40 citations · 72 across the 18 of their papers we have counts for
19 papers
The Safety Operator: Modulating the Expression of Safety Instructions via Spectral Optimization
Benoit Dherin, Michael Munn, Xavier Gonzalvo +14
Context tokens in a transformer-based language model can be absorbed into the model's weights as a multiplicative operator. We study this operator in the setting of safety instruct…
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…
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…
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…
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,…
Learning without training: The implicit dynamics of in-context learning
Benoit Dherin, Michael Munn, Hanna Mazzawi +2
One of the most striking features of Large Language Models (LLMs) is their ability to learn in-context. Namely at inference time an LLM is able to learn new patterns without any ad…