activity
20242026
collaborators

11 papers

cs.AI2026

Scaling Scientific Discovery Environments for Turn-Level Agentic RL

Yucheng Xu, Keyi Zhang, Yuyang Yu +4

Large language model agents have shown promising capabilities in data-driven scientific discovery tasks, where an agent interacts with an execution environment and produces a stati…

cs.CV2026

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…

cs.CL2026

Dripper: Token-Efficient Main HTML Extraction with a Lightweight LM

Mengjie Liu, Jiahui Peng, Wenchang Ning +14

High-quality main content extraction from web pages is a critical prerequisite for constructing large-scale training corpora. While traditional heuristic extractors are efficient,…

cs.CL2025

AICC: Parse HTML Finer, Make Models Better -- A 7.3T AI-Ready Corpus Built by a Model-Based HTML Parser

Ren Ma, Jiantao Qiu, Chao Xu +26

While web data quality is crucial for large language models, most curation efforts focus on filtering and deduplication,treating HTML-to-text extraction as a fixed pre-processing s…

cs.CV2025

MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing

Junbo Niu, Zheng Liu, Zhuangcheng Gu +58

We introduce MinerU2.5, a 1.2B-parameter document parsing vision-language model that achieves state-of-the-art recognition accuracy while maintaining exceptional computational effi…

cs.CV2025

Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling

Zhe Chen, Weiyun Wang, Yue Cao +39

We introduce InternVL 2.5, an advanced multimodal large language model (MLLM) series that builds upon InternVL 2.0, maintaining its core model architecture while introducing signif…