Lawrence Chan
7 papers · 2021–2025 · 4 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 ↓+2 more ↓ Show less ↑
🗺️ Taxonomy Completionist (20) 🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Gold 👥 Mega-Team · Squad
🌈
Renaissance Researcher
(5)
🔥
Unstoppable · Bronze
Venues
Top co-authors
Research topics
Artificial Intelligence
(6)
Machine Learning
(6)
Core AI
(6)
Optimization & Theory
(5)
Deep Learning
(4)
Architectures
(3)
Learning Types · Machine Learning
(2)
Mathematics & Optimization
(1)
Natural Language Processing
(1)
Reinforcement Learning
(1)
Robotics
(1)
Applications
(1)
Capabilities
(1)
Generation
(1)
Learning Types · Deep Learning
(1)
Keywords
mechanistic interpretability
(3)
text generation
(1)
language model
(1)
adversarial training
(1)
group theory
(1)
model predictive control
(1)
neural network optimization
(1)
ai safety
(1)
formal verification
(1)
optimal control
(1)
trajectory optimization
(1)
worst-case performance
(1)
cost function
(1)
reward hacking
(1)
autonomous driving
(1)
human expert
(1)
zeroth-order optimization
(1)
neural network verification
(1)
autonomous vehicle
(1)
learning theory
(1)
Papers
RE-Bench: Evaluating Frontier AI R&D Capabilities of Language Model Agents against Human Experts
ICML 2025
Compact Proofs of Model Performance via Mechanistic Interpretability
NeurIPS 2024
The Alignment Problem from a Deep Learning Perspective
ICLR 2024
A Toy Model of Universality: Reverse Engineering how Networks Learn Group Operations
ICML 2023
Progress measures for grokking via mechanistic interpretability
ICLR 2023
Adversarial training for high-stakes reliability
NeurIPS 2022
Optimal Cost Design for Model Predictive Control
L4DC 2021