Scholar
Xinnan Zhang
Google Scholar ID: 5zJlq3QAAAAJ
University of Minnesota, Twin Cities
Alignment
RLHF
agent
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
73
H-index
5
i10-index
5
Publications
12
Co-authors
4
list available
Contact
GitHub
Open ↗
Publications
2 items
Aligning Frozen LLMs by Reinforcement Learning: An Iterative Reweight-then-Optimize Approach
2025
Cited
0
Benchmark on Drug Target Interaction Modeling from a Structure Perspective
arXiv.org · 2024
Cited
0
Resume (English only)
Academic Achievements
Amazon Machine Learning System Fellowship, 2025
Paper at NeurIPS 2024 Workshop: 'LLM alignment through successive policy re-weighting'
Paper at ICLR 2025 Workshop: 'Reinforcement Learning in Inference Time: A Perspective from Successive Policy Iterations'
Paper at KDD 2024: 'The Heterophilic Snowflake Hypothesis: Training and Empowering GNNs for Heterophilic Graphs'
Published in IEEE Transactions on Signal Processing: 'CRB analysis for mixed-ADC based DOA estimation'
Published in IEEE Signal Processing Letters: 'A Novel Mixed-ADC Architecture for DOA Estimation'
Presented at EUSIPCO 2023 (Oral) and ICASSP 2023 (Poster) on mixed-precision DOA estimation
Outstanding Project Award, Neural Network Intelligence (NNI) by MSRA, 2020
Co-authors
4 total
Co-author 1
Mingyi Hong
Associate Professor, University of Minnesota; Amazon AGI
Kaixiong Zhou
Assistant Professor, North Carolina State University
Co-author 4
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up