63 citations · 143 across the 20 of their papers we have counts for
20 papers
OneFlow: Concurrent Mixed-Modal and Interleaved Generation with Edit Flows
John Nguyen, Marton Havasi, Tariq Berrada +2
We present OneFlow, the first non-autoregressive multimodal model that enables variable-length and concurrent mixed-modal generation. Unlike autoregressive models that enforce rigi…
Set Block Decoding is a Language Model Inference Accelerator
Itai Gat, Heli Ben-Hamu, Marton Havasi +6
Autoregressive next token prediction language models offer powerful capabilities but face significant challenges in practical deployment due to the high computational and memory co…
Edit Flows: Flow Matching with Edit Operations
Marton Havasi, Brian Karrer, Itai Gat +1
Autoregressive generative models naturally generate variable-length sequences, while non-autoregressive models struggle, often imposing rigid, token-wise structures. We propose Edi…
Diverse Concept Proposals for Concept Bottleneck Models
Katrina Brown, Marton Havasi, Finale Doshi-Velez
Concept bottleneck models are interpretable predictive models that are often used in domains where model trust is a key priority, such as healthcare. They identify a small number o…
EvalGIM: A Library for Evaluating Generative Image Models
Melissa Hall, Oscar Mañas, Reyhane Askari-Hemmat +14
As the use of text-to-image generative models increases, so does the adoption of automatic benchmarking methods used in their evaluation. However, while metrics and datasets abound…
Flow Matching Guide and Code
Yaron Lipman, Marton Havasi, Peter Holderrieth +7
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 b…
Flow Matching with General Discrete Paths: A Kinetic-Optimal Perspective
Neta Shaul, Itai Gat, Marton Havasi +6
The design space of discrete-space diffusion or flow generative models are significantly less well-understood than their continuous-space counterparts, with many works focusing onl…
Boosting Latent Diffusion with Perceptual Objectives
Tariq Berrada, Pietro Astolfi, Melissa Hall +6
Latent diffusion models (LDMs) power state-of-the-art high-resolution generative image models. LDMs learn the data distribution in the latent space of an autoencoder (AE) and produ…
On Improved Conditioning Mechanisms and Pre-training Strategies for Diffusion Models
Tariq Berrada Ifriqi, Pietro Astolfi, Melissa Hall +8
Large-scale training of latent diffusion models (LDMs) has enabled unprecedented quality in image generation. However, the key components of the best performing LDM training recipe…
Generator Matching: Generative modeling with arbitrary Markov processes
Peter Holderrieth, Marton Havasi, Jason Yim +6
We introduce Generator Matching, a modality-agnostic framework for generative modeling using arbitrary Markov processes. Generators characterize the infinitesimal evolution of a Ma…
Exact Byte-Level Probabilities from Tokenized Language Models for FIM-Tasks and Model Ensembles
Buu Phan, Brandon Amos, Itai Gat +3
Tokenization is associated with many poorly understood shortcomings in language models (LMs), yet remains an important component for long sequence scaling purposes. This work studi…
Understanding and Mitigating Tokenization Bias in Language Models
Buu Phan, Marton Havasi, Matthew Muckley +1
State-of-the-art language models are autoregressive and operate on subword units known as tokens. Specifically, one must encode the conditioning string into a list of tokens before…
Guarantee Regions for Local Explanations
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…
What Makes a Good Explanation?: A Harmonized View of Properties of Explanations
Zixi Chen, Varshini Subhash, Marton Havasi +2
Interpretability provides a means for humans to verify aspects of machine learning (ML) models and empower human+ML teaming in situations where the task cannot be fully automated.…
Uncertainty Baselines: Benchmarks for Uncertainty & Robustness in Deep Learning
Zachary Nado, Neil Band, Mark Collier +23
High-quality estimates of uncertainty and robustness are crucial for numerous real-world applications, especially for deep learning which underlies many deployed ML systems. The ab…
Training independent subnetworks for robust prediction
Marton Havasi, Rodolphe Jenatton, Stanislav Fort +5
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 th…
Compressing Images by Encoding Their Latent Representations with Relative Entropy Coding
Gergely Flamich, Marton Havasi, José Miguel Hernández-Lobato
Variational Autoencoders (VAEs) have seen widespread use in learned image compression. They are used to learn expressive latent representations on which downstream compression meth…
Minimal Random Code Learning: Getting Bits Back from Compressed Model Parameters
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 re…
Inference in Deep Gaussian Processes using Stochastic Gradient Hamiltonian Monte Carlo
Marton Havasi, José Miguel Hernández-Lobato, Juan José Murillo-Fuentes
Deep Gaussian Processes (DGPs) are hierarchical generalizations of Gaussian Processes that combine well calibrated uncertainty estimates with the high flexibility of multilayer mod…
Deep Gaussian Processes with Decoupled Inducing Inputs
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. They combi…