Termsslug: vqa

VQA

视觉问答

Combines computer vision and NLP to answer questions about image content

Curated Intelligence

3 items · Page 1/1
IT之家 · 智能时代T2·Open Source
78 pts
Xiaomi Open-Sources 0.8B OCR Model for Document Parsing and VQA

Xiaomi has open-sourced Xiaomi-OCR-0, a lightweight document understanding model built on the Qwen3.5-0.8B base. This single-model architecture covers document parsing, key information extraction, and OCR visual question answering, natively supporting Markdown, LaTeX, and JSON outputs. The training process employs a heterogeneous expert consensus mechanism and a 'predict-re-render-compare' closed-loop verification to significantly enhance accuracy in complex tables, formulas, and long-tail scenarios.

Qwen 官方博客 (通义)T1·Models
78 pts
Qwen3-VL Open-Sources Multimodal Embedding & Reranker Models

The Qwen team has open-sourced Qwen3-VL-Embedding and Qwen3-VL-Reranker, built upon the Qwen3-VL foundation model. This series enables unified representation and high-precision reranking for multimodal inputs including text, images, and video, supporting tasks like image-text retrieval and VQA across 30+ languages with flexible vector dimensions.

Hugging Face BlogT1·Models
35 pts
LAVE: Zero-shot VQA Evaluation on Docmatix

The study introduces the LAVE framework for zero-shot Visual Question Answering (VQA) evaluation on the Docmatix dataset using Large Language Models (LLMs). It investigates whether fine-tuning remains necessary given current LLM capabilities. Due to severely truncated source text containing only the title, specific experimental results, methodologies, and conclusions are unavailable.