572 citations · 788 across the 31 of their papers we have counts for
34 papers
Assessing Sample Quality in Conditional Generation under Compositional Shift
Berker Demirel, Valentino Maiorca, Marco Fumero +2
Conditional generators provide a natural tool for controllable generation, including settings where the desired condition is a new composition of observed attributes or experimenta…
Position: agentic AI orchestration should be Bayes-consistent
Theodore Papamarkou, Pierre Alquier, Matthias Bauer +27
LLMs excel at predictive tasks and complex reasoning tasks, but many high-value deployments rely on decisions under uncertainty, for example, which tool to call, which expert to co…
Calibrated Test-Time Guidance for Bayesian Inference
Daniel Geyfman, Felix Draxler, Jan Groeneveld +3
Test-time guidance is a widely used mechanism for steering pretrained diffusion models toward outcomes specified by a reward function. Existing approaches, however, focus on maximi…
Parallel Token Prediction for Language Models
Felix Draxler, Justus Will, Farrin Marouf Sofian +3
Autoregressive decoding in language models is inherently slow, generating only one token per forward pass. We propose Parallel Token Prediction (PTP), a general-purpose framework f…
A path towards AI-scale, interoperable biological data
Brian Aevermann, Andrea Califano, Chi-Li Chiu +27
Biology is at the precipice of a new era where AI accelerates and amplifies the ability to study how cells operate, organize, and work as systems, revealing why disease happens and…
MorphGen: Controllable and Morphologically Plausible Generative Cell-Imaging
Berker Demirel, Marco Fumero, Theofanis Karaletsos +1
Simulating in silico cellular responses to interventions is a promising direction to accelerate high-content image-based assays, critical for advancing drug discovery and gene edit…
Learning Explicit Single-Cell Dynamics Using ODE Representations
Jan-Philipp von Bassewitz, Adeel Pervez, Marco Fumero +3
Modeling the dynamics of cellular differentiation is fundamental to advancing the understanding and treatment of diseases associated with this process, such as cancer. With the rap…
Variational Control for Guidance in Diffusion Models
Kushagra Pandey, Farrin Marouf Sofian, Felix Draxler +2
Diffusion models exhibit excellent sample quality, but existing guidance methods often require additional model training or are limited to specific tasks. We revisit guidance in di…
How to Build the Virtual Cell with Artificial Intelligence: Priorities and Opportunities
Charlotte Bunne, Yusuf Roohani, Yanay Rosen +39
The cell is arguably the most fundamental unit of life and is central to understanding biology. Accurate modeling of cells is important for this understanding as well as for determ…
Adjusting Pretrained Backbones for Performativity
Berker Demirel, Lingjing Kong, Kun Zhang +3
With the widespread deployment of deep learning models, they influence their environment in various ways. The induced distribution shifts can lead to unexpected performance degrada…
Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI
Theodore Papamarkou, Maria Skoularidou, Konstantina Palla +22
In the current landscape of deep learning research, there is a predominant emphasis on achieving high predictive accuracy in supervised tasks involving large image and language dat…
Modelling Cellular Perturbations with the Sparse Additive Mechanism Shift Variational Autoencoder
Michael Bereket, Theofanis Karaletsos
Generative models of observations under interventions have been a vibrant topic of interest across machine learning and the sciences in recent years. For example, in drug discovery…
Compositional Deep Probabilistic Models of DNA Encoded Libraries
Benson Chen, Mohammad M. Sultan, Theofanis Karaletsos
DNA-Encoded Library (DEL) has proven to be a powerful tool that utilizes combinatorially constructed small molecules to facilitate highly-efficient screening assays. These selectio…
Channel Vision Transformers: An Image Is Worth 1 x 16 x 16 Words
Yujia Bao, Srinivasan Sivanandan, Theofanis Karaletsos
Vision Transformer (ViT) has emerged as a powerful architecture in the realm of modern computer vision. However, its application in certain imaging fields, such as microscopy and s…
Contextual Vision Transformers for Robust Representation Learning
Yujia Bao, Theofanis Karaletsos
We introduce Contextual Vision Transformers (ContextViT), a method designed to generate robust image representations for datasets experiencing shifts in latent factors across vario…
Black-box Coreset Variational Inference
Dionysis Manousakas, Hippolyt Ritter, Theofanis Karaletsos
Recent advances in coreset methods have shown that a selection of representative datapoints can replace massive volumes of data for Bayesian inference, preserving the relevant stat…
TyXe: Pyro-based Bayesian neural nets for Pytorch
Hippolyt Ritter, Theofanis Karaletsos
We introduce TyXe, a Bayesian neural network library built on top of Pytorch and Pyro. Our leading design principle is to cleanly separate architecture, prior, inference and likeli…
Localized Uncertainty Attacks
Ousmane Amadou Dia, Theofanis Karaletsos, Caner Hazirbas +3
The susceptibility of deep learning models to adversarial perturbations has stirred renewed attention in adversarial examples resulting in a number of attacks. However, most of the…
Stochastic Aggregation in Graph Neural Networks
Yuanqing Wang, Theofanis Karaletsos
Graph neural networks (GNNs) manifest pathologies including over-smoothing and limited discriminating power as a result of suboptimally expressive aggregating mechanisms. We herein…
Variational Auto-Regressive Gaussian Processes for Continual Learning
Sanyam Kapoor, Theofanis Karaletsos, Thang D. Bui
Through sequential construction of posteriors on observing data online, Bayes' theorem provides a natural framework for continual learning. We develop Variational Auto-Regressive G…
Hierarchical Gaussian Process Priors for Bayesian Neural Network Weights
Theofanis Karaletsos, Thang D. Bui
Probabilistic neural networks are typically modeled with independent weight priors, which do not capture weight correlations in the prior and do not provide a parsimonious interfac…
Generalized Hidden Parameter MDPs Transferable Model-based RL in a Handful of Trials
Christian F. Perez, Felipe Petroski Such, Theofanis Karaletsos
There is broad interest in creating RL agents that can solve many (related) tasks and adapt to new tasks and environments after initial training. Model-based RL leverages learned s…
Applying SVGD to Bayesian Neural Networks for Cyclical Time-Series Prediction and Inference
Xinyu Hu, Paul Szerlip, Theofanis Karaletsos +1
A regression-based BNN model is proposed to predict spatiotemporal quantities like hourly rider demand with calibrated uncertainties. The main contributions of this paper are (i) A…
Efficient transfer learning and online adaptation with latent variable models for continuous control
Christian F. Perez, Felipe Petroski Such, Theofanis Karaletsos
Traditional model-based RL relies on hand-specified or learned models of transition dynamics of the environment. These methods are sample efficient and facilitate learning in the r…