Phillip Wallis
Source-listed: Google
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- LoRA: Low-Rank Adaptation of Large Language ModelsSaved credit: Contributor · 2021Explore people connected to this work →
- Differential Equation Units: Learning Functional Forms of Activation Functions from DataSaved credit: Contributor · 2020Explore people connected to this work →
- Reinforcement Learning with Backtracking FeedbackSaved credit: Contributor · 2026Explore people connected to this work →
- CausalArmor: Efficient Indirect Prompt Injection Guardrails via Causal AttributionSaved credit: Contributor · 2026Explore people connected to this work →
- LiSA: Lifelong Safety Adaptation via Conservative Policy InductionSaved credit: Contributor · 2026Explore people connected to this work →