Youngsuk Park
Scholar

Youngsuk Park

Google Scholar ID: jWROvQ0AAAAJ
AWS AI Labs, Stanford University
machine learningoptimizationcontrolreinforcement learningdata science
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
866
 
H-index
13
 
i10-index
17
 
Publications
20
 
Co-authors
4
list available
Contact
Emailyoungsuk@cs.stanford.eduLinkedInOpen ↗
Publications
10 items
Not-a-Bandit: Provably No-Regret Drafter Selection in Speculative Decoding for LLMs
2025
Cited
0
Scaling Laws Meet Model Architecture: Toward Inference-Efficient LLMs
2025
Cited
0
Demystifying Transition Matching: When and Why It Can Beat Flow Matching
2025
Cited
0
MuonBP: Faster Muon via Block-Periodic Orthogonalization
2025
Cited
0
TritonRL: Training LLMs to Think and Code Triton Without Cheating
2025
Cited
0
Training LLMs with MXFP4
2025
Cited
0
Stochastic Rounding for LLM Training: Theory and Practice
2025
Cited
0
RoSTE: An Efficient Quantization-Aware Supervised Fine-Tuning Approach for Large Language Models
2025
Cited
0
Resume (English only)
Research Experience
  • Machine Learning Scientist at Amazon Web Service (AWS) AI Labs, Jun. 2020– Present.
  • Data Science Research Intern at Adobe Research, Summer 2019.
  • Research Scientist Intern at Criteo Artificial Intelligence Labs, Summer 2018.
  • Machine Learning Intern at Bosch Center for Artificial Intelligence, Summer 2017.
  • Teaching Assistant for Convex Optimization II, Spring 2015.
Background
  • Research Interests: Time Series Forecasting, Explainable and Causal AI, Machine Learning, Optimization, Reinforcement Learning.
Co-authors
4 total
Stephen Boyd
Stephen Boyd
Professor of Electrical Engineering, Computer Science, and Management Science, Stanford
Jure Leskovec
Jure Leskovec
Professor of Computer Science, Stanford University
Co-author 3
Co-author 3
Ernest K. Ryu
Ernest K. Ryu
University of California, Los Angeles