Yunjian Xu
Scholar

Yunjian Xu

Google Scholar ID: BVw1yP0AAAAJ
The Chinese University of Hong Kong
Deep reinforcement learningPower systemsElectricity marketsOperations ResearchStochastic optimal control
Google Scholar↗
Citations & Impact
All-time
Citations
2,134
 
H-index
28
 
i10-index
49
 
Publications
20
 
Co-authors
33
list available
Contact
No contact links provided.
Publications
5 items
DASH-OPD: Discrepancy-Aware Switching with Hysteresis for On-Policy Distillation
2026
Cited
0
ADG: Ambient Diffusion-Guided Dataset Recovery for Corruption-Robust Offline Reinforcement Learning
2025
Cited
0
Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs
2025
Cited
0
Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key
2025
Cited
0
GAS: Generative Auto-bidding with Post-training Search
The Web Conference · 2024
Cited
0
Resume (English only)
Co-authors
33 total
Co-author 1
Co-author 1
Costas Courcoubetis
Costas Courcoubetis
Professor in SDS, CUHK Shenzhen
Lang Tong
Lang Tong
Irwin and Joan Professor in Engineering, Cornell University
Adam Wierman
Adam Wierman
Carl F Braun Professor of Computing+Mathematical Sciences, Caltech
Co-author 5
Co-author 5
Co-author 6
Co-author 6
Subhonmesh Bose
Subhonmesh Bose
University of Illinois Urbana-Champaign
Co-author 8
Co-author 8