Generative models and uncertainty quantification lie at the heart of Bayesian modelling and inference. At this small meeting, we discuss recent developments within the field. The workshop is deliberately kept small to ensure the discussions remain honest, lively and interesting. Attendance is, thus, primarily by invitation, but one can apply to join (see below).
A safe environment is a prerequisite for engaging discussions. Participants are, thus, expected to abide by the DDSA Code of Conduct.
Speakers
Program
| Wednesday (Sep 18) | Thursday (Sep 19) | ||
|---|---|---|---|
| 08:30-8:55 | Registration and coffee |
08:30-9:00 | Coffee |
Session 1: Flow matching Chair: Jes Frellsen |
Session 3: Bayesian and probabilistic methods Chair: Søren Hauberg |
||
| 08:55-09:00 | Opening remarks Jes Frellsen |
||
| 09:00-09:50 | Ricky T. Q. Chen The Flow Matching Recipe for Generative Modeling: continuous and discrete |
09:00-09:50 | Julyan Arbel Rapture of the deep: highs and lows of Bayes in a world of depths |
| 09:50-10:40 | Heli Ben-Hamu Differentiating through flows for controlled generation |
09:50-10:40 | Robert Peharz Probabilistic circuits: progress and challenges |
| 10:40-11:10 | Coffee |
10:40-11:10 | Coffee |
Session 4: Large language model Chair: Ole Winther |
|||
| 11:10-12:00 | Michael Albergo Flow map matching |
11:10-12:00 | Michal Valko Gamification of large language models |
| 12:00-13:30 | Lunch at Hyttefadet |
12:00-13:30 | Lunch at FIAT |
Session 2: Diffusion Chair: Ole Winther |
Session 5: Climate and weather Chair: Wouter Boomsma |
||
| 13:30-14:20 | Sander Dieleman Perspectives on diffusion |
13:30-14:20 | Anna Vaughan Neural processes for climate and weather |
| 14:20-15:10 | Christian A. Naesseth There and back again: A forward diffusion tale |
14:20-15:10 | Fredrik Lindsten Probabilistic weather forecasting with hierarchical graph neural networks |
| 15:10-15:30 | Coffee |
15:10-15:30 | Coffee |
| 15:30-16:20 | Jiaxin Shi Discrete generative modeling with masked diffusions |
15:30-16:20 | Frank Wood Some challenges en route to embodied AI |
| 16:20-17:10 | Ruiqi Gao Exploring the power of diffusion: From understanding the objectives to 3D applications |
16:20-16:30 | Closing remarks |
| 17:10-17:20 | Break |
||
| 17:20-18:10 | Ayush Tewari Probabilistic 3D Perception |
||
| 18:10-19:30 | Poster session |
||
| 20:30-00:00 | Dinner at Baka d'busk |
||
Registration
Registration is closed.
Venue
Assembly Hall at Charlottenborg Castle
The Royal Danish Academy of Art
Kongens Nytorv 1
1050 Copenhagen K
Venue website
Charlottenborg is a one-minute walk from the Kongens Nytorv metro station, which is reachable directly from the airport (M2 line, 15 minutes).
Dinner
Baka d'busk
Rantzausgade 44
2200 Copenhagen
Restaurant website
The kitchen is a plant-based bistro. The menu changes with the season, and the availability of locally grown crops decides what will end up on your plate. The house Sommelier also attentively created the wine card, and the main focus is on natural wines.
Recommended hotel
Ibsens Hotel
Vendersgade 23
DK-1363 Copenhagen K.
Hotel website
We recommend this nearby hotel where most speakers will also stay.
Organisation
The workshop is jointly organised by:
Funding
The workshop is funded by the Center for Basic Machine Learning Research in Life Science, the Carlsberg Foundation, the Pioneer Center for AI, and the Danish Data Science Academy.