Scholar
Peiyang Xu
Google Scholar ID: 9rPOyVsAAAAJ
Princeton University
Citations & Impact
Citations
17
H-index
3
i10-index
0
Publications
3
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- Mitigating Object Hallucination in Large Vision-Language Models through Adversarial Contrastive Finetuning (AAAI 2026, Under review)
- SafeVision: Efficient Image Guardrail with Robust Policy Adherence and Explainability (NeurIPS 2025, Under review)
- MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models (ICLR 2025)
- Natural Language Induced Adversarial Images (ACM Multimedia 2024)
- CurBench: Curriculum Learning Benchmark (ICML 2024)
Co-authors