papers

Publications (22)

cs.LG2022

Plex: Towards Reliability using Pretrained Large Model Extensions

Dustin Tran, Jeremiah Liu, Michael W. Dusenberry +23

A recent trend in artificial intelligence is the use of pretrained models for language and vision tasks, which have achieved extraordinary performance but also puzzling failures. P…

cs.LG2018

Deep Contextual Multi-armed Bandits

Mark Collier, Hector Urdiales Llorens

Contextual multi-armed bandit problems arise frequently in important industrial applications. Existing solutions model the context either linearly, which enables uncertainty driven…

cs.CL2025

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Gheorghe Comanici, Eric Bieber, Mike Schaekermann +3431

In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our…

cs.LG2020

Routing Networks with Co-training for Continual Learning

Mark Collier, Efi Kokiopoulou, Andrea Gesmundo +1

The core challenge with continual learning is catastrophic forgetting, the phenomenon that when neural networks are trained on a sequence of tasks they rapidly forget previously le…

cs.CV2024

Representing Online Handwriting for Recognition in Large Vision-Language Models

Anastasiia Fadeeva, Philippe Schlattner, Andrii Maksai +4

The adoption of tablets with touchscreens and styluses is increasing, and a key feature is converting handwriting to text, enabling search, indexing, and AI assistance. Meanwhile,…

cs.LG2021

VAEs in the Presence of Missing Data

Mark Collier, Alfredo Nazabal, Christopher K. I. Williams

Real world datasets often contain entries with missing elements e.g. in a medical dataset, a patient is unlikely to have taken all possible diagnostic tests. Variational Autoencode…

cs.LG2018

An Empirical Comparison of Syllabuses for Curriculum Learning

Mark Collier, Joeran Beel

Syllabuses for curriculum learning have been developed on an ad-hoc, per task basis and little is known about the relative performance of different syllabuses. We identify a number…

cs.CV2024

Pretrained Visual Uncertainties

Michael Kirchhof, Mark Collier, Seong Joon Oh +1

Accurate uncertainty estimation is vital to trustworthy machine learning, yet uncertainties typically have to be learned for each task anew. This work introduces the first pretrain…

cs.LG2024

Pi-DUAL: Using Privileged Information to Distinguish Clean from Noisy Labels

Ke Wang, Guillermo Ortiz-Jimenez, Rodolphe Jenatton +3

Label noise is a pervasive problem in deep learning that often compromises the generalization performance of trained models. Recently, leveraging privileged information (PI) -- inf…

stat.ML2022

Deep Classifiers with Label Noise Modeling and Distance Awareness

Vincent Fortuin, Mark Collier, Florian Wenzel +7

Uncertainty estimation in deep learning has recently emerged as a crucial area of interest to advance reliability and robustness in safety-critical applications. While there have b…

cs.LG2022

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…

cs.CV2023

Three Towers: Flexible Contrastive Learning with Pretrained Image Models

Jannik Kossen, Mark Collier, Basil Mustafa +7

We introduce Three Towers (3T), a flexible method to improve the contrastive learning of vision-language models by incorporating pretrained image classifiers. While contrastive mod…

cs.LG2019

Memory-Augmented Neural Networks for Machine Translation

Mark Collier, Joeran Beel

Memory-augmented neural networks (MANNs) have been shown to outperform other recurrent neural network architectures on a series of artificial sequence learning tasks, yet they have…

cs.LG2021

Correlated Input-Dependent Label Noise in Large-Scale Image Classification

Mark Collier, Basil Mustafa, Efi Kokiopoulou +2

Large scale image classification datasets often contain noisy labels. We take a principled probabilistic approach to modelling input-dependent, also known as heteroscedastic, label…

cs.LG2018

Implementing Neural Turing Machines

Mark Collier, Joeran Beel

Neural Turing Machines (NTMs) are an instance of Memory Augmented Neural Networks, a new class of recurrent neural networks which decouple computation from memory by introducing an…

cs.LG2023

When does Privileged Information Explain Away Label Noise?

Guillermo Ortiz-Jimenez, Mark Collier, Anant Nawalgaria +4

Leveraging privileged information (PI), or features available during training but not at test time, has recently been shown to be an effective method for addressing label noise. Ho…

cs.LG2022

Transfer and Marginalize: Explaining Away Label Noise with Privileged Information

Mark Collier, Rodolphe Jenatton, Efi Kokiopoulou +1

Supervised learning datasets often have privileged information, in the form of features which are available at training time but are not available at test time e.g. the ID of the a…

cs.CV2025

Semantic Document Derendering: SVG Reconstruction via Vision-Language Modeling

Adam Hazimeh, Ke Wang, Mark Collier +3

Multimedia documents such as slide presentations and posters are designed to be interactive and easy to modify. Yet, they are often distributed in a static raster format, which lim…

cs.LG2019

Scalable Deep Unsupervised Clustering with Concrete GMVAEs

Mark Collier, Hector Urdiales

Discrete random variables are natural components of probabilistic clustering models. A number of VAE variants with discrete latent variables have been developed. Training such meth…

cs.LG2023

Massively Scaling Heteroscedastic Classifiers

Mark Collier, Rodolphe Jenatton, Basil Mustafa +3

Heteroscedastic classifiers, which learn a multivariate Gaussian distribution over prediction logits, have been shown to perform well on image classification problems with hundreds…

cs.LG2020

A Simple Probabilistic Method for Deep Classification under Input-Dependent Label Noise

Mark Collier, Basil Mustafa, Efi Kokiopoulou +2

Datasets with noisy labels are a common occurrence in practical applications of classification methods. We propose a simple probabilistic method for training deep classifiers under…

cs.CV2025

Sketch-to-Layout: Sketch-Guided Multimodal Layout Generation

Riccardo Brioschi, Aleksandr Alekseev, Emanuele Nevali +9

Graphic layout generation is a growing research area focusing on generating aesthetically pleasing layouts ranging from poster designs to documents. While recent research has explo…