Christian A. Naesseth
banner
canaesseth.bsky.social
Christian A. Naesseth
@canaesseth.bsky.social
Assistant Professor of Machine Learning
Generative AI, Uncertainty Quantification, AI4Science
Amsterdam Machine Learning Lab, University of Amsterdam

https://naesseth.github.io
Oh, rip, the camera-ready PDF on Open Review is only "privately revealed". Sorry about that :(

proceedings.mlr.press/v258/chen25f...
proceedings.mlr.press/v258/timans2...
May 3, 2025 at 10:19 PM
Come check out SDE Matching at the #ICLR2025 workshops, a new simulation-free framework for training fully general Latent/Neural SDEs (generalisation of diffusion and bridge models).

FPI: Morning poster session
DeLTa: Afternoon poster session

#SDE #Bayes #GenAI #Diffusion #Flow
April 27, 2025 at 11:27 PM
Make sure to get your tickets to AABI if you are in Singapore on April 29 (just after #ICLR2025) and interested in probabilistic modeling, inference, and decision-making!

Tickets (free but limited!): lu.ma/5syzr79m
More info: approximateinference.org

#Bayes #MachineLearning #ICLR2025 #AABI2025
April 13, 2025 at 7:43 AM
April 13, 2025 at 7:40 AM
One way to get (almost) both is to penalise the curvature of the learned velocity field of diffusion/bridge explicitly. We do this in our paper on Neural Flow Diffusion Models. There are also bridge variants in the paper.

arxiv.org/abs/2404.12940
February 8, 2025 at 2:39 PM
#AISTATS decisions are out! My lab went 2 for 2 😀

I would also recommend having a look at submitting to the AABI fast-track or workshop track that happens in-between ICLR and AISTATS in Singapore: approximateinference.org
January 22, 2025 at 11:08 AM
Today is Lucia, not really celebrated much outside Sweden. But it's a fun tradition with lots of candles, song, snacks, glögg, etc.

For now here is a pic with Christmas tree 🎄 at work #Lab42 #NeuralNetworks #ML
December 13, 2024 at 11:22 AM
VISA: Variational Inference with Sequential Sample-Average Approximations

Heiko Zimmermann · Christian Andersson Naesseth · Jan-Willem van de Meent

Thu 12 Dec 11 a.m. PST — 2 p.m. PST
East Exhibit Hall A-C #4105
December 12, 2024 at 1:05 PM
Fast yet Safe: Early-Exiting with Risk Control

Metod Jazbec · Alexander Timans · Tin Hadži Veljković · Kaspar Sakmann · Dan Zhang · Christian Andersson Naesseth · Eric Nalisnick

Thu 12 Dec 11 a.m. PST — 2 p.m. PST
East Exhibit Hall A-C #4505
December 12, 2024 at 1:05 PM
Equivariant Neural Diffusion for Molecule Generation

François Cornet · Grigory Bartosh · Mikkel Schmidt · Christian Andersson Naesseth

Thu 12 Dec 11 a.m. PST — 2 p.m. PST
East Exhibit Hall A-C #2403
December 12, 2024 at 1:05 PM
December 9, 2024 at 7:52 AM