Metod Jazbec

Machine Learning PhD student at @AmlabUva

[Erik Bekkers @erikjbekkers]

Excited to share that we're looking for a new colleague at @AMLab_UvA : Assistant Professor in AI for Science 🔬🤖

AMLab is a world-class ML research group embedded in Amsterdam's thriving AI ecosystem: leading research groups, an ELLIS unit, startups, and big tech — all within reach.

And Dutch academic labor conditions are genuinely among the best in Europe ❤️

Deadline: May 30 👉 https://t.co/PseZ3bsh2B

[Floor Eijkelboom @FEijkelboom]

Discrete diffusion — but fast? ⚡️ Test-time inference — but for discrete data? 🧠

Categorical Flow Maps: continuous transport toward the simplex, turning discrete generation into a single-step problem. Built on Variational FM (CatFlow), we obtain (self-)distillation from scratch.

Language, molecules, and test-time steering — one framework.

Scaling to LLMs and foundation models next. Watch this space 👀

[Metod Jazbec @MetodJazbec]

Presenting today at @NeurIPSConf from 11am-2pm (poster number #3904)👇👇

[Mona Schirmer @ ICLR 🇧🇷 @monaschir]

TTA Monitor is coming to #NeurIPS2025!

Our monitor flags risk increase of a continuously adapting model without any labels and with false-alarm guarantees.

Let’s dive in! 🧵 1/6

📄 Paper: https://t.co/ABtcNfNZhz
📌 Poster: https://t.co/SWMbHlAqqZ

[Metod Jazbec @MetodJazbec]

This was a super fun project with @monaschir, see you all at NeurIPS soon! ✈️

[Mona Schirmer @ ICLR 🇧🇷 @monaschir]

TTA Monitor is coming to #NeurIPS2025!

Our monitor flags risk increase of a continuously adapting model without any labels and with false-alarm guarantees.

Let’s dive in! 🧵 1/6

📄 Paper: https://t.co/ABtcNfNZhz
📌 Poster: https://t.co/SWMbHlAqqZ

[Mona Schirmer @ ICLR 🇧🇷 @monaschir]

Come by our Oral on Monitoring Risks in Test-time Adaptation at the @PUT_TTA_ICML25 #ICML Workshop

⏱️: Friday, 10am PDT
🚩: West Meeting Room 220-222

Work with @MetodJazbec @canaesseth @eric_nalisnick

[Christian A. Naesseth @canaesseth]

📜 Monitoring Risks in Test-Time Adaptation
(ICML PUT Workshop Oral!)

Time: Fri 18 Jul 10 a.m. PDT
Location: West Meeting Room 220-222
Presenter: @monaschir

https://t.co/r8av1Gozyn

[Metod Jazbec @MetodJazbec]

Great too see that our Generative Uncertainty won the best paper award at the ICLR QUESTION workshop (https://t.co/5O1iUK2Kmv). If you're interested in what Bayesian/ensembling methods can bring to the world of diffusion models, check out the paper 👇

https://t.co/41SII4NAUq

[UvA AMLab @AmlabUva]

🥇 3 Best Paper Awards for AMLab members!

1. Towards Variational Flow Matching on General Geometries by @olgazaghen @FEijkelboom

2. Generative Uncertainty in Diffusion Models by @MetodJazbec

3. SDE Matching by @GrigoryBartosh

Congrats to everyone! 🔥

[UvA AMLab @AmlabUva]

Generative Uncertainty in Diffusion Models (spotlight)

by @MetodJazbec Eliot Wong-Toi, Guoxuan Xia, Dan Zhang, Eric Nalisnick, Stephan Mandt

➡️ https://t.co/fTVDcft6B8
⚠️ Quantify Uncertainty and Hallucination in Foundation Models: The Next Frontier in Reliable AI

[Metod Jazbec @MetodJazbec]

Come say hi to me, @AlexTimans, and @eric_nalisnick today between 11am-2pm in East Exhibit Hall A-C #4505 . We'll be presenting our Fast yet Safe paper on efficient inference and risk control 👇

[Metod Jazbec @MetodJazbec]

Hey! Catch me next week at @NeurIPSConf where we’ll be presenting our Fast yet Safe paper. We show how to equip efficient AI methods like early-exiting or soft speculative decoding with performance guarantees using risk control!

https://t.co/8zwhOefRhA

🧵🔽

[Metod Jazbec @MetodJazbec]

All there projects are a result of very fun collaborations with Master students at @UvA_Amsterdam and my summer internship at @Microsoft

If you also find efficiency and robustness of LLMs/diffusion interesting, do reach out next week, happy to chat more about it!

[Metod Jazbec @MetodJazbec]

I will also be presenting 3 workshop papers at @NeurIPSConf , all related to the efficiency of LLMs/diffusion

🧵👇

[Metod Jazbec @MetodJazbec]

And finally in “On Efficient Distillation from LLMs to SLMs”, we investigate the importance of incorporating student model’s feedback for data efficiency when generating synthetic data for knowledge distillation between LLMs and SLMs

https://t.co/YQ4TkZE6PR

[Metod Jazbec @MetodJazbec]

If this caught your attention, have a look at out paper and come talk to us during the NeurIPS poster session on Thu 12 Dec at 11:00 a.m. PST (East Exhibit Hall A-C #4505)

Great collaboration with: @AlexTimans, @eric_nalisnick, @canaesseth, @isDanZhang, @HvTin and others

[Metod Jazbec @MetodJazbec]

Hey! Catch me next week at @NeurIPSConf where we’ll be presenting our Fast yet Safe paper. We show how to equip efficient AI methods like early-exiting or soft speculative decoding with performance guarantees using risk control!

https://t.co/8zwhOefRhA

🧵🔽

[Metod Jazbec @MetodJazbec]

In our experiments, we apply our approach to calibrate a broad set of models for different tasks, ranging from machine translation using LLMs to image generation with diffusion