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 17) | Thursday (Sep 18) | ||
|---|---|---|---|
| 08:30-8:55 | Registration and coffee |
08:30-9:00 | Coffee |
| 08:55-09:00 | Opening remarks Jes Frellsen |
||
Session 1: Diffusion models and controlled generation Chair: Jes Frellsen |
Session 3: Stochastic interpolants Chair: Pierre-Alexandre Mattei |
||
| 09:00-10:00 | Valentin De Bortoli On the Edge of Memorization in Diffusion Models |
09:00-10:00 | Eric Vanden-Eijnden Beyond standard diffusion: Stochastic interpolants for Föllmer processes and multitask learning |
| 10:00-10:30 | Coffee |
10:00-10:30 | Coffee |
Session 4: Generative models for molecules Chair: Wouter Boomsma |
|||
| 10:30-11:30 | Marta Skreta Controlling Diffusion Models at Inference Time for Scientific Discovery |
10:30-11:30 | Masatoshi Uehara Reward-Guided Generation in Diffusion Models: Toward Programmable Protein Design |
| 11:30-12:30 | Francisco Vargas Density ratios for diffusion process: From sampling to conditional generative modelling |
11:30-12:30 | Michalis Titsias Learning-Order Autoregressive Models with Application to Molecular Graph Generation |
| 12:30-13:30 | Lunch |
12:30-13:30 | Lunch |
Session 2: AI in society and economics Chair: Ole Winther |
Session 5: Inductive structures in generative modelling Chair: Søren Hauberg |
||
| 13:30-14:30 | Michael I. Jordan A Collectivist, Economic Perspective on AI |
13:30-14:30 | Alexander Denker Solving Inverse Problems using Diffusion Models |
| 14:30-15:00 | Coffee |
14:30-15:30 | Siddharth N Explicit Inductive Biases for Efficient Modelling and Representation Learning |
Session 3: Experimental design Chair: Pierre-Alexandre Mattei |
|||
| 15:00-16:00 | Florence Forbes Scalable Bayesian Experimental Design with Diffusions |
15:30-15:35 | Parting remarks Søren Hauberg |
| 16:00-17:00 | Tom Rainforth Intelligent Information Gathering with LLMs and Bayesian Experimental Design |
15:10-15:30 | Coffee and goodbye |
| 17:00-19:00 | Poster session with reception |
||
| 19:30-22:30 | Dinner at Gemini |
||
Registration
If you would like to attend this workshop but have yet to receive an invitation, then please write an email to Søren Hauberg and include a link to your website or Google Scholar profile. Note that seating is limited, so we cannot guarantee a ticket.
Venue
Carlsberg Akademi
Gamle Carlsberg Vej 15
1799 Copenhagen V
Carlsberg Akademi is less than 10 minutes walk from Carlsberg S-train Station.
Dinner
Restaurant Gemini
Gl. Kongevej 10, Entrance from the sea
1610 Copenhagen V
Restaurant website
Gemini offers a dining experience centered on fresh, seasonal Nordic ingredients, where sustainability and taste take center stage.
Recommended hotel
Hotel Ottilia
Bryggernes Plads 7
1799 Copenhagen V
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 Danish Data Science Academy, the Carlsberg Foundation, and the Center for Basic Machine Learning Research in Life Science.