Eric J. Michaud

1. There Will Be a Scientific Theory of Deep Learning
   2026/04/23 by Jamie Simon, Daniel Kunin, Alexander Atanasov +11 · 31 voices · 1 citation
   #stat.ML #cs.LG
2. The Geometry of Concepts: Sparse Autoencoder Feature Structure
   2024/10/10 by Yuxiao Li, Eric J. Michaud, David D. Baek +3 · 9 voices · 19 citations
   Computer Science · Biochemistry, Genetics and Molecular Biology · #Neural Networks and Applications #Machine Learning in Bioinformatics #Fractal and DNA sequence analysis
3. Open Problems in Mechanistic Interpretability
   2025/01/27 by Lee Sharkey, Sharkey, Lee, Bilal Chughtai +58 · 7 voices · 64 citations
   Computer Science · #Natural Language Processing Techniques #Statistical and Computational Modeling #cs.LG
4. Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback
   2023/07/27 by Stephen Casper, Casper, Stephen, Xander Davies +65 · 3 voices · 142 citations
   Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Software Reliability and Analysis Research #cs.AI #cs.CL #cs.LG
5. Towards Understanding Grokking: An Effective Theory of Representation Learning
   2022/05/20 by Ziming Liu, Liu, Ziming, O. Kitouni +9 · 45 citations
   Computer Science · Neuroscience · Physics and Astronomy · #Artificial Intelligence (cs.AI) #Classical Physics (physics.class-ph) #Disordered Systems and Neural Networks (cond-mat.dis-nn) #FOS: Computer and information sciences #FOS: Physical sciences #Machine Learning (cs.LG) #Neural Networks and Applications #Neural dynamics and brain function #Statistical Mechanics (cond-mat.stat-mech) #Statistical Mechanics and Entropy
6. Not All Language Model Features Are One-Dimensionally Linear
   2024/05/23 by Joshua Engels, Engels, Joshua, Eric J. Michaud +7 · 53 citations
   Computer Science · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques
7. Omnigrok: Grokking Beyond Algorithmic Data
   2022/10/03 by Ziming Liu, Eric J. Michaud, Liu, Ziming +3 · 1 voice · 22 citations
   Computer Science · Materials Science · Mathematics · Physics and Astronomy · #Machine Learning and Data Classification #Machine Learning in Materials Science #Neural Networks and Applications #cs.AI #cs.LG #physics.data-an #stat.ME #stat.ML
8. The Quantization Model of Neural Scaling
   2023/03/23 by Eric J. Michaud, Michaud, Eric J., Ziming Liu +5 · 27 citations
   Biochemistry, Genetics and Molecular Biology · Computer Science · #Disordered Systems and Neural Networks (cond-mat.dis-nn) #FOS: Computer and information sciences #FOS: Physical sciences #Machine Learning (cs.LG) #Machine Learning in Bioinformatics #Neural Networks and Applications #Topic Modeling
9. Efficient Dictionary Learning with Switch Sparse Autoencoders
   2024/10/10 by Anish Mudide, Joshua Engels, Mudide, Anish +7 · 17 citations
   Computer Science · #Speech and Audio Processing #Face and Expression Recognition #Advanced Data Compression Techniques
10. Understanding Learned Reward Functions
    2020/12/10 by Eric J. Michaud, Adam Gleave, Michaud, Eric J. +3 · 3 citations
    Computer Science · #Explainable Artificial Intelligence (XAI) #Reinforcement Learning in Robotics #Topic Modeling
11. Physics of Skill Learning
    2025/01/21 by Ziming Liu, Y Liu, Liu, Ziming +7 · 3 citations
    Social Sciences · #Artificial Intelligence (cs.AI) #Data Analysis #Education and Critical Thinking Development #FOS: Computer and information sciences #FOS: Physical sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Statistics and Probability (physics.data-an)
12. Opening the AI black box: program synthesis via mechanistic interpretability
    2024/02/07 by Eric J. Michaud, Michaud, Eric J., Isaac Liao +17 · 1 citation
    Computer Science · #Computability, Logic, AI Algorithms #Evolutionary Algorithms and Applications #FOS: Computer and information sciences #Machine Learning (cs.LG)
13. Survival of the Fittest Representation: A Case Study with Modular Addition
    2024/05/27 by Xiaoman Delores Ding, Zifan Carl Guo, Ding, Xiaoman Delores +7 · 1 citation
    Economics, Econometrics and Finance · #Diverse Scientific and Economic Studies #FOS: Computer and information sciences #Italy: Economic History and Contemporary Issues #Machine Learning (cs.LG)