OW

Olivia Watkins

cs.LGcs.AIcs.CLcs.CVcs.CRcs.CYcs.HCcs.ROstat.MLcs.PL

On Valency

published · living versions
W_3b5urp7g·v1 · currentpublished
Persona Features Control Emergent Misalignment
with Miles Wang, Tom Dupré la Tour, Alex Makelov, Ryan A. Chi +6
1 version

Preprints & journals

15 papers in the corpus · 2018–2026
OpenAI GPT-5 System Card2601.03267v2 · Aaditya Singh, Adam Fry, Adam Perelman et al.2025 · 18 citationsarXiv
Persona Features Control Emergent Misalignment2506.19823v2 · Miles Wang, Tom Dupr'e la Tour, Olivia Watkins et al.2025 · 2 citationsarXivon Valency
GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks2510.04374v1 · Tejal Patwardhan, Rachel Dias, Elizabeth Proehl et al.2025 · 7 citationsarXiv
GPT-4o System Card2410.21276v1 · OpenAI: Aaron Hurst, Adam Lerer, Adam P. Goucher et al.2024 · 165 citationsarXiv
A StrongREJECT for Empty Jailbreaks2402.10260v2 · Alexandra Souly, Qingyuan Lu, Dillon Bowen et al.2024 · 23 citationsarXiv
Learning to Model the World with Language2308.01399v2 · Jessy Lin, Yuqing Du, Olivia Watkins et al.2023 · 3 citationsarXiv
Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game2311.01011v1 · Sam Toyer, Olivia Watkins, Ethan Adrian Mendes et al.2023 · 8 citationsarXiv
DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models2305.16381v3 · Ying Fan, Olivia Watkins, Yuqing Du et al.2023 · 56 citationsarXiv
Guiding Pretraining in Reinforcement Learning with Large Language Models2302.06692v2 · Yuqing Du, Olivia Watkins, Zihan Wang et al.2023 · 37 citationsarXiv
Aligning Text-to-Image Models using Human Feedback2302.12192v1 · Kimin Lee, Hao Liu, Moonkyung Ryu et al.2023 · 35 citationsarXiv
Teachable Reinforcement Learning via Advice Distillation2203.11197v2 · Olivia Watkins, Trevor Darrell, Pieter Abbeel et al.2022 · 0 citationsarXiv
Explaining Reinforcement Learning Policies through Counterfactual Trajectories2201.12462v2 · Julius Frost, Olivia Watkins, Eric Weiner et al.2022 · 3 citationsarXiv
Auto-Tuned Sim-to-Real Transfer2104.07662v2 · Yuqing Du, Olivia Watkins, Trevor Darrell et al.2021 · 53 citationsarXiv
Hierarchical Text Generation using an Outline1810.08802v1 · Mehdi Drissi, Olivia Watkins, Jugal Kalita2018 · 8 citationsarXiv
Program Language Translation Using a Grammar-Driven Tree-to-Tree Model1807.01784v1 · Mehdi Drissi, Olivia Watkins, Aditya Khant et al.2018 · 8 citationsarXiv
Career total: 20 works. 15 are in this corpus.

Profile built from the corpus for this byline.

Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.