T-Sunm/VMARC-QA
Official implementation of 'A knowledge-based Multi-agent approach for Vietnamese VQA with rationale explanations' (AICI 2026).
This project helps AI researchers and developers improve how machines understand Vietnamese images and answer questions about them. It takes Vietnamese image-question pairs as input and produces an accurate answer along with a clear, verifiable explanation for that answer. The primary users are AI practitioners working on advanced Natural Language Processing and Computer Vision challenges for the Vietnamese language.
No commits in the last 6 months.
Use this if you need an AI system that not only answers questions about images in Vietnamese but also provides logical, evidence-based explanations for its responses.
Not ideal if your primary focus is on English-language VQA or if you require a system that runs without external API dependencies or specialized environment setups.
Stars
9
Forks
1
Language
Jupyter Notebook
License
—
Category
Last pushed
Sep 07, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/T-Sunm/VMARC-QA"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
InfinitiBit/graphbit
GraphBit is the world’s first enterprise-grade Agentic AI framework, built on a Rust core with a...
autogluon/autogluon-assistant
Multi-Agent System Powered by LLMs for End-to-end Multimodal ML Automation
pguso/agents-from-scratch
Build AI agents from first principles using a local LLM - no frameworks, no cloud APIs, no...
samholt/L2MAC
🚀 The LLM Automatic Computer Framework: L2MAC
pguso/ai-agents-from-scratch
Demystify AI agents by building them yourself. Local LLMs, no black boxes, real understanding of...