsible AI Initiative December 1, 2025 The University of Utah One-U Responsible Artificial Intelligence Initiative (One-U RAI) at the Scientific Computing and Imaging (SCI) Institute has named 12...

📣 Meet the 12 new faculty fellows joining SCI’s One-U Responsible AI Initiative. These professors are advancing AI research to solve real-world challenges, from protecting the West’s water supply to improving medical care to embedding ethics in AI education. bit.ly/rai-fac-26

Mine also see 100% human-written!

Is it me or more reviewers are -strongly- opinionated about how you paper should be written?

I feel like my responses in the past year or two are turning into arguments about why my writing is just fine

Current ChatGPT response format is such an eyesore, what’s up with all the lists and emojis

Luca Guadagnino making an OpenAI movie, what's happening 👀👀