Kamilė Stankevičiūtė

PhantomWiki has just been accepted at #ICLR2025 DATA-FM workshop! 🎉

🎉 PhantomWiki is accepted to the @iclr-conf.bsky.social DATA-FM workshop! Come chat with us in Singapore 🦁

🧠 The reasoning + retrieval benchmark comes right on the heels of new @realaaai.bsky.social presidential report: AI Reasoning and Agents research front and center!

Excited to announce our new work on reasoning and retrieval evaluation in LLMs! 😊

Check it out!

An Adversarial Analysis of Thompson Sampling for Full-information Online Learning: from Finite to Infinite Action Spaces We develop an analysis of Thompson sampling for online learning under full feedback - also known as prediction with expert advice - where the learner's prior is defined over the space of an adversary'...

New preprint!

This is a hardcore technical paper on Thompson sampling - as a strategy for the so-called online learning game.

I think it's one of the most long-term important things I have ever worked on due to what it makes possible.

That needs explaining: thread below!

arxiv.org/abs/2502.14790

I work on machine learning for tabular medical data—especially the data efficiency and reproducibility aspects. Excited to meet new people in the field!

👋😊

Hi, I am currently at Cornell! 😊