Chao Huang
Scholar

Chao Huang

Google Scholar ID: 5yYP5RIAAAAJ
University of Rochester
Computer VisionMulti-modal
Citations & Impact
All-time
Citations
422
 
H-index
10
 
i10-index
11
 
Publications
19
 
Co-authors
10
list available
Resume (English only)
Academic Achievements
  • Multiple papers accepted to top-tier venues: NeurIPS 2025 (3 papers), ICCV 2025 (1 paper), CVPR 2025 (2 papers), ECCV 2024 (1 paper), ACCV 2024 (2 papers, including an Oral presentation for DAVIS), NeurIPS 2023 (1 paper), CVPR 2023 (1 paper), and IEEE TCSVT (survey).
  • DAVIS paper received Honorable Mention for Best Paper Award at ACCV 2024.
  • Selected for ICCV 2025 Doctoral Consortium.
  • Co-organizing the 'TrustFM: Workshop on Trustworthy Foundation Models' at ICCV 2025.
  • Published notable works including DRIFT (enhancing MLLM reasoning via gradient-space guidance), ZeroSep (zero-training audio separation), and XModBench (benchmark for cross-modal consistency in omni-language models).