Sean McLeish

Advanced
@mcleish7
mcleish7.github.io/

arithmetic. Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)

201

retrofitting-recurrence. Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence

68

gemstone-scaling-laws. Gemstones: A Model Suite for Multi-Faceted Scaling Laws (NeurIPS 2025)

35

CLRS4LM. Python

8

MLRC-deep-thinking. Deep Thinking Code for MLRC 2023

3
5
Apply