Medium

OpenGVLab

In

AI Advances

by

OpenGVLab

·

May 2, 2024

Open-source vision-language model now comparable to GPT-4V

InternVL 1.5 VS GPT4V. Here are some real cases.

Open-source vision-language model now comparable to GPT-4V

In

AI Advances

by

OpenGVLab

·

Apr 17, 2024

Does Your Multi-model LLM Truly See The Diagrams In Visual Math Problems?

If you want to use an AI model to solve math problems, you need to make sure which one understands diagrams.

Does Your Multi-model LLM Truly See The Diagrams In Visual Math Problems?

In

AI Advances

by

OpenGVLab

·

Apr 3, 2024

InternVid: Video-Text Dataset to Empowering Video Creation and Understanding

A large-scale video-text dataset contains over 7 million videos.

InternVid: Video-Text Dataset to Empowering Video Creation and Understanding

In

AI Advances

by

OpenGVLab

·

Mar 27, 2024

VideoMamba: State Space Model for Efficient Video Understanding

Better, faster, cheaper method for Video understanding with AI

VideoMamba: State Space Model for Efficient Video Understanding

In

AI Advances

by

OpenGVLab

·

Mar 26, 2024

The All-Seeing Project: Towards Panoptic Visual Recognization and General Relation Comprehension…

The All-Seeing Project: Towards Panoptic Visual Recognization and General Relation Comprehension…

OpenGVLab

·

Mar 12, 2024

OmniQuant: Calibrated Quantization for LLMs, Has been Integrated with commercial APP

An open-source, efficient LLM Model quantization method.

OmniQuant: Calibrated Quantization for LLMs, Has been Integrated with commercial APP

OpenGVLab

OpenGVLab

General Vision Team of Shanghai AI Lab; https://github.com/OpenGVLab; https://twitter.com/opengvlab

Following

Help

Status

About

Careers

Press

Blog

Store

Privacy

Rules

Terms

Text to speech