Adam S. Shai

According to our database, Adam S. Shai authored at least 6 papers between 2024 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

Transformers learn factored representations.

Adam S. Shai, Loren Amdahl-Culleton, Casper L. Christensen, Henry R. Bigelow, Fernando E. Rosas, Alexander B. Boyd, Eric A. Alt, Kyle J. Ray, Paul M. Riechers

CoRR, February, 2026

2025

Rank-1 LoRAs Encode Interpretable Reasoning Signals.

Jake Ward, Paul M. Riechers, Adam S. Shai

CoRR, November, 2025

Neural networks leverage nominally quantum and post-quantum representations.

Paul M. Riechers, Thomas J. Elliott, Adam S. Shai

CoRR, July, 2025

Next-token pretraining implies in-context learning.

Paul M. Riechers, Henry R. Bigelow, Eric A. Alt, Adam S. Shai

CoRR, May, 2025

Constrained Belief Updates Explain Geometric Structures in Transformer Representations.

Mateusz Piotrowski, Paul M. Riechers, Daniel Filan, Adam S. Shai

Proceedings of the Forty-second International Conference on Machine Learning, 2025

2024

Transformers Represent Belief State Geometry in their Residual Stream.

Adam S. Shai, Lucas Teixeira, Alexander Gietelink Oldenziel, Sarah Marzen, Paul M. Riechers

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024