◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Thomas Dooms

10 papers hereh-index 563 citations12 works total

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • first author5
  • middle author3
  • last author1

Across the 9 of 10 papers where every author was matched, so the position is known.

fields
  • cs.LG9
  • cs.CL1

identity via Semantic Scholar / OpenAlex

activity
20232026
most citedThe Trifecta: Three simple techniques for training deeper Forward-Forward networks

3 citations · 3 across the 9 of their papers we have counts for

collaborators
Showing 2024 · cs.LGShow all

2 papers · 2 filters

cs.LG2024

Bilinear MLPs enable weight-based mechanistic interpretability

Michael T. Pearce, Thomas Dooms, Alice Rigg +2

A mechanistic understanding of how MLPs do computation in deep neural networks remains elusive. Current interpretability work can extract features from hidden activations over an i…

cs.LG2024

Weight-based Decomposition: A Case for Bilinear MLPs

Michael T. Pearce, Thomas Dooms, Alice Rigg

Gated Linear Units (GLUs) have become a common building block in modern foundation models. Bilinear layers drop the non-linearity in the "gate" but still have comparable performanc…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.