NeurIPS 2025 Explorer
Concepts
Authors
Glossary
johnsanterre.github.io
architectural constraints
3 papers
Born a Transformer -- Always a Transformer? On the Effect of Pretraining on Architectural Abilities
Neural Stochastic Flows: Solver-Free Modelling and Inference for SDE Solutions
Reinforcement Learning Finetunes Small Subnetworks in Large Language Models