Our research

Empowering discovery

We’re on the quest toward radically transparent and efficient lifelong AI.

• [May 2026 – present] – We work on General Pretrained Kernels (GPK) as a semantic substrate layer for robust Lifelong Embodied AI.
• [May 2026, paper, code, demo] – We provide a unifying view on neural computation and introduce Semantic Pullbacks as an effective explanation method for deep models. Our results suggest that pullbacks are often a more natural and informative backward signal than gradients.
• [March 2024, paper, code] – We introduce Semantic Features as a candidate building block for transparent neural networks that are both self-explainable and adversarially robust.