193 citations · 348 across the 28 of their papers we have counts for
30 papers
Learning -Powered Conditional Distributions with Importance-Weighted Flow Matching
Maciej Falkiewicz, Frantzeska Lavda, Jason Ramapuram +1
Classifier-Free Guidance (CFG) with guidance scale is commonly motivated by the -powered conditional distribution obtained by setting , but CFG does not, in general, sa…
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…
Path-Constrained Mixture-of-Experts
Zijin Gu, Tatiana Likhomanenko, Vimal Thilak +2
Sparse Mixture-of-Experts (MoE) architectures route each token through a subset of experts at each layer independently. We propose viewing MoE computation through the lens of \emph…
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…
A Small-Scale System for Autoregressive Program Synthesis Enabling Controlled Experimentation
Russ Webb, Jason Ramapuram
What research can be pursued with small models trained to complete true programs? Typically, researchers study program synthesis via large language models (LLMs) which introduce is…
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 e…
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…
Learning Unmasking Policies for Diffusion Language Models
Metod Jazbec, Theo X. Olausson, Louis Béthune +6
Diffusion (Large) Language Models (dLLMs) now match the downstream performance of their autoregressive counterparts on many tasks, while holding the promise of being more efficient…
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…
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…
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…
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-…
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…
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…
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…
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…
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,…
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…
Challenges of Adversarial Image Augmentations
Arno Blaas, Xavier Suau, Jason Ramapuram +2
Image augmentations applied during training are crucial for the generalization performance of image classifiers. Therefore, a large body of research has focused on finding the opti…
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…
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…
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…
Kanerva++: extending The Kanerva Machine with differentiable, locally block allocated latent memory
Jason Ramapuram, Yan Wu, Alexandros Kalousis
Episodic and semantic memory are critical components of the human memory model. The theory of complementary learning systems (McClelland et al., 1995) suggests that the compressed…
Self-Supervised MultiModal Versatile Networks
Jean-Baptiste Alayrac, Adrià Recasens, Rosalia Schneider +6
Videos are a rich source of multi-modal supervision. In this work, we learn representations using self-supervision by leveraging three modalities naturally present in videos: visua…