Publications

Model Merging via Data-Free Covariance Estimation

Grokking Finite-Dimensional Algebra

Grokking Beyond the Euclidean Norm of Model Parameters

Lost in Translation: The Algorithmic Gap Between LMs and the Brain

Predicting Grokking Long Before it Happens: A look into the loss landscape of models which grok

Adaptive Discrete Communication Bottlenecks with Dynamic Vector Quantization for Heterogeneous Representational Coarseness

Stochastic Average Gradient : A Simple Empirical Investigation

On the use of linguistic similarities to improve Neural Machine Translation for African Languages