rednote-hilab ORG

Multilingual Document Layout Parsing in a Single Vision-Language Model

Open-weight AI model from Xiaohongshu that parses documents, PDFs, and images into structured text, tables, and diagrams locally without sending data to a third-party API.

No description.

The official repository of the dots.llm1 base and instruct models proposed by rednote-hilab.

The official repository of the dots.vlm1 instruct models proposed by rednote-hilab.

Multimodal OCR: Parse Anything from Documents

TELL: Test-time Experiential Lifelong Learning – a single LLM agent that learns from experience at test time, achieving 43.9% on ARC-AGI-3 with no training.

No description.

SGLang is a fast serving framework for large language models and vision language models.

No description.

No description.

HiLab fork of verl, RL framework for dots.llm and dots.vlm