-
Inject, Align, Recover: Staged Post-Training for Retrieval-Free Document Knowledge Internalization
Paper • 2608.20281 • Published • 10 -
MechVQA: Benchmarking and Enhancing Multimodal LLMs on Comprehensive Mechanical Drawing Understanding
Paper • 2605.30794 • Published • 5 -
ChartWalker: Benchmarking the Cross-Chart RAG Task
Paper • 2606.23997 • Published • 3 -
RAFT: Data Refinement and Adaptive Distillation for Domain Fine-Tuning with Alleviated Forgetting
Paper • 2606.00147 • Published • 2
🔄 In a Training Loop
XiaofengShi
XiaofengAlg
AI & ML interests
AIGC, VLM, NLP, Agent
Recent Activity
upvoted a paper 1 day ago
Aqulia-Med LLM: Pioneering Full-Process Open-Source Medical Language
Models updated a collection 1 day ago
Papers