← People

Roger Grosse

Source-listed: Associate Professor of Computer Science; Member of Technical Staff; Schwartz Reisman Chair in Technology and Society · University of Toronto; Anthropic

Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.

Selected work

5
  1. Better Training Data Attribution via Better Inverse Hessian-Vector ProductsSaved credit: Contributor · 2025Explore people connected to this work →
  2. Training Data Attribution via Approximate Unrolled DifferentiationSaved credit: Contributor · 2024Explore people connected to this work →
  3. Studying Large Language Model Generalization with Influence FunctionsSaved credit: Contributor · 2023Explore people connected to this work →
  4. Sleeper Agents: Training Deceptive LLMs that Persist Through Safety TrainingSaved credit: Contributor · 2024Explore people connected to this work →
  5. Discovering Language Model Behaviors with Model-Written EvaluationsSaved credit: Contributor · 2022Explore people connected to this work →