
I'm a computer science student at TU Darmstadt working on machine learning research. My work is scattered across different areas, but most connect directly to deep learning. My work focused on optimization dynamics, interpretability and simulation of neurons.
I list my work on axym.org:
- AxoSim and AxoBench — neural simulation [2026]
- The Hierarchical Data Hypothesis — data distributions [2026]
- Exploring How ImageNet Classes Relate to Vision Model Features — interpretability [2026]
- A Handful of Neurons Hold Up a Language Model — interpretability [2026]
- Kernelized Parameter Sensitivity Atlases — interpretability [2026]
- Improved Elastic Weight Consolidation — continual learning [2026]
- Temporal Regularized Learning — local learning [2025]
- pptrain — task-agnostic learning [2026]
- Marey — scientific visualization [2026]
- Share Weights Across Width, Not Depth — architecture [2026]
Reach me at: davide.wiest2 [at] gmail [dot] com