Scholar
Kexin Huang
Google Scholar ID: ELa-ADAAAAAJ
University of Science and Technology of China
Citations & Impact
Citations
123
H-index
3
i10-index
2
Publications
10
Co-authors
6
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Two first-author papers accepted at ICML 2025: 'Larger or Smaller Reward Margins to Select Preferences for Alignment?' and 'Learning Bayesian Nash Equilibrium in Auction Games via Approximate Best Response'
- Paper accepted at NeurIPS 2025: 'RePO: ReLU-based Preference Optimization'
- Paper accepted at EMNLP 2025 (Findings): 'LaMP-Val: Large Language Models Empower Personalized Valuation in Auction'
- Paper accepted as Oral at WWW 2025: 'SPRec: Leveraging Self-Play to Debias Preference Alignment for Large Language Model-based Recommendations'
- First-author paper accepted at ICML 2024: 'Auctionformer: A Unified Deep Learning Algorithm for Solving Equilibrium Strategies in Auction Games'
- Paper accepted at SIGIR 2023: 'Alleviating Matthew Effect of Offline Reinforcement Learning in Recommendation', received Best Paper Honorable Mention
- Paper accepted at ICDE 2023: 'Learn to Explore: on Bootstrapping Interactive Data Exploration with Meta-learning'
- Invited reviewer for ICLR and TKDE in 2025
