Marcovaldon

Pinned Repositories

• ADE-dataset

  A first dataset to determine the alignment relation between visual and textual elements on diagrams for diagram understanding. We will open the dataset and code after the paper is acceped.

  0120

• InternLM-XComposer

  InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions

  Language:Python2.6k44395159

• TabRecSet

  A large scale camera-taken table detection and recognition dataset.

  Language:Python1134138

• ms-swift

  Use PEFT or Full-parameter to finetune 400+ LLMs (Qwen2.5, Llama3.2, GLM4, Internlm2.5, Yi1.5, Mistral, Baichuan2, DeepSeek, ...) or 100+ MLLMs (Qwen2-VL, Qwen2-Audio, Llama3.2-Vision, Llava, InternVL2.5, MiniCPM-V-2.6, GLM4v, Xcomposer2.5, Yi-VL, DeepSeek-VL2, Phi3.5-Vision, GOT-OCR2, ...).

  Language:Python4.7k241.4k407

• CuMo

  CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts

  Language:Python13621310

• surya

  OCR, layout analysis, reading order, table recognition in 90+ languages

  Language:Python14.6k108170924

• vqaonline.github.io

  Language:JavaScript0110

Marcovaldon's Repositories