Guillaume Lajoie

14

Papers

99

Total Citations

Papers (14)

Amortizing intractable inference in large language models

Expressivity of Neural Networks with Random Weights and Learned Biases

In-Context Learning and Occam's Razor

Accelerating Training with Neuron Interaction and Nowcasting Networks

Tracing the Representation Geometry of Language Models from Pretraining to Post-training

LEAD: Min-Max Optimization from a Physical Perspective

Multi-agent cooperation through learning-aware policy gradients

A Unified, Scalable Framework for Neural Population Decoding

Non-normal Recurrent Neural Network (nnRNN): learning long time dependencies while improving expressivity with transient dynamics

Untangling tradeoffs between recurrence and self-attention in artificial neural networks

Gradient Starvation: A Learning Proclivity in Neural Networks

Beyond accuracy: generalization properties of bio-plausible temporal credit assignment rules

Is a Modular Architecture Enough?

Formalizing locality for normative synaptic plasticity models