Assistant professor. I am investigating the question: how much data do we need for AI? I am interested in transformers, Bayesian ML, and meta-learning.
Delft, Netherlands
Joined November 2011
- Tweets42
- Following220
- Followers245
- Likes637
ICLR got 507 submissions in 2017. This year: 60,000+.
Clearly, we have entered a new era of scientific discovery. As an AI professor, I dealt with this the only reasonable way: I made a slopcore music video with Claude + Suno.
Slop-science 🎶🔊
🤖 Made with AI
Very happy today with the interesting questions at the posters when presenting our work: Alpha-PFN Fast Entropy Search via ICL! Find model weights here: github.com/automl/AlphaPFN Let me know if you have any questions or want to chat at ICML!
Drowning in 6,000+ ICML papers? 😵I vibecoded an ICML 2026 paper filter: scores all 6,341 accepted papers against keyword you define, then outputs a one page offline HTML file with day/time/room + filters. Uses simple keyword matching (no LLMs).
github.com/tomviering/ICML20…
Excited to be presenting 3 papers at ICML this year, would love to chat if you're around!
MalTree: Tracing Malware Evolution using Embeddings at Scale
α-PFN: Fast Entropy Search via In-Context Learning
Context-Aware Learning Curve Extrapolation with Prior-Data Fitted Networks
🗓️ Sat, FMSD Workshop, 15:45–17:00
Context-Aware Learning Curve Extrapolation
We adapt LC-PFN transformer with register tokens to curb overfitting, and condition extrapolation on learner identity to capture learner-specific curve dynamics.
🔗 openreview.net/forum?id=oN4F…
🗓️ Wed, Poster Session 4, 14:30–16:15, Hall A
α-PFN: Fast Entropy Search
We use Prior-Data Fitted Networks (PFNs) to accelerate Predictive, Max, and Joint Entropy Search up to 72x. We amortize the expensive Bayesian Optimization acquisition function.
automl.github.io/AlphaPFN/
🗓️ Tue, Poster Session 2, 14:00–15:45, Hall A
MalTree: Tracing Malware Evolution using Embeddings at Scale
The first Malware Family Tree, built with Transformer embeddings over large-scale malware corpora. By my MSc student Akash Amalan.
🔗 aj730.github.io/Phylogenetic…
Tom Viering retweeted
I'm hiring for a fully funded #PhD position in #ComputerVision on 'Detailed Video Understanding' at @LIACS @UniLeiden.
Apply before 22nd June. More info👇
universiteitleiden.nl/en/vac…
Tom Viering retweeted
The deadline for @NeurIPSConf 2024 has passed, but it doesn't mean we don't work hard to have another fantastic conference! Right now, we are in need for REVIEWERS. If you know someone suitable for this role, please fill in this form: forms.gle/W3Yrdqxu4jE11QhG7
Tom Viering retweeted
🚀 We're looking for a PhD student to join our team at @tudelft!
Deadline for applications is January 5.
Please share, and feel free to contact me if you have any questions.
Together with Julia Olkhovskaia I am looking for a (fully paid) PhD student to work on multi-armed bandits and reinforcement learning theory.
Please share!
More details: fransoliehoek.net/wp/vacanci…
Note: we hope to recruit through the ELLIS PhD program. Deadline Nov. 15!
Tom Viering retweeted
Every StatML intro class covers complexity-error U-curves, so @Jeffaresalan & I asked ourselves whether the info from these classes is enough to explain double descent too? Our #NeurIPS23 paper does a roundtrip of The Elements of Statistical Learning and answers “Yes”! Long🧵1/n
I am hiring a PhD student. The topic will be related to deep meta-learning on learning curves. You can apply here:
tudelft.nl/over-tu-delft/wer…
I will soon open up a PhD position for deep learning on learning curves. See here:
tomviering.nl/vacancy.html
Challenge: Developing deep meta-learning algorithms to model and understand learning curve patterns in machine learning.
Impact: Faster, better, more cost-efficient ML.
Tom Viering retweeted
And one more new MOOC, by Hongrui Wang, Amira lnouty, Luca laurenti, Wendelin Bohmer and @TViering. Covers AI concepts of clustering, dimensionality reduction, and introduces you to reinforcement and deep learning. Starts May 16th, so enroll now! online-learning.tudelft.nl/c…
Tom Viering retweeted
New MOOC by @TViering and Hanne Kekkonen: learn the basics of (supervised) machine learning, e.g. various classification and regression machine learning algorithms to solve real-life problems with scikit-learn in Python. Starts May 16th, so enroll now!
online-learning.tudelft.nl/c…
Tom Viering retweeted
📢 #PhDposition! I have a vacancy @tudelft dealing with generating digital humans in social contexts. If you're interested in working at the intersection of multimodal ML, social cognition, and CV/graphics, this may be for you!
linkedin.com/jobs/view/35376…
#GenerativeAI #vacancy
Tom Viering retweeted
We love learning curves! This is why we created #LCDB (github.com/fmohr/lcdb), a database with API to LCs of 20 sklearn classifiers for 219 datasets, including pred. vectors for train/val/test folds. Check out @TViering's talk on the associated paper this Thursday at @ECMLPKDD.
