activity
20202026
most citedGaussian Processes on Distributions based on Regularized Optimal Transport

2 citations · 7 across the 13 of their papers we have counts for

collaborators
Showing cs.LGShow all

14 papers · 1 filter

cs.LG2026

Mix, Don't Tune: Bilingual Pre-Training Outperforms Hyperparameter Search in Data-Constrained Settings

Paul Jeha, Anastasiia Sedova, Louis Béthune +4

For most languages of the world, language model pre-training operates in a data-constrained regime where models must repeat their training data many times, degrading generalization…

cs.LG2026

DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures

Eleonora Gualdoni, Sonia Laguna, Louis Bethune +3

Multi-domain fine-tuning of large language models requires improving performance on target domains while preserving performance on constrained domains, such as general knowledge, i…

cs.LG2026

Scaling Categorical Flow Maps

Oscar Davis, Anastasiia Filippova, Pierre Ablin +4

Continuous diffusion and flow matching models could represent a powerful alternative to autoregressive approaches for language modelling (LM), as they unlock a host of advantages c…

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.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 e…

cs.LG2025

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…