no code implementations • 24 Dec 2024 • Katrina Brown, Marton Havasi, Finale Doshi-Velez
On EHR data, our model was able to identify 4 out of the 5 pre-defined concepts without supervision.
1 code implementation • 13 Dec 2024 • Melissa Hall, Oscar Mañas, Reyhane Askari-Hemmat, Mark Ibrahim, Candace Ross, Pietro Astolfi, Tariq Berrada Ifriqi, Marton Havasi, Yohann Benchetrit, Karen Ullrich, Carolina Braga, Abhishek Charnalia, Maeve Ryan, Mike Rabbat, Michal Drozdzal, Jakob Verbeek, Adriana Romero-Soriano
To enable actionable evaluation insights, we introduce ''Evaluation Exercises'' that highlight takeaways for specific evaluation questions.
1 code implementation • 9 Dec 2024 • Yaron Lipman, Marton Havasi, Peter Holderrieth, Neta Shaul, Matt Le, Brian Karrer, Ricky T. Q. Chen, David Lopez-Paz, Heli Ben-Hamu, Itai Gat
Flow Matching (FM) is a recent framework for generative modeling that has achieved state-of-the-art performance across various domains, including image, video, audio, speech, and biological structures.
no code implementations • 4 Dec 2024 • Neta Shaul, Itai Gat, Marton Havasi, Daniel Severo, Anuroop Sriram, Peter Holderrieth, Brian Karrer, Yaron Lipman, Ricky T. Q. Chen
Through the lens of optimizing the symmetric kinetic energy, we propose velocity formulas that can be applied to any given probability path, completely decoupling the probability and velocity, and giving the user the freedom to specify any desirable probability path based on expert knowledge specific to the data domain.
no code implementations • 6 Nov 2024 • Tariq Berrada, Pietro Astolfi, Melissa Hall, Marton Havasi, Yohann Benchetrit, Adriana Romero-Soriano, Karteek Alahari, Michal Drozdzal, Jakob Verbeek
LDMs learn the data distribution in the latent space of an autoencoder (AE) and produce images by mapping the generated latents into RGB image space using the AE decoder.
no code implementations • 5 Nov 2024 • Tariq Berrada Ifriqi, Pietro Astolfi, Melissa Hall, Reyhane Askari-Hemmat, Yohann Benchetrit, Marton Havasi, Matthew Muckley, Karteek Alahari, Adriana Romero-Soriano, Jakob Verbeek, Michal Drozdzal
In this work, we perform an in-depth study of LDM training recipes focusing on the performance of models and their training efficiency.
no code implementations • 27 Oct 2024 • Peter Holderrieth, Marton Havasi, Jason Yim, Neta Shaul, Itai Gat, Tommi Jaakkola, Brian Karrer, Ricky T. Q. Chen, Yaron Lipman
We introduce generator matching, a modality-agnostic framework for generative modeling using arbitrary Markov processes.
no code implementations • 11 Oct 2024 • Buu Phan, Brandon Amos, Itai Gat, Marton Havasi, Matthew Muckley, Karen Ullrich
In FIM tasks where input prompts may terminate mid-token, leading to out-of-distribution tokenization, our method mitigates performance degradation and achieves an approximately 18% improvement in FIM coding benchmarks, consistently outperforming the standard token healing fix.
no code implementations • 24 Jun 2024 • Buu Phan, Marton Havasi, Matthew Muckley, Karen Ullrich
As a result, we show that one can simulate token-free behavior from a tokenized language model.
1 code implementation • 20 Feb 2024 • Marton Havasi, Sonali Parbhoo, Finale Doshi-Velez
Interpretability methods that utilise local surrogate models (e. g. LIME) are very good at describing the behaviour of the predictive model at a point of interest, but they are not guaranteed to extrapolate to the local region surrounding the point.
no code implementations • 10 Nov 2022 • Zixi Chen, Varshini Subhash, Marton Havasi, Weiwei Pan, Finale Doshi-Velez
In this work, we survey properties defined in interpretable machine learning papers, synthesize them based on what they actually measure, and describe the trade-offs between different formulations of these properties.
3 code implementations • 7 Jun 2021 • Zachary Nado, Neil Band, Mark Collier, Josip Djolonga, Michael W. Dusenberry, Sebastian Farquhar, Qixuan Feng, Angelos Filos, Marton Havasi, Rodolphe Jenatton, Ghassen Jerfel, Jeremiah Liu, Zelda Mariet, Jeremy Nixon, Shreyas Padhy, Jie Ren, Tim G. J. Rudner, Faris Sbahi, Yeming Wen, Florian Wenzel, Kevin Murphy, D. Sculley, Balaji Lakshminarayanan, Jasper Snoek, Yarin Gal, Dustin Tran
In this paper we introduce Uncertainty Baselines: high-quality implementations of standard and state-of-the-art deep learning methods on a variety of tasks.
2 code implementations • ICLR 2021 • Marton Havasi, Rodolphe Jenatton, Stanislav Fort, Jeremiah Zhe Liu, Jasper Snoek, Balaji Lakshminarayanan, Andrew M. Dai, Dustin Tran
Recent approaches to efficiently ensemble neural networks have shown that strong robustness and uncertainty performance can be achieved with a negligible gain in parameters over the original network.
1 code implementation • NeurIPS 2020 • Gergely Flamich, Marton Havasi, José Miguel Hernández-Lobato
Variational Autoencoders (VAEs) have seen widespread use in learned image compression.
no code implementations • 25 Sep 2019 • Gergely Flamich, Marton Havasi, José Miguel Hernández-Lobato
Standard compression algorithms work by mapping an image to discrete code using an encoder from which the original image can be reconstructed through a decoder.
no code implementations • 25 Sep 2019 • Marton Havasi, Jasper Snoek, Dustin Tran, Jonathan Gordon, José Miguel Hernández-Lobato
Variational inference (VI) is a popular approach for approximate Bayesian inference that is particularly promising for highly parameterized models such as deep neural networks.
2 code implementations • ICLR 2019 • Marton Havasi, Robert Peharz, José Miguel Hernández-Lobato
While deep neural networks are a highly successful model class, their large memory footprint puts considerable strain on energy consumption, communication bandwidth, and storage requirements.
3 code implementations • NeurIPS 2018 • Marton Havasi, José Miguel Hernández-Lobato, Juan José Murillo-Fuentes
The current state-of-the-art inference method, Variational Inference (VI), employs a Gaussian approximation to the posterior distribution.
no code implementations • 9 Jan 2018 • Marton Havasi, José Miguel Hernández-Lobato, Juan José Murillo-Fuentes
Deep Gaussian Processes (DGP) are hierarchical generalizations of Gaussian Processes (GP) that have proven to work effectively on a multiple supervised regression tasks.