James Amarel

According to our database, James Amarel authored at least 4 papers between 2024 and 2026.

Collaborative distances:

• Dijkstra number of three.
• Erdős number of three.

2026

Loss Landscape Geometry and the Learning of Symmetries: Or, What Influence Functions Reveal About Robust Generalization.

James Amarel, Robyn Miller, Nicolas Hengartner, Benjamin Migliori, Emily Casleton, Alexei N. Skurikhin, Earl Lawrence, Gerd J. Kunde

CoRR, January, 2026

2025

Towards Reasoning for PDE Foundation Models: A Reward-Model-Driven Inference-Time-Scaling Algorithm.

Siddharth Mansingh, James Amarel, Ragib Arnab, Arvind T. Mohan, Kamaljeet Singh, Gerd J. Kunde, Nicolas Hengartner, Benjamin Migliori, Emily Casleton, Nathan DeBardeleben, Ayan Biswas, Diane Oyen, Earl Lawrence

CoRR, September, 2025

Generalization vs. Memorization in Autoregressive Deep Learning: Or, Examining Temporal Decay of Gradient Coherence.

James Amarel, Nicolas Hengartner, Robyn Miller, Kamaljeet Singh, Siddharth Mansingh, Arvind T. Mohan, Benjamin Migliori, Emily Casleton, Alexei N. Skurikhin, Earl Lawrence, Gerd J. Kunde

CoRR, September, 2025

2024

Symmetry constrained neural networks for detection and localization of damage in metal plates.

James Amarel, Christopher Rudolf, Athanasios Iliopoulos, John G. Michopoulos, Leslie N. Smith

CoRR, 2024