Pascal Jr. Tikeng Notsawo

I learn stuff.

About me Explore my research Blog

Research Interests

Optimization Generalization Deep Learning Theory Grokking AI Alignment LLM Unlearning

News

Jul 2026 Model Merging via Data-Free Covariance Estimation accepted at the Conference on Language Modeling (COLM 2026).
May 2026 New paper: Model Merging via Data-Free Covariance Estimation accepted as Oral at the CATS (Continual Adaptation at Scale) Workshop, ICML 2026.
May 2026 Recognized as an ICML 2026 Gold Reviewer (top 25%) and awarded complimentary registration.
Apr 2026 New paper: Grokking Finite-Dimensional Algebra accepted at ICML 2026.
Jul 2025 Grokking Beyond the Euclidean Norm of Model Parameters accepted at ICML 2025.

Selected Publications

Model Merging via Data-Free Covariance Estimation

Marawan Gamal Abdel Hameed, Derek Tam, Pascal Jr Tikeng Notsawo, Colin Raffel, Guillaume Rabusseau

CATS (Continual Adaptation at Scale) Workshop, ICML, 2026 (Oral)

Conference on Language Modeling (COLM), 2026

Model MergingCovariance EstimationTransfer Learning

Grokking Finite-Dimensional Algebra

Pascal Jr. Tikeng Notsawo, Guillaume Dumas, Guillaume Rabusseau

Forty-Third International Conference on Machine Learning (ICML), 2026

GrokkingAlgebraRepresentation LearningGeneralization

Grokking Beyond the Euclidean Norm of Model Parameters

Pascal Jr. Tikeng Notsawo, Guillaume Dumas, Guillaume Rabusseau

Forty-Second International Conference on Machine Learning (ICML), 2025

GrokkingGeneralizationRegularizationDeep Learning

View all publications →