Scholar
Hardy Chen
Google Scholar ID: Gype-NsAAAAJ
UC Santa Cruz
Citations & Impact
Citations
1,323
H-index
11
i10-index
11
Publications
12
Co-authors
7
list available
Publications
Resume (English only)
Academic Achievements
- Paper 'ViLBench: A Suite for Vision-Language Process Reward Modeling' accepted by EMNLP 2025
- Paper 'SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models' (VLAA-Thinker) accepted by TMLR 2025
- Two papers accepted to EMNLP 2024 main conference, including first-authored 'LLM Evaluation Bias' and 'HuatuoGPT-Vision'
- Developed ViLBench, a vision-language benchmark requiring intensive process reward signals, along with a 73.6K-sample reward dataset
- Work 'Humans or LLMs as the Judge? A Study on Judgement Biases' inspired Chatbot Arena to disentangle style and substance in ELO scores
