papers

Publications (28)

cs.LG2023

REALM: Robust Entropy Adaptive Loss Minimization for Improved Single-Sample Test-Time Adaptation

Skyler Seto, Barry-John Theobald, Federico Danieli +2

Fully-test-time adaptation (F-TTA) can mitigate performance loss due to distribution shifts between train and test data (1) without access to the training data, and (2) without kno…

cs.AI2020

Learning medical triage from clinicians using Deep Q-Learning

Albert Buchard, Baptiste Bouvier, Giulia Prando +10

Medical Triage is of paramount importance to healthcare systems, allowing for the correct orientation of patients and allocation of the necessary resources to treat them adequately…

cs.LG2025

Completed Hyperparameter Transfer across Modules, Width, Depth, Batch and Duration

Bruno Mlodozeniec, Pierre Ablin, Louis Béthune +4

Hyperparameter tuning can dramatically impact training stability and final performance of large-scale models. Recent works on neural network parameterisations, such as P, have…

cs.HC2022

The Impact of Explanations on Layperson Trust in Artificial Intelligence-Driven Symptom Checker Apps: Experimental Study

Claire Woodcock, Brent Mittelstadt, Dan Busbridge +1

To achieve the promoted benefits of an AI symptom checker, laypeople must trust and subsequently follow its instructions. In AI, explanations are seen as a tool to communicate the…

cs.LG2023

Stabilizing Transformer Training by Preventing Attention Entropy Collapse

Shuangfei Zhai, Tatiana Likhomanenko, Etai Littwin +5

Training stability is of great importance to Transformers. In this work, we investigate the training dynamics of Transformers by examining the evolution of the attention layers. In…

cs.LG2025

Parameters vs FLOPs: Scaling Laws for Optimal Sparsity for Mixture-of-Experts Language Models

Samira Abnar, Harshay Shah, Dan Busbridge +3

Scaling the capacity of language models has consistently proven to be a reliable approach for improving performance and unlocking new capabilities. Capacity can be primarily define…

cs.LG2023

The Role of Entropy and Reconstruction in Multi-View Self-Supervised Learning

Borja Rodríguez-Gálvez, Arno Blaas, Pau Rodríguez +5

The mechanisms behind the success of multi-view self-supervised learning (MVSSL) are not yet fully understood. Contrastive MVSSL methods have been studied through the lens of InfoN…

cs.LG2024

Poly-View Contrastive Learning

Amitis Shidani, Devon Hjelm, Jason Ramapuram +3

Contrastive learning typically matches pairs of related views among a number of unrelated negative views. Views can be generated (e.g. by augmentations) or be observed. We investig…

cs.LG2022

Position Prediction as an Effective Pretraining Strategy

Shuangfei Zhai, Navdeep Jaitly, Jason Ramapuram +7

Transformers have gained increasing popularity in a wide range of applications, including Natural Language Processing (NLP), Computer Vision and Speech Recognition, because of thei…

cs.LG2021

Stochastic Contrastive Learning

Jason Ramapuram, Dan Busbridge, Xavier Suau +1

While state-of-the-art contrastive Self-Supervised Learning (SSL) models produce results competitive with their supervised counterparts, they lack the ability to infer latent varia…

cs.LG2021

Evaluating the fairness of fine-tuning strategies in self-supervised learning

Jason Ramapuram, Dan Busbridge, Russ Webb

In this work we examine how fine-tuning impacts the fairness of contrastive Self-Supervised Learning (SSL) models. Our findings indicate that Batch Normalization (BN) statistics pl…

cs.LG2026

The Design Space of Tri-Modal Masked Diffusion Models

Louis Bethune, Victor Turrisi, Bruno Kacper Mlodozeniec +21

Discrete diffusion models have emerged as strong alternatives to autoregressive language models, with recent work initializing and fine-tuning a base unimodal model for bimodal gen…

cs.CV2025

How PARTs assemble into wholes: Learning the relative composition of images

Melika Ayoughi, Samira Abnar, Chen Huang +10

The composition of objects and their parts, along with object-object positional relationships, provides a rich source of information for representation learning. Hence, spatial-awa…

cs.LG2020

Neural Temporal Point Processes For Modelling Electronic Health Records

Joseph Enguehard, Dan Busbridge, Adam Bozson +2

The modelling of Electronic Health Records (EHRs) has the potential to drive more efficient allocation of healthcare resources, enabling early intervention strategies and advancing…

cs.LG2025

Distillation Scaling Laws

Dan Busbridge, Amitis Shidani, Floris Weers +3

We propose a distillation scaling law that estimates distilled model performance based on a compute budget and its allocation between the student and teacher. Our findings mitigate…

cs.LG2022

Elastic Weight Consolidation Improves the Robustness of Self-Supervised Learning Methods under Transfer

Andrius Ovsianas, Jason Ramapuram, Dan Busbridge +2

Self-supervised representation learning (SSL) methods provide an effective label-free initial condition for fine-tuning downstream tasks. However, in numerous realistic scenarios,…

cs.LG2025

Scaling Laws for Forgetting during Finetuning with Pretraining Data Injection

Louis Bethune, David Grangier, Dan Busbridge +3

A widespread strategy to obtain a language model that performs well on a target domain is to finetune a pretrained model to perform unsupervised next-token prediction on data from…

cs.CL2019

Neural Language Priors

Joseph Enguehard, Dan Busbridge, Vitalii Zhelezniak +1

The choice of sentence encoder architecture reflects assumptions about how a sentence's meaning is composed from its constituent words. We examine the contribution of these archite…

cs.LG2023

DUET: 2D Structured and Approximately Equivariant Representations

Xavier Suau, Federico Danieli, T. Anderson Keller +5

Multiview Self-Supervised Learning (MSSL) is based on learning invariances with respect to a set of input transformations. However, invariance partially or totally removes transfor…

cs.AI2018

Decoding Decoders: Finding Optimal Representation Spaces for Unsupervised Similarity Tasks

Vitalii Zhelezniak, Dan Busbridge, April Shen +2

Experimental evidence indicates that simple models outperform complex deep networks on many unsupervised similarity tasks. We provide a simple yet rigorous explanation for this beh…

cs.CL2026

Scaling Properties of Continuous Diffusion Spoken Language Models

Jason Ramapuram, Eeshan Gunesh Dhekane, Amitis Shidani +6

Speech-only spoken language models (SLMs) lag behind text and text-speech models in performance, with recent discrete autoregressive (AR) SLMs indicating significant computational…

cs.LG2019

Relational Graph Attention Networks

Dan Busbridge, Dane Sherburn, Pietro Cavallo +1

We investigate Relational Graph Attention Networks, a class of models that extends non-relational graph attention mechanisms to incorporate relational information, opening up these…

cs.LG2023

Bootstrap Your Own Variance

Polina Turishcheva, Jason Ramapuram, Sinead Williamson +3

Understanding model uncertainty is important for many applications. We propose Bootstrap Your Own Variance (BYOV), combining Bootstrap Your Own Latent (BYOL), a negative-free Self-…

cs.CV2021

Do Self-Supervised and Supervised Methods Learn Similar Visual Representations?

Tom George Grigg, Dan Busbridge, Jason Ramapuram +1

Despite the success of a number of recent techniques for visual self-supervised deep learning, there has been limited investigation into the representations that are ultimately lea…

cs.LG2025

Theory, Analysis, and Best Practices for Sigmoid Self-Attention

Jason Ramapuram, Federico Danieli, Eeshan Dhekane +8

Attention is a key part of the transformer architecture. It is a sequence-to-sequence mapping that transforms each sequence element into a weighted sum of values. The weights are t…

cs.LG2025

Revisiting the Scaling Properties of Downstream Metrics in Large Language Model Training

Jakub Krajewski, Amitis Shidani, Dan Busbridge +2

While scaling laws for Large Language Models (LLMs) traditionally focus on proxy metrics like pretraining loss, predicting downstream task performance has been considered unreliabl…

cs.LG2025

Scaling Laws for Optimal Data Mixtures

Mustafa Shukor, Louis Bethune, Dan Busbridge +4

Large foundation models are typically trained on data from multiple domains, with the data mixture--the proportion of each domain used--playing a critical role in model performance…

stat.ML2023

How to Scale Your EMA

Dan Busbridge, Jason Ramapuram, Pierre Ablin +4

Preserving training dynamics across batch sizes is an important tool for practical machine learning as it enables the trade-off between batch size and wall-clock time. This trade-o…