50 citations · 167 across the 15 of their papers we have counts for
15 papers
PaliGemma: A versatile 3B VLM for transfer
Lucas Beyer, Andreas Steiner, André Susano Pinto +32
PaliGemma is an open Vision-Language Model (VLM) that is based on the SigLIP-So400m vision encoder and the Gemma-2B language model. It is trained to be a versatile and broadly know…
Improving fine-grained understanding in image-text pre-training
Ioana Bica, Anastasija Ilić, Matthias Bauer +8
We introduce SPARse Fine-grained Contrastive Alignment (SPARC), a simple method for pretraining more fine-grained multimodal representations from image-text pairs. Given that multi…
Invariant Causal Imitation Learning for Generalizable Policies
Ioana Bica, Daniel Jarrett, Mihaela van der Schaar
Consider learning an imitation policy on the basis of demonstrated behavior from multiple environments, with an eye towards deployment in an unseen environment. Since the observabl…
Time-series Generation by Contrastive Imitation
Daniel Jarrett, Ioana Bica, Mihaela van der Schaar
Consider learning a generative model for time-series data. The sequential setting poses a unique challenge: Not only should the generator capture the conditional dynamics of (stepw…
Neural Algorithmic Reasoning with Causal Regularisation
Beatrice Bevilacqua, Kyriacos Nikiforou, Borja Ibarz +5
Recent work on neural algorithmic reasoning has investigated the reasoning capabilities of neural networks, effectively demonstrating they can learn to execute classical algorithms…
Data-IQ: Characterizing subgroups with heterogeneous outcomes in tabular data
Nabeel Seedat, Jonathan Crabbé, Ioana Bica +1
High model performance, on average, can hide that models may systematically underperform on subgroups of the data. We consider the tabular setting, which surfaces the unique issue…
Transfer Learning on Heterogeneous Feature Spaces for Treatment Effects Estimation
Ioana Bica, Mihaela van der Schaar
Consider the problem of improving the estimation of conditional average treatment effects (CATE) for a target domain of interest by leveraging related information from a source dom…
DAPDAG: Domain Adaptation via Perturbed DAG Reconstruction
Yanke Li, Hatt Tobias, Ioana Bica +1
Leveraging labelled data from multiple domains to enable prediction in another domain without labels is a significant, yet challenging problem. To address this problem, we introduc…
Benchmarking Heterogeneous Treatment Effect Models through the Lens of Interpretability
Jonathan Crabbé, Alicia Curth, Ioana Bica +1
Estimating personalized effects of treatments is a complex, yet pervasive problem. To tackle it, recent developments in the machine learning (ML) literature on heterogeneous treatm…
Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?
Nenad Tomasev, Ioana Bica, Brian McWilliams +4
Despite recent progress made by self-supervised methods in representation learning with residual networks, they still underperform supervised learning on the ImageNet classificatio…
Disentangled Counterfactual Recurrent Networks for Treatment Effect Inference over Time
Jeroen Berrevoets, Alicia Curth, Ioana Bica +2
Choosing the best treatment-plan for each individual patient requires accurate forecasts of their outcome trajectories as a function of the treatment, over time. While large observ…
The Medkit-Learn(ing) Environment: Medical Decision Modelling through Simulation
Alex J. Chan, Ioana Bica, Alihan Huyuk +2
Understanding decision-making in clinical environments is of paramount importance if we are to bring the strengths of machine learning to ultimately improve patient outcomes. Sever…
Estimating Counterfactual Treatment Outcomes over Time Through Adversarially Balanced Representations
Ioana Bica, Ahmed M. Alaa, James Jordon +1
Identifying when to give treatments to patients and how to select among multiple treatments over time are important medical problems with a few existing solutions. In this paper, w…
Estimating the Effects of Continuous-valued Interventions using Generative Adversarial Networks
Ioana Bica, James Jordon, Mihaela van der Schaar
While much attention has been given to the problem of estimating the effect of discrete interventions from observational data, relatively little work has been done in the setting o…
Time Series Deconfounder: Estimating Treatment Effects over Time in the Presence of Hidden Confounders
Ioana Bica, Ahmed M. Alaa, Mihaela van der Schaar
The estimation of treatment effects is a pervasive problem in medicine. Existing methods for estimating treatment effects from longitudinal observational data assume that there are…