-
MechVQA: Benchmarking and Enhancing Multimodal LLMs on Comprehensive Mechanical Drawing Understanding
Paper • 2605.30794 • Published • 5 -
XiaofengAlg/MechVL-4B-RL
Visual Question Answering • 5B • Updated • 491 • 4 -
XiaofengAlg/MechVL-4B-SFT
Visual Question Answering • 570k • Updated • 30 -
XiaofengAlg/MechVQA
Viewer • Updated • 13.5k • 1.16k • 6
👋 Open to Work
XiaofengShi
XiaofengAlg
AI & ML interests
AIGC, VLM, NLP, Agent
Recent Activity
new activity 14 days ago
BAAI/IndustryInstruction:Clarification on commercial model training and customer deployment rights upvoted a collection 17 days ago
MiMo-V2.6 updated a dataset 22 days ago
XiaofengAlg/SPAR-arxiv-cache