Yihang Chen
Scholar

Yihang Chen

Google Scholar ID: HzlOQRkAAAAJ
UCLA
Large Language ModelsAlignment
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
164
 
H-index
5
 
i10-index
3
 
Publications
11
 
Co-authors
0
 
Contact
Emailyhangchen@cs.ucla.eduTwitterOpen ↗GitHubOpen ↗LinkedInOpen ↗
Publications
2 items
A Unifying Lens on Supervised Fine-Tuning Through Target Distribution Design
2026
Cited
0
Text is All You Need for Vision-Language Model Jailbreaking
2026
Cited
0
Resume
Academic Achievements
  • Awarded Amazon Fellowship (2025)
  • NeurIPS 2024 Scholar Award with financial assistance
  • Selected as an ootable reviewer for ICLR 2025
  • Recognized as a top reviewer for NeurIPS 2024
  • Oral presentation at Language Gamification Workshop @ NeurIPS 2024 for work on multi-step preference optimization
  • Paper 'Membership Inference Attacks against Large Vision-Language Models' accepted at NeurIPS 2024
  • Paper 'High-Dimensional Kernel Methods under Covariate Shift' accepted at ICML 2024
  • Paper 'Order-Preserving GFlowNets' accepted at ICLR 2024, with a patent filed
  • Contributed to multiple under-review works including IRIS (intrinsic reward-based image synthesis) and DiffCAP (adversarial purification for vision-language models)