Scholar
Alexander Havrilla
Google Scholar ID: uWFF710AAAAJ
Georgia Institute of Technology
Citations & Impact
Citations
658
H-index
11
i10-index
13
Publications
20
Co-authors
0
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- 1. SPARQ: Synthetic Problem Generation for Reasoning via Quality-Diversity Algorithms, ArXiv
- 2. Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Models, ArXiv
- 3. GLoRe: When, Where, and How to Improve LLM Reasoning via Global and Local Refinements, Accepted to ICML 2024
- 4. Predicting Scaling Laws with Statistical and approximation Theory for Transformer Neural Networks, Accepted to Neurips 2024
- 5. Teaching Large Language Models to Reason with Reinforcement Learning, Submitted to Neurips 2024
- 6. A study in RL for LLM reasoning, Accepted to Neurips 2023 ICBINB workshop
- 7. ARB: An Advanced Reasoning Benchmark for Large Language Modeling, To appear in Neurips 2023 MathAI workshop
- 8. trlX: A Framework for Large Scale Reinforcement Learning from Human Feedback, To appear in EMNLP 2023
- 9. Training Large Language Models with Noisy Algorithmic Chain of Thought, To appear in ICML 2023 worksohp on Symbolic and Data driven methods for reasoning in NLP
- 10. On Deep Generative models for Approximation and Estimation of Distributions on Manifolds, To appear in Neurips 2022
Research Experience
- 1. Research Scientist at Google DeepMind
- 2. Intern at Facebook AI Research (FAIR)
- 3. Intern at Microsoft Research
- 4. Intern at Google Research
- 5. Co-founder of CarperAI, an early open-source research group studying RLHF at scale
Education
- 1. PhD, Machine Learning, Georgia Tech, Advisor: Wenjing Liao
- 2. Joint MS/BS, Mathematics and Computer Science, Carnegie Mellon University, Master's thesis on novel Khintchine type inequalities for random variables
Background
- Research interests include the theoretical/practical limits of AI creativity and discovery, spanning Network Statistical and Approximation theory, RL, LLMs, Synthetic Data, and open-endedness. Obtained a PhD in Machine Learning from Georgia Tech, with a dissertation titled 'Toward a Theory and Practice of Open-ended Reasoning with Generative Models'.
Miscellany
- Website for my research (+ other miscellaneous projects).
Co-authors