Scholar
Qunyi Xie
Google Scholar ID: JZiUJj6_MJYC
Baidu VIS
OCR、MLLM
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
44
H-index
4
i10-index
0
Publications
16
Co-authors
0
Publications
7 items
HPD-Parsing: Hierarchical Parallel Document Parsing
2026
Cited
0
P-MTP: Efficient Document Parsing via Multi-Token Prediction with Progressive Depth Scaling
2026
Cited
0
Unlimited OCR Works
2026
Cited
0
ERNIE 5.0 Technical Report
2026
Cited
0
Agentic Learner with Grow-and-Refine Multimodal Semantic Memory
2025
Cited
0
MLLMs Need 3D-Aware Representation Supervision for Scene Understanding
2025
Cited
0
On Data Synthesis and Post-training for Visual Abstract Reasoning
2025
Cited
0
