Alert button
Picture for Ioana Bica

Ioana Bica

Alert button

Improving fine-grained understanding in image-text pre-training

Jan 18, 2024
Ioana Bica, Anastasija Ilić, Matthias Bauer, Goker Erdogan, Matko Bošnjak, Christos Kaplanis, Alexey A. Gritsenko, Matthias Minderer, Charles Blundell, Razvan Pascanu, Jovana Mitrović

Viaarxiv icon

Invariant Causal Imitation Learning for Generalizable Policies

Nov 02, 2023
Ioana Bica, Daniel Jarrett, Mihaela van der Schaar

Viaarxiv icon

Time-series Generation by Contrastive Imitation

Nov 02, 2023
Daniel Jarrett, Ioana Bica, Mihaela van der Schaar

Viaarxiv icon

Clairvoyance: A Pipeline Toolkit for Medical Time Series

Oct 28, 2023
Daniel Jarrett, Jinsung Yoon, Ioana Bica, Zhaozhi Qian, Ari Ercole, Mihaela van der Schaar

Viaarxiv icon

Neural Algorithmic Reasoning with Causal Regularisation

Feb 20, 2023
Beatrice Bevilacqua, Kyriacos Nikiforou, Borja Ibarz, Ioana Bica, Michela Paganini, Charles Blundell, Jovana Mitrovic, Petar Veličković

Figure 1 for Neural Algorithmic Reasoning with Causal Regularisation
Figure 2 for Neural Algorithmic Reasoning with Causal Regularisation
Figure 3 for Neural Algorithmic Reasoning with Causal Regularisation
Figure 4 for Neural Algorithmic Reasoning with Causal Regularisation
Viaarxiv icon

Data-IQ: Characterizing subgroups with heterogeneous outcomes in tabular data

Oct 24, 2022
Nabeel Seedat, Jonathan Crabbé, Ioana Bica, Mihaela van der Schaar

Figure 1 for Data-IQ: Characterizing subgroups with heterogeneous outcomes in tabular data
Figure 2 for Data-IQ: Characterizing subgroups with heterogeneous outcomes in tabular data
Figure 3 for Data-IQ: Characterizing subgroups with heterogeneous outcomes in tabular data
Figure 4 for Data-IQ: Characterizing subgroups with heterogeneous outcomes in tabular data
Viaarxiv icon

Transfer Learning on Heterogeneous Feature Spaces for Treatment Effects Estimation

Oct 08, 2022
Ioana Bica, Mihaela van der Schaar

Figure 1 for Transfer Learning on Heterogeneous Feature Spaces for Treatment Effects Estimation
Figure 2 for Transfer Learning on Heterogeneous Feature Spaces for Treatment Effects Estimation
Figure 3 for Transfer Learning on Heterogeneous Feature Spaces for Treatment Effects Estimation
Figure 4 for Transfer Learning on Heterogeneous Feature Spaces for Treatment Effects Estimation
Viaarxiv icon

DAPDAG: Domain Adaptation via Perturbed DAG Reconstruction

Aug 02, 2022
Yanke Li, Hatt Tobias, Ioana Bica, Mihaela van der Schaar

Figure 1 for DAPDAG: Domain Adaptation via Perturbed DAG Reconstruction
Figure 2 for DAPDAG: Domain Adaptation via Perturbed DAG Reconstruction
Figure 3 for DAPDAG: Domain Adaptation via Perturbed DAG Reconstruction
Figure 4 for DAPDAG: Domain Adaptation via Perturbed DAG Reconstruction
Viaarxiv icon

Benchmarking Heterogeneous Treatment Effect Models through the Lens of Interpretability

Jun 16, 2022
Jonathan Crabbé, Alicia Curth, Ioana Bica, Mihaela van der Schaar

Figure 1 for Benchmarking Heterogeneous Treatment Effect Models through the Lens of Interpretability
Figure 2 for Benchmarking Heterogeneous Treatment Effect Models through the Lens of Interpretability
Figure 3 for Benchmarking Heterogeneous Treatment Effect Models through the Lens of Interpretability
Figure 4 for Benchmarking Heterogeneous Treatment Effect Models through the Lens of Interpretability
Viaarxiv icon

Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?

Jan 13, 2022
Nenad Tomasev, Ioana Bica, Brian McWilliams, Lars Buesing, Razvan Pascanu, Charles Blundell, Jovana Mitrovic

Figure 1 for Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?
Figure 2 for Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?
Figure 3 for Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?
Figure 4 for Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?
Viaarxiv icon