Jonah Brown-Cohen
5 papers · 2021–2024 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (13) 🐣 Hot Topic Early Bird 👑 Triple Crown
🧭
Keyword Pioneer
Venues
Top co-authors
Research topics
Keywords
debate protocol
(2)
policy optimization
(1)
semidefinite programming
(1)
model evaluation
(1)
ai safety
(1)
state representation
(1)
statistical estimation
(1)
online convex optimization
(1)
adversarial attack
(1)
scalable oversight
(1)
weak-to-strong generalization
(1)
multi-agent debate
(1)
human supervision
(1)
eigenvector computation
(1)
emergent behavior
(1)
large language model
(1)
policy robustness
(1)
neural network
(1)
multi-agent system
(1)
robust decision making
(1)
Papers
On scalable oversight with weak LLMs judging strong LLMs
NeurIPS 2024
Scalable AI Safety via Doubly-Efficient Debate
ICML 2024
SKILL-MIX: a Flexible and Expandable Family of Evaluations for AI Models
ICLR 2024
Detecting Adversarial Directions in Deep Reinforcement Learning to Make Robust Decisions
ICML 2023
Faster Algorithms and Constant Lower Bounds for the Worst-Case Expected Error
NeurIPS 2021