In an era where multimodal large language models (MLLMs) are rapidly advancing, a critical barrier remains: most high-performing vision-language models…
vision-language modeling
VLMEvalKit: One-Command Evaluation for 200+ Vision-Language Models Across 80+ Benchmarks 3536
Evaluating large vision-language models (LVLMs) used to be a fragmented, time-consuming chore—juggling dozens of benchmark repositories, writing custom data loaders,…
PP-OCR: Ultra-Lightweight, Multilingual OCR and Document AI for Real-World Applications 66154
In today’s AI-driven world, turning unstructured visual data—like scanned invoices, handwritten notes, or multilingual PDFs—into structured, machine-readable formats is a…
MonkeyOCR: High-Accuracy Document Parsing for Complex Layouts with Tables, Formulas, and Multilingual Text—Fast, Lightweight, and Deployable 6354
Parsing complex documents—especially those containing tables, mathematical formulas, mixed layouts, or multilingual content—remains a persistent challenge in real-world AI applications.…