Scholar
Pierre Ablin
Google Scholar ID: 1ZsunaYAAAAJ
Apple Machine Learning Research
Optimization
Machine Learning
Statistics
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
1,594
H-index
21
i10-index
28
Publications
20
Co-authors
67
list available
Contact
GitHub
Open ↗
LinkedIn
Open ↗
Publications
24 items
Mix, Don't Tune: Bilingual Pre-Training Outperforms Hyperparameter Search in Data-Constrained Settings
2026
Cited
0
Scaling Laws for Mixture Pretraining Under Data Constraints
2026
Cited
0
Locking Pretrained Weights via Deep Low-Rank Residual Distillation
2026
Cited
0
DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures
2026
Cited
0
Nectar: Neural Estimation of Cached-Token Attention via Regression
2026
Cited
0
Scaling Categorical Flow Maps
2026
Cited
0
Optimal Splitting of Language Models from Mixtures to Specialized Domains
2026
Cited
0
The Design Space of Tri-Modal Masked Diffusion Models
2026
Cited
0
Load more
Resume (English only)
Co-authors
67 total
Alexandre Gramfort
Meta
Gabriel Peyré
CNRS, DMA, Ecole Normale Supérieure
Thomas Moreau
Inria, CEA, Université Paris-Saclay
Co-author 4
Samuel Vaiter
CNRS Researcher
Mathieu Dagréou
Inria
David Grangier
Apple Machine Learning Research
Michael E. Sander
Google DeepMind
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up