Xianhang Li
Scholar

Xianhang Li

Google Scholar ID: YKpFz4YAAAAJ
Ph.D. in UCSC
Computer Vision
Citations & Impact
All-time
Citations
1,273
 
H-index
15
 
i10-index
17
 
Publications
20
 
Co-authors
14
list available
Resume (English only)
Academic Achievements
  • Paper accepted at NeurIPS 2024: 'Scaling White-Box Transformers for Vision'
  • Paper accepted at TMLR 2024: 'Unleashing the Power of Visual Prompting At the Pixel Level'
  • Two papers accepted at CVPR 2024: 'Revisiting Adversarial Training at Scale' and 'Learning to Bootstrap for Combating Label Noise'
  • Paper accepted at NeurIPS 2023: 'An Inverse Scaling Law for CLIP Training'
  • Paper accepted at ECCV 2022: 'In Defense of Image Pre-Training for Spatiotemporal Recognition'
  • Paper accepted at WACV 2022: 'Pose-guided Generative Adversarial Net for Novel View Action Synthesis'
  • Paper accepted at ICLR 2021: 'CT-Net: Channel Tensorization Network for Video Classification'
  • Paper accepted at CVPR 2020: 'SmallBigNet: Integrating Core and Contextual Views for Video Classification'
  • Additional publications at ICLR 2021, NeurIPS ML Safety Workshop 2022, etc.
  • Awarded the Jack Baskin and Peggy Downes-Baskin Fellowship in 2024 (sole recipient)
  • Released Recap-DataComp-1B in 2024, recaptioning 1.3 billion images from DataComp-1B using an LLaMA-3-powered LLaVA model