Metod Jazbec

49 posts

Metod Jazbec

Metod Jazbec

@MetodJazbec

Machine Learning PhD student at @AmlabUva

Amsterdam, Netherlands Katılım Temmuz 2011
419 Takip Edilen202 Takipçiler
Metod Jazbec retweetledi
Erik Bekkers
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 👉 werkenbij.uva.nl/en/vacancies/a…
Erik Bekkers tweet media
English
3
34
191
22.6K
Metod Jazbec retweetledi
Floor Eijkelboom
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 👀
Oscar Davis@osclsd

You like discrete diffusion, but it's too slow? 🥀 You like test-time inference, but it's for continuous methods? 😩 We fixed it. Introducing Categorical Flow Maps: continuously sample discrete data in a single step 🚀💫 How? 🧵⬇️ 💪 Co-led with @FEijkelboom, @daan_roos_

English
2
18
102
20.9K
Metod Jazbec
Metod Jazbec@MetodJazbec·
Great too see that our Generative Uncertainty won the best paper award at the ICLR QUESTION workshop (…certainty-foundation-models.github.io). If you're interested in what Bayesian/ensembling methods can bring to the world of diffusion models, check out the paper 👇 arxiv.org/abs/2502.20946
Metod Jazbec tweet media
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! 🔥

English
2
2
30
2.1K
Metod Jazbec retweetledi
UvA AMLab
UvA AMLab@AmlabUva·
Generative Uncertainty in Diffusion Models (spotlight) by @MetodJazbec Eliot Wong-Toi, Guoxuan Xia, Dan Zhang, Eric Nalisnick, Stephan Mandt ➡️ openreview.net/forum?id=K54Vk… ⚠️ Quantify Uncertainty and Hallucination in Foundation Models: The Next Frontier in Reliable AI
UvA AMLab tweet media
English
1
1
8
434
Metod Jazbec
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! arxiv.org/abs/2405.20915 🧵🔽

English
1
1
17
659
Metod Jazbec
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!
English
0
0
3
120
Metod Jazbec
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 openreview.net/attachment?id=…
English
1
0
2
122
Metod Jazbec
Metod Jazbec@MetodJazbec·
I will also be presenting 3 workshop papers at @NeurIPSConf , all related to the efficiency of LLMs/diffusion 🧵👇
English
1
0
11
353
Metod Jazbec
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
Metod Jazbec tweet media
English
1
0
1
110
Metod Jazbec
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! arxiv.org/abs/2405.20915 🧵🔽
Metod Jazbec tweet media
English
1
3
24
2.4K

Keşfet

@NeurIPSConf @monaschir @PUT_TTA_ICML25 @canaesseth @UvA_Amsterdam @Microsoft @isDanZhang @HvTin