Papers
1–3 of 3Research Paper·Mar 8, 2026
Interpretable-by-Design Transformers via Architectural Stream Independence
While transformers achieve strong performance, their internal decision-making processes remain opaque. We investigate whether architectural constraints can enforce interpretability by design through a...
7.0 viability
Research Paper·Feb 11, 2026
Low-Dimensional Execution Manifolds in Transformer Learning Dynamics: Evidence from Modular Arithmetic Tasks
We investigate the geometric structure of learning dynamics in overparameterized transformer models through carefully controlled modular arithmetic tasks. Our primary finding is that despite operating...
4.0 viability
Research Paper·Mar 2, 2026
What Helps -- and What Hurts: Bidirectional Explanations for Vision Transformers
Vision Transformers (ViTs) achieve strong performance in visual recognition, yet their decision-making remains difficult to interpret. We propose BiCAM, a bidirectional class activation mapping method...
3.0 viability