Guillaume Lajoie

13

Papers

99

Total Citations

Papers (13)

Amortizing intractable inference in large language models

Expressivity of Neural Networks with Random Weights and Learned Biases

Accelerating Training with Neuron Interaction and Nowcasting Networks

In-Context Learning and Occam's Razor

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

NeurIPS 2025arXiv

Multi-agent cooperation through learning-aware policy gradients

LEAD: Min-Max Optimization from a Physical Perspective

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

Gradient Starvation: A Learning Proclivity in Neural Networks

NeurIPS 2021arXiv

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

NeurIPS 2022arXiv

Is a Modular Architecture Enough?

NeurIPS 2022arXiv

Formalizing locality for normative synaptic plasticity models

A Unified, Scalable Framework for Neural Population Decoding

NeurIPS 2023arXiv