Zhe Chen
Scholar

Zhe Chen

Google Scholar ID: j1rq_lYAAAAJ
Nanjing University
Vision-Language ModelVision Foundation ModelLLM Agent
Citations & Impact
All-time
Citations
8,521
 
H-index
29
 
i10-index
36
 
Publications
20
 
Co-authors
20
list available
Resume (English only)
Academic Achievements
  • - Publications:
  • - Vision-RWKV and OmniCorpus accepted as ICLR 2025 spotlight papers
  • - InternVL 1.5 accepted by Science China Information Sciences
  • - InternVL 2.5 released
  • - InternVL 2.0 released
  • - InternVL 1.5 released
  • - InternVL (oral) accepted by CVPR 2024
  • - GeoDiffusion, All-Seeing, BoS (spotlight) accepted by ICLR 2024
  • - AVSegFormer accepted by AAAI 2024
  • - InternImage selected as one of CVPR 2023 Top-10 Influential Papers
  • - VisionLLM accepted by NeurIPS 2023
  • - DDP accepted by ICCV 2023
  • - GPTrans accepted by IJCAI 2023
  • - InternImage (highlight) accepted by CVPR 2023
  • - ViT-Adapter (spotlight) accepted by ICLR 2023
  • - URST accepted by AAAI 2022
  • - Awards:
  • - May 2023: Released InternGPT
  • - Jan 2023: Team won the champion of WSDM Cup 2023 Toloka VQA Challenge
  • - Nov 2022: InternImage-H created new record of 65.4 box AP on COCO test-dev
  • - Sep 2022: Team won the champions in 7 tracks of Ego4D ECCV2022 Challenge
  • - Dec 2020: Team won the champion of NAIC 2020 Remote Sensing Semantic Segmentation Task (1,000,000 RMB bonus)
  • - May 2020: SiameseCCR accepted by IET Image Processing
Research Experience
  • - Started studies in 2020 through a combined Master's and PhD program, expected to graduate in 2026
Education
  • - Sept 2020 - Present: Nanjing University, School of Computer Science, supervised by Prof. Tong Lu
  • - Sept 2016 - June 2020: Zhejiang University of Science and Technology
Background
  • - PhD Candidate at Nanjing University
  • - Research interests include multimodal large language models (MLLMs), vision foundation models (VFMs), and visual perception (e.g., detection & segmentation)