Scholar
Yefan Zhou
Google Scholar ID: TAeVaicAAAAJ
Dartmouth College
Citations & Impact
Citations
101
H-index
6
i10-index
5
Publications
13
Co-authors
12
list available
Publications
Resume (English only)
Academic Achievements
- Publications: [1] Variation in Verification: Understanding Verification Dynamics in Large Language Models [2] Diffusion Language Models Know the Answer Before Decoding [3] Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training [4] AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models [5] Sharpness-diversity tradeoff: improving flat ensembles with SharpBalance [6] MD tree: a model-diagnostic tree grown on loss landscape [7] A Three-regime model of Network Pruning [8] Model Balancing Helps Low-data Training and Fine-tuning
Research Experience
- Jun 2025 - Sep 2025: Research Intern at Salesforce AI Research; Jan 2023 - Aug 2023: Research Intern at UC Berkeley ICSI and Sky Computing Lab.
Education
- 2023-Present: CS PhD candidate at Dartmouth College; Master's degree in EECS from UC Berkeley.
Background
- Research Interests: Developing evaluation metrics and systems for ML models, spanning three dimensions: training quality, output reliability, and hyperparameter. Professional Field: Computer Science.
Miscellany
- Personal Achievements: Passed the PhD qualification exam in August 2024.
