Haotian Zhang
Scholar

Haotian Zhang

Google Scholar ID: 1vz0kKUAAAAJ
Research Scientist, Apple
Deep LearningComputer VisionVision + Language
Citations & Impact
All-time
Citations
4,599
 
H-index
21
 
i10-index
29
 
Publications
20
 
Co-authors
18
list available
Publications
20 items
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
  • GLIPv2 accepted to NeurIPS 2022.
  • GLIP accepted to CVPR 2022 and selected as a Best Paper Finalist.
  • Recipient of the NeurIPS 2022 Young Scholar Award.
  • Paper 'UDA: Empowering Unsupervised Domain Adaptation with Large-scale Pre-trained Vision-Language Models' accepted to WACV 2024 (Oct 2023).
  • Co-developed Ferret, a multimodal LLM capable of referring and grounding objects at any granularity.
  • Proposed veCLIP, leveraging LLMs for alt-text rewriting to improve CLIP training.