Scholar
Zhiqiu Lin
Google Scholar ID: TFlZ2OcAAAAJ
Carnegie Mellon University
Citations & Impact
Citations
1,440
H-index
15
i10-index
16
Publications
20
Co-authors
3
list available
Publications
Resume (English only)
Academic Achievements
- 1. CameraBench accepted to NeurIPS’25 (Spotlight)
- 2. NaturalBench accepted to NeurIPS’24
- 3. VQAScore accepted to ECCV’24, highlighted in Google’s Imagen3 Technical Report as the strongest replacement for CLIPScore
- 4. GenAI-Bench won Best Short Paper Award at SynData@CVPR2024
- 5. VisualGPTScore accepted to ICML’24
- 6. Two papers accepted to CVPR’24: 'Language Models as Black-Box Optimizers for Vision-Language Models' and 'The Neglected Tails of Vision-Language Models'
- 7. 'Revisiting the Role of Language Priors in Vision-Language Models' demonstrates top-tier performance across retrieval benchmarks like ARO/SugarCrepe/Winoground
- 8. 'Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning with Multimodal Models' accepted by CVPR’23
- 9. 'LECO: Continual Learning with Evolving Class Ontologies' accepted by NeurIPS’22
- 10. 'The CLEAR Benchmark: Continual LEArning on Real-World Imagery' accepted by NeurIPS’21
- 11. 'Visual Chirality' received Best Paper Nomination at CVPR’20
Research Experience
- 1. Internship at Meta GenAI, Mentors: Pengchuan Zhang and Xide Xia
- 2. Research projects include CameraBench, NaturalBench, VQAScore, GenAI-Bench, etc.
Education
- 1. Ph.D.: Robotics Institute, Carnegie Mellon University, Advisor: Prof. Deva Ramanan
- 2. Undergraduate: Computer Science and Mathematics, Cornell University
Background
- Ph.D. student at Robotics Institute of Carnegie Mellon University, advised by Prof. Deva Ramanan. Undergrad in Computer Science and Maths at Cornell University and served as college symbol bearer (top 5 of the college). Current research focuses on computer vision and language, especially evaluating and improving multimodal generative models.
Miscellany
- No additional information provided
