Sotabase

Career

· AI Research Intern, Salesforce (Current)2025–
· Research Staff Member, ICSI - International Computer Science Institute2023–2025
· Graduate Student Researcher, Berkeley RISE Lab2021–2023
· Master of Engineering - MEng, Electrical Engineering and Computer Science, University of California, Berkeley2021–2022
· Exchange Student, Electrical Engineering and Computer Science, 4.0/4.0, University of California, Berkeley2019–2019
· Bachelor of Engineering - BE, Information Engineering, Southeast University2016–2020

Publications (14)

Learn to Grasp with Less Supervision: A Data-Efficient Maximum Likelihood Grasp Sampling Loss
IEEE International Conference on Robotics and Automation · 2021
15
cited
AlphaLoRA: Assigning LoRA Experts Based on Layer Training Quality
Conference on Empirical Methods in Natural Language Processing · 2024
14
cited
A Three-regime Model of Network Pruning
International Conference on Machine Learning · 2023
13
cited
A Dataset-Dispersion Perspective on Reconstruction Versus Recognition in Single-View 3D Reconstruction Networks
International Conference on 3D Vision · 2021
AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models
2024
A Model Zoo on Phase Transitions in Neural Networks
2025
A TWO-REGIME MODEL OF NETWORK PRUNING: METRICS AND SCALING LAWS
2023
A Two-Stream Network For Driving Hand Gesture Recognition
2020
DDGNet-YOLO: A Target Detection Network For Dangerous Driving Gestures
2020
Layerwise Training of Deep Neural Networks
2023
MD tree: a model-diagnostic tree grown on loss landscape
2024
Model Balancing Helps Low-data Training and Fine-tuning
2024
Sharpness-diversity tradeoff: improving flat ensembles with SharpBalance
2024
Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training
2023
Sotabase
Yefan Zhou | Researcher Profile | Sotabase | Sotabase