BB
Bowen Baker
cs.AIcs.LGstat.MLcs.CLcs.MAcs.ROblood pressurecardiovascular diseasescs.CVcs.NE
On Valency
published · living versionsW_fvh7g6bt·v1 · currentpublished
Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation
with Joost Huizinga, Leo Gao, Zehao Dou, Melody Y. Guan +4
1 version
Preprints & journals
14 papers in the corpus · 2016–2026OpenAI GPT-5 System Card2601.03267v2 · Aaditya Singh, Adam Fry, Adam Perelman et al.2025 · 18 citationsarXiv
OpenAI o1 System Card2412.16720v2 · OpenAI: Aaron Jaech, Adam Kalai, Adam Lerer et al.2024 · 44 citationsarXiv
Monitoring Monitorability2512.18311v1 · Melody Y. Guan, Miles Wang, Micah Carroll et al.2025 · 1 citationarXiv
Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety2507.11473v2 · Tomek Korbak, Mikita Balesni, Elizabeth Barnes et al.2025 · 2 citationsarXiv
Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision2312.09390v1 · Collin Burns, Pavel Izmailov, Jan Hendrik Kirchner et al.2023 · 25 citationsarXiv
Let's Verify Step by Step2305.20050v1 · Hunter Lightman, Vineet Kosaraju, Yura Burda et al.2023 · 31 citationsarXiv
Use of machine-learning algorithms to determine features of systolic blood pressure variability that predict poor outcomes in hypertensive patients.30976397 · Lacson, Ronilda C, Baker, Bowen, Suresh, Harini et al.2022 · 50 citationsClinical kidney journal. 2019;12(2):206-212
Multi-task curriculum learning in a complex, visual, hard-exploration domain: Minecraft2106.14876v1 · Ingmar Kanitscheider, Joost Huizinga, David Farhi et al.2021 · 9 citationsarXiv
Emergent Reciprocity and Team Formation from Randomized Uncertain Social Preferences2011.05373v1 · Bowen Baker2020 · 5 citationsarXiv
Emergent Tool Use From Multi-Agent Autocurricula1909.07528v2 · Bowen Baker, Ingmar Kanitscheider, Todor Markov et al.2019 · 396 citationsarXiv
Learning Dexterous In-Hand Manipulation1808.00177v5 · OpenAI, Marcin Andrychowicz, Bowen Baker et al.2018 · 1,822 citationsarXiv
Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research1802.09464v2 · Matthias Plappert, Marcin Andrychowicz, Alex Ray et al.2018 · 309 citationsarXiv
Accelerating Neural Architecture Search using Performance Prediction1705.10823v2 · Bowen Baker, Otkrist Gupta, Ramesh Raskar et al.2017 · 43 citationsarXiv
Designing Neural Network Architectures using Reinforcement Learning1611.02167v3 · Bowen Baker, Otkrist Gupta, Nikhil Naik et al.2016 · 418 citationsarXiv
Career total: 18 works. 14 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.