Haomin Wang
Scholar

Haomin Wang

Google Scholar ID: EkfrzcYAAAAJ
Shanghai AI Laboratory | Shanghai Jiao Tong University
Computer VisionMultimodal Large Language Models
Citations & Impact
All-time
Citations
304
 
H-index
2
 
i10-index
2
 
Publications
5
 
Co-authors
3
list available
Resume (English only)
Academic Achievements
  • Oct 2025: Released InternSVG
  • Sep 2025: VecFormer and ArchCAD-400K accepted by NeurIPS 2025
  • Aug 2025: Co-released InternVL 3.5
  • Apr 2025: Co-released InternVL 3
  • Published 'InternSVG: Towards Unified SVG Tasks with Multimodal Large Language Models' (2025)
  • Contributed to 'InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency' (2025)
  • Contributed to 'InternSpatial: A Comprehensive Dataset for Spatial Reasoning in Vision-Language Models' (2025)
  • Published 'Point or Line? Using Line-based Representation for Panoptic Symbol Spotting in CAD Drawings' (2025)
  • Contributed to 'InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models' (2025)