6 papers
MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale
Bin Wang, Tianyao He, Linke Ouyang +40
Current document parsing methods advance primarily through model architecture innovation, while systematic engineering of training data remains underexplored. Yet state-of-the-art…
MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding
Hejun Dong, Junbo Niu, Bin Wang +3
Optical character recognition (OCR) has evolved from line-level transcription to structured document parsing, requiring models to recover long-form sequences containing layout, tab…
LoVR: A Benchmark for Long Video Retrieval in Multimodal Contexts
Qifeng Cai, Hao Liang, Zhaoyang Han +6
Long videos contain a vast amount of information, making video-text retrieval an essential and challenging task in multimodal learning. However, existing benchmarks suffer from lim…
Native Visual Understanding: Resolving Resolution Dilemmas in Vision-Language Models
Junbo Niu, Yuanhong Zheng, Ziyang Miao +8
Vision-Language Models (VLMs) face significant challenges when dealing with the diverse resolutions and aspect ratios of real-world images, as most existing models rely on fixed, l…
LogicPuzzleRL: Cultivating Robust Mathematical Reasoning in LLMs via Reinforcement Learning
Zhen Hao Wong, Jingwen Deng, Runming He +7
Large language models (LLMs) excel at many supervised tasks but often struggle with structured reasoning in unfamiliar settings. This discrepancy suggests that standard fine-tuning…
EVQAScore: A Fine-grained Metric for Video Question Answering Data Quality Evaluation
Hao Liang, Zirong Chen, Hejun Dong +1
Video question-answering (QA) is a core task in video understanding. Evaluating the quality of video QA and video caption data quality for training video large language models (Vid…