Autonomous Qwen3-VL training-code research on the official DocVQA benchmark. main: NVIDIA multi-GPU, mlx: Apple Silicon/MPS.
-
Updated
Apr 19, 2026 - Python
#
docvqa
Here are 7 public repositories matching this topic...
99.156% Accuracy from Agentic Document Extraction DPT-2 model on DocVQA val split
-
Updated
Nov 20, 2025 - HTML
Quasar PoC, Multitenant PoC.
docker bedrock ingress-controller kubectl oidc quasar kapsule ecr-registry faiss envoy-proxy rag fastapi eks-cluster multitenant-architecure streamlit titan-embeddings claude-instant-1 docvqa langchain-document multimodal-question-answering
-
Updated
Feb 23, 2024 - Python
Config-driven long-context benchmark toolkit for vision-language models
-
Updated
Mar 5, 2026 - Python
The repository host codes, link to datasets and models for our research paper. In this paper we have developed a novel approach that can perform DocVQA, RCVQA and MathVQA tasks.
-
Updated
Mar 7, 2025 - Jupyter Notebook
Improve this page
Add a description, image, and links to the docvqa topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the docvqa topic, visit your repo's landing page and select "manage topics."