Get started
Author

Dongsheng Ma

MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing
2026 · Junbo Niu, Zheng Liu, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting · 9
MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale
2026 · Wang, Bin, He, Tianyao, et al. · arXiv (Cornell University) · 1
PDF
CLIVO: Differentiable Cluster-Based Instruction Mixing with Learned Validation Objectives
2026 · Wang, Yuhan, Hu, Rui, et al. · arXiv (Cornell University)
PDF
Better Supervision Is Nearby: Neighborhood On-Policy Self-Distillation
2026 · Wei, Xincheng, Ding, Yifan, et al. · arXiv (Cornell University)
PDF
Do Coding Agents Reuse Existing Code or Reinvent the Wheel?
2026 · Ma, Dongsheng, Wang, Sizhe, et al. · arXiv (Cornell University)
PDF
Learning What to Practice: Diagnosis-Guided Self-Evolution for Language Models
2026 · Wei, Xincheng, Ding, Yifan, et al. · arXiv (Cornell University)
PDF
From Diagnosis to Correction: Benchmarking and Improving Real-World Table Parsing
2026 · Xiao, Jutao, Qu, Yuan, et al. · arXiv (Cornell University)
PDF
SAF-OPD: Stable Advantage Fusion for On-Policy Distillation
2026 · Ding, Yifan, Wei, Xincheng, et al. · arXiv (Cornell University)
PDF
CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence
2026 · Ma, Dongsheng, Li, Jiayu, et al. · arXiv (Cornell University)
PDF
mAVE: A Watermark for Joint Audio-Visual Generation Models
2026 · Si, Luyang, Pan, Leyi, et al. · arXiv (Cornell University)
PDF
AgenticOCR: Parsing Only What You Need for Efficient Retrieval-Augmented Generation
2026 · Wang, Zhengren, Ma, Dongsheng, et al. · arXiv (Cornell University)
PDF
Seeing Before Agreeing: Aligning Multi-Agent Consensus with Visual Evidence
2026 · Yuhan Wang, Shuochen Chang, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)
PDF
Works count: 12
Citation count: 10
H-index: 1
I10-index:
Year
Topic
Type