Mona Schirmer @ NeurIPS

35 posts

Mona Schirmer @ NeurIPS

Mona Schirmer @ NeurIPS

@monaschir

PhD Candidate @AmlabUva @ELLISforEurope | AI safety & robustness | Alumni @Amazon @WorldBank @ENSAEparis @TUBerlin

Amsterdam, Niederlande Katılım Ocak 2018
305 Takip Edilen230 Takipçiler
Mona Schirmer @ NeurIPS 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
193
23.2K
Mona Schirmer @ NeurIPS
Mona Schirmer @ NeurIPS@monaschir·
5/ The monitor reliably detects risk violations across TTA methods and datasets and even detects TTA collapse!
Mona Schirmer @ NeurIPS tweet media
English
0
0
2
60
Mona Schirmer @ NeurIPS
Mona Schirmer @ NeurIPS@monaschir·
4/ Our bound is unsupervised and uses only model uncertainty as a loss proxy. Because we calibrate the proxy threshold online, the bound remains valid and tight even under severe shift and model adaptation (e.g. via entropy minimization).
English
0
0
2
55
Mona Schirmer @ NeurIPS
Mona Schirmer @ NeurIPS@monaschir·
3/ Our monitor lower-bounds the test risk (🟩) and raises an alarm once the confidence lower bound (🟦) exceeds a pre-defined risk level (⬛). Confidence sequences ensure that the alarm remains anytime-valid with statistical guarantees on the false-alarm rate.
Mona Schirmer @ NeurIPS tweet media
English
0
0
2
58
Mona Schirmer @ NeurIPS
Mona Schirmer @ NeurIPS@monaschir·
2/ Test-Time Adaptation (TTA) helps models adjust to distribution shift on the fly without labels. But TTA can silently fail or collapse (e.g., by predicting a single class ⬆️)!
English
0
0
2
58
Mona Schirmer @ NeurIPS retweetledi
Natasha Butt
Natasha Butt@NatashaEve4·
🔥New preprint: Soft Tokens, Hard Truths Introduces the first scalable continuous-token RL method for LLMs - no reference CoTs needed; scales to hundreds of thought tokens. Best to train soft, infer hard! Pass@1 parity ⚖️, Pass@32 gains 📈& better robustness 🛡️ vs. hard CoT 1/🧵
Natasha Butt tweet mediaNatasha Butt tweet media
English
5
50
276
35.9K
Mona Schirmer @ NeurIPS retweetledi
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
Mona Schirmer @ NeurIPS retweetledi
Manuel Madeira
Manuel Madeira@manuelmlmadeira·
Good morning NeurIPS! Excited to present "Generative Modelling of Structurally Constrained Graphs" with Clément Vignac, @DorinaThanou , and @pafrossard. Come find me at poster #2704 in East Exhibit Hall A-C from 16:30-19:30 if you're interested in constrained graph diffusion!
English
0
4
14
1.3K
Mona Schirmer @ NeurIPS
Mona Schirmer @ NeurIPS@monaschir·
Excited to see #ImpactAI debuting at @Googleorg 's Impact Summit! Very grateful to have been part of the journey over the last two years. Check out how #ImpactAI helps to make better decisions in development economics ⬇️
World Bank Research@wb_research

Today @WorldBank Development Impact (#DiME) is debuting #ImpactAI at @Googleorg’s Impact Summit. Learn how DiME's team is making research more accessible with #GenAI ➡️ rb.gy/5mtywu #AcceleratedWithGoogle

English
0
0
4
368
Mona Schirmer @ NeurIPS retweetledi
Stratis Tsirtsis
Stratis Tsirtsis@stratis_·
👋I am on the academic job market, looking for tenure-track positions. I work on machine learning, decision making, and social aspects of AI. Let's get in touch if your institution is hiring! 💻stsirtsis.github.io 😀Shares are very much appreciated!
Stratis Tsirtsis tweet media
English
2
20
52
9K
Mona Schirmer @ NeurIPS retweetledi
WiML
WiML@WiMLworkshop·
📢 ⏰ Deadline Alert! ⏰ Only 10 days left to submit your abstracts for the 19th Women in Machine Learning Workshop at #NeurIPS2024! 👩‍💻 Don't miss this amazing opportunity to share your research! Submit now: tinyurl.com/wiml2024cfp #womenintech #WiML #MachineLearning
English
2
19
46
17.1K
Mona Schirmer @ NeurIPS retweetledi
Christian A. Naesseth
Christian A. Naesseth@canaesseth·
I’m hiring a postdoc to work with me on exciting projects in generative modelling (AI) and/or uncertainty quantification. You'll be part of a great team, embedded in @AmlabUva and the UvA-Bosch Delta Lab. Apply here: vacatures.uva.nl/UvA/job/Postdo… RT appreciated! #ML #GenAI
English
1
30
95
17.1K
Mona Schirmer @ NeurIPS
Mona Schirmer @ NeurIPS@monaschir·
Had a great time presenting our STAD work at the #ICML2024 SPIGM workshop this weekend. Thanks for the many engaging discussions!
Mona Schirmer @ NeurIPS tweet media
English
3
9
99
8.3K
Mona Schirmer @ NeurIPS retweetledi
Dan Zhang
Dan Zhang@isDanZhang·
Things change all the time, and we cannot stop that. Check out our poster if you don’t want to keep retraining your deployed models!
Mona Schirmer @ NeurIPS@monaschir

Drop by our poster at the #ICML2024 SPIGM Workshop on Friday! With @eric_nalisnick and @isDanZhang we propose probabilistic state-space models to adapt a classifier to distribution shift without seeing any labels. 📍SPIGM Workshop, Lehar 3, 15:10-16:10

English
0
1
3
366
Mona Schirmer @ NeurIPS
Mona Schirmer @ NeurIPS@monaschir·
Drop by our poster at the #ICML2024 SPIGM Workshop on Friday! With @eric_nalisnick and @isDanZhang we propose probabilistic state-space models to adapt a classifier to distribution shift without seeing any labels. 📍SPIGM Workshop, Lehar 3, 15:10-16:10
Mona Schirmer @ NeurIPS tweet media
English
1
2
20
1.9K

Keşfet

@NeurIPSConf @MetodJazbec @canaesseth @PUT_TTA_ICML25 @DorinaThanou @pafrossard @Googleorg @AmlabUva