Shangpin Peng
Scholar

Shangpin Peng

Google Scholar ID: mKnBrRAAAAAJ
Harbin Institute of Technology, Shenzhen
Artificial IntelligenceLLMPreference Optimization
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
4
 
H-index
2
 
i10-index
0
 
Publications
2
 
Co-authors
2
list available
Contact
Emailpspdada0808@gmail.comGitHubOpen ↗
Publications
2 items
Mitigating Object Hallucinations via Sentence-Level Early Intervention
2025
Cited
0
Omni-DPO: A Dual-Perspective Paradigm for Dynamic Preference Learning of LLMs
2025
Cited
0
Resume (English only)
Academic Achievements
  • [ICCV 2025] Official repository of 'Mitigating Object Hallucinations via Sentence-Level Early Intervention'.
Research Experience
  • No specific research experience information provided.
Education
  • Undergraduate at Harbin Institute of Technology (Shenzhen).
Background
  • Undergraduate at Harbin Institute of Technology (Shenzhen); Enthusiast in Multimodal LLMs, Preference Optimization, Multimodal Agents, and Open Source; Passionate about academic research and continuous learning; Always open to innovative collaborations and new opportunities.
Miscellany
  • Hobbies: Badminton, Swimming; Contact: pspdada0808@gmail.com; Other platforms: GitHub / Google Scholar / ORCID / OpenReview / RedNote / Hugging Face.
Co-authors
2 total
Zhuotao Tian
Zhuotao Tian
Professor, Harbin Institute of Technology (Shenzhen)
Senqiao Yang
Senqiao Yang
The Chinese University of Hong Kong