Thomas Dooms

According to our database, Thomas Dooms authored at least 10 papers between 2024 and 2026.

Collaborative distances:

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

2026

When Are Two Networks the Same? Tensor Similarity for Mechanistic Interpretability.

ML Nissen Gonzalez, Melwina Albuquerque, Laurence Wroe, Jacob Meyer Cohen, Logan Riggs Smith, Thomas Dooms

CoRR, May, 2026

From Mechanistic to Compositional Interpretability.

Ward Gauderis, Thomas Dooms, Steven T. Holmer, Kola Ayonrinde, Geraint A. Wiggins

CoRR, May, 2026

Bilinear autoencoders find interpretable manifolds.

Thomas Dooms, Ward Gauderis, Geraint Wiggins, José Oramas M.

CoRR, May, 2026

2025

Finding Manifolds With Bilinear Autoencoders.

Thomas Dooms, Ward Gauderis

CoRR, October, 2025

Parameterized Synthetic Text Generation with SimpleStories.

Lennart Finke, Thomas Dooms, Mat Allen, Juan Diego Rodriguez, Noa Nabeshima, Dan Braun

CoRR, April, 2025

Compositionality Unlocks Deep Interpretable Models.

Thomas Dooms, Ward Gauderis, Geraint A. Wiggins, José Oramas

CoRR, April, 2025

Tokenized SAEs: Disentangling SAE Reconstructions.

Thomas Dooms, Daniel Wilhelm

CoRR, February, 2025

Bilinear MLPs enable weight-based mechanistic interpretability.

Michael T. Pearce, Thomas Dooms, Alice Rigg, José Oramas, Lee Sharkey

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

The Trifecta: Three simple techniques for training deeper Forward-Forward networks.

Thomas Dooms, Ing Jyh Tsang, José Oramas

Trans. Mach. Learn. Res., 2024

Weight-based Decomposition: A Case for Bilinear MLPs.

Michael T. Pearce, Thomas Dooms, Alice Rigg

CoRR, 2024