Probabilistic machine learning, Bayesian computation, and computer vision
PhD in Computer Science
📍Helsinki, Finland
https://pipme.github.io/
Chengkun Li
Loading...
All approximations are wrong, but some are useful --> Stacking can make them more useful 😄
I’ll be at the AABI symposium tomorrow. Looking forward to seeing everyone there!
😀 Enter the amortized Bayesian workflow from here 👉
pipme.github.io/amortized-Ba...
Huge thanks to my great collaborators:
@avehtari.bsky.social, @paulbuerkner.com, @stefanradev.bsky.social, @lacerbi.bsky.social, @marvin-schmitt.com!
1/ Introducing ACE (Amortized Conditioning Engine)! Our new AISTATS 2025 paper presents a transformer framework that unifies tasks from image completion to BayesOpt & simulator-based inference under *one* probabilistic conditioning approach. It's Bayes all the way down!
If you want to start your own research group in AI & machine learning, with access to top resources for research incl. @lumi-supercomputer.eu, generous starting package & professorship affiliation with a university in the world’s happiest country, apply by March 9: www.ellisinstitute.fi/PI-recruit
1/ If you are at ICLR / AABI / AISTATS, check out work from our lab and collaborators on *inference everywhere anytime all at once*!
Go talk to my incredible PhD students @huangdaolang.bsky.social & @chengkunli.bsky.social + amazing collaborator Severi Rissanen.
@univhelsinkics.bsky.social FCAI
Do you like to train neural networks to solve all your nasty probabilistic inference and sequential design problems?
Do you love letter salads such as NPs, PFNs, NPE, SBI, BED?
Then no place is better than the Amortized ProbML workshop we are organizing at #ELLIS UnConference.
1/ Just saw this paper using our PyVBMC (acerbilab.github.io/pyvbmc/) in structural engineering.
Nice to see sample-efficient Bayesian inference for expensive computational models used in the wild!
(Although we feel a bit more pressure to triple-check that our implementation has no bugs...)
Multi-Head Latent Attention vs Group Query Attention: We break down why MLA is a more expressive memory compression technique AND why naive implementations can backfire. Check it out!
Chengkun Li
Chengkun Li
Chengkun Li
Adaptive Bayesian workflow combining amortized inference with PSIS and MCMC diagnostics.
1/ Wouldn't it be nice if you could perform Bayesian inference *efficiently* but also *reliably*? Amortized inference offers the former, while MCMC is often presented as the "gold standard" for accuracy and reliability.
Enter the Amortized Bayesian Workflow...
Luigi Acerbi
me: now I've read the basic lit on approximate bayesian computation via bayesflow and I can start trying to distil it on time for the last lecture, to awe the students.
@chengkunli.bsky.social : hold my mcmc
(really really cool!)
Riccardo Fusaroli
Now recruiting new PIs in artificial intelligence and machine learning
1/ Excited to share our new work published in Transactions on Machine Learning Research (TMLR), Stacking Variational Bayesian Monte Carlo (S-VBMC)!
1/10🔥 New paper alert in #AABI2025 Proceedings!
Normalizing Flow Regression (NFR) — an offline Bayesian inference method.
What if you could get a full posterior using *only* the evaluations you *already* have, maybe from optimization runs?
😀 Enter the amortized Bayesian workflow from here 👉
pipme.github.io/amortized-Ba...
Huge thanks to my great collaborators:
@avehtari.bsky.social, @paulbuerkner.com, @stefanradev.bsky.social, @lacerbi.bsky.social, @marvin-schmitt.com!
⚡️Multi-Head Latent Attention is one of the key innovations that enabled @deepseek_ai's V3 and the subsequent R1 model.
⏭️ Join us as we continue our series into efficient AI inference, covering both theoretical insights and practical implementation:
🔗 datacrunch.io/blog/deepsee...
Luigi Acerbi
Luigi Acerbi
Adaptive Bayesian workflow combining amortized inference with PSIS and MCMC diagnostics.
1/ Wouldn't it be nice if you could perform Bayesian inference *efficiently* but also *reliably*? Amortized inference offers the former, while MCMC is often presented as the "gold standard" for accuracy and reliability.
Enter the Amortized Bayesian Workflow...
Multi-Head Latent Attention (MLA) improves upon Group Query Attention (GQA), enabling long-context reasoning models and wider adoption across open-source LLMs.
