pith. sign in

Pierre Ablin

Identifiers

  • name variant Pierre Ablin 0.60 · backfill

Papers (13)

  1. Balanced LoRA: Removing Parameter Invariance to Accelerate Convergence cs.LG · 2026 · author #3
  2. Mix, Don't Tune: Bilingual Pre-Training Outperforms Hyperparameter Search in Data-Constrained Settings cs.LG · 2026 · author #6
  3. Scaling Laws for Mixture Pretraining Under Data Constraints cs.LG · 2026 · author #4
  4. Locking Pretrained Weights via Deep Low-Rank Residual Distillation cs.LG · 2026 · author #2
  5. DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures cs.LG · 2026 · author #5
  6. Nectar: Neural Estimation of Cached-Token Attention via Regression cs.LG · 2026 · author #3
  7. Scaling Categorical Flow Maps cs.LG · 2026 · author #3
  8. LaCy: What Small Language Models Can and Should Learn is Not Just a Question of Loss cs.CL · 2026 · author #3
  9. Learning Unmasking Policies for Diffusion Language Models cs.LG · 2025 · author #4
  10. Learning step sizes for unfolded sparse coding stat.ML · 2019 · author #1
  11. Stochastic algorithms with descent guarantees for ICA stat.ML · 2018 · author #1
  12. Faster ICA under orthogonal constraint stat.ML · 2017 · author #1
  13. Faster independent component analysis by preconditioning with Hessian approximations stat.ML · 2017 · author #1

Mentions

  • 2512.09106 #4 · arxiv_oai · confidence 0.70 Pierre Ablin
  • 2605.31484 #3 · arxiv_oai · confidence 0.70 Pierre Ablin
  • 2605.12715 #4 · arxiv_oai · confidence 0.70 Pierre Ablin
  • 2602.12005 #3 · arxiv_oai · confidence 0.70 Pierre Ablin

Frequent Coauthors