activity
20242026
most citedLearning without training: The implicit dynamics of in-context learning

2 citations · 3 across the 5 of their papers we have counts for

collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2026

Equivalence of Context and Parameter Updates in Modern Transformer Blocks

Adrian Goldwaser, Michael Munn, Javier Gonzalvo +1

Recent research has established that the impact of context in a vanilla transformer can be represented implicitly by forming a token-dependent, rank-1 patch to its MLP weights. Thi…

cs.LG2026

Transmuting prompts into weights

Hanna Mazzawi, Benoit Dherin, Michael Munn +3

A growing body of research has demonstrated that the behavior of large language models can be effectively controlled at inference time by directly modifying their internal states,…

cs.LG20261 cited

How iteration order influences convergence and stability in deep learning

Benoit Dherin, Benny Avelin, Anders Karlsson +3

Despite exceptional achievements, training neural networks remains computationally expensive and is often plagued by instabilities that can degrade convergence. While learning rate…

cs.LG2026

Grow, Don't Overwrite: Fine-tuning Without Forgetting

Dyah Adila, Hanna Mazzawi, Benoit Dherin +1

Adapting pre-trained models to specialized tasks often leads to catastrophic forgetting, where new knowledge overwrites foundational capabilities. Existing methods either compromis…

cs.LG2025

On residual network depth

Benoit Dherin, Michael Munn

Deep residual architectures, such as ResNet and the Transformer, have enabled models of unprecedented depth, yet a formal understanding of why depth is so effective remains an open…

cs.LG2025

Learning by solving differential equations

Benoit Dherin, Michael Munn, Hanna Mazzawi +3

Modern deep learning algorithms use variations of gradient descent as their main learning methods. Gradient descent can be understood as the simplest Ordinary Differential Equation…