Is NEO free to use? What license does it have?

NEO is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.

Is NEO still maintained?

Updated within 6 months. The last commit to NEO was on Jul 27, 2026.

What can I use NEO for?

Researching native or encoder-free multimodal model design. Benchmarking vision-language models on image, video and spatial tasks. Fine-tuning a compact 2B or 9B VLM on custom image-text data.

The source code and installation instructions are on GitHub: https://github.com/EvolvingLMMs-Lab/NEO

EvolvingLMMs-Lab/NEO

Open-source native vision-language models (NEO series) that process pixels and words in one encoder-free dense architecture, with 2B and 9B releases.

View on GitHub

Stars: 903
Forks: 0
Open issues: 0
Last commit: 3 months ago

Key features

01Encoder-free dense architecture that unifies pixel and word encoding in one model.
022B and 9B model weights released across training stages.
03Evaluation guide and code built on VLMEvalKit.
04Training code for NEO models in a dedicated guide.
05Covers single-image, multi-image, video and spatial understanding tasks.

Use cases

Researching native or encoder-free multimodal model design.
Benchmarking vision-language models on image, video and spatial tasks.
Fine-tuning a compact 2B or 9B VLM on custom image-text data.

Topics

#multimodal #vision-language-model #vlm #encoder-free #large-language-models #deep-learning #agi #encoder-free-vlm #mllm #multimodal-large-language-models

FAQ

What is NEO?: Open-source native vision-language models (NEO series) that process pixels and words in one encoder-free dense architecture, with 2B and 9B releases.
Is NEO free to use? What license does it have?: NEO is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
Is NEO still maintained?: Updated within 6 months. The last commit to NEO was on Jul 27, 2026.
What can I use NEO for?: Researching native or encoder-free multimodal model design. Benchmarking vision-language models on image, video and spatial tasks. Fine-tuning a compact 2B or 9B VLM on custom image-text data.
Where can I get NEO?: The source code and installation instructions are on GitHub: https://github.com/EvolvingLMMs-Lab/NEO

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects

EvolvingLMMs-Lab / lmms-engine

GitHub

A unified training engine for multimodal models, supporting vision-language, diffusion, and MoE architectures with FSDP2, Muon, and Liger kernels.

AI & Machine Learning #multimodal #training-framework #pytorch #distributed-training #vision-language-model

8300PythonNo licenseUpdated 2 days ago

OpenSenseNova / SenseNova-Vision

GitHub

A unified multimodal model that handles many computer vision tasks by generating text, images, or both from natural-language instructions.

AI & Machine Learning #multimodal #vision-language-model #computer-vision #segmentation #object-detection

7160PythonApache-2.0Updated 2 months ago

OpenSenseNova / SenseNova-U1

GitHub

Open-source native unified multimodal models from SenseNova that handle image understanding, text-to-image generation, and image editing in one architecture.

AI & Machine Learning #multimodal #image-generation #image-editing #vision-language-model #text-to-image

6.9K532PythonApache-2.0Updated 18 days ago

Taichu-AI / ZDTaichu5.0-9B

GitHub

A 9B-parameter open-weight multimodal model for visual understanding, spatial reasoning, agentic tool use, and embodied-AI research, built on Qwen3.5 and C-RADIOv4-H.

AI & Machine Learning #multimodal #vision-language-model #llm #spatial-reasoning #embodied-ai

3.1K540PythonApache-2.0Updated last month

magicrew / doc7

GitHub

Converts PDFs, Office files, scans, screenshots and diagrams into Markdown by sending pages to your own OpenAI-compatible vision model.

AI & Machine Learning #document-ai #pdf-to-markdown #vision-language-model #multimodal #ocr-alternative

7210GoMITUpdated 2 months ago

showlab / livecc

GitHub

A video LLM trained with streaming speech transcription so it can produce real-time commentary on video, with Gradio and CLI demos.

AI & Machine Learning #video-llm #multimodal #speech-transcription #deep-learning #pytorch

4800PythonNo licenseUpdated 12 months ago