---
title: "SenseTime releases NEO architecture, expected to be the industry's first to achieve deep integration of native multimodal architecture"
type: "News"
locale: "en"
url: "https://longbridge.com/en/news/268352812.md"
description: "SenseTime released and open-sourced the multimodal model architecture \"NEO\" developed in collaboration with the S-Lab of Nanyang Technological University. This is the industry's first native multimodal architecture that achieves deep integration. The NEO architecture realizes unified processing of vision and language through innovative underlying design and adopts a dual-stage fusion training strategy to enhance the model's visual perception capabilities. SenseTime plans to promote NEO as the next-generation AI infrastructure through open-source collaboration and scene implementation, facilitating the industrial application of multimodal technology"
datetime: "2025-12-03T03:42:22.000Z"
locales:
  - [zh-CN](https://longbridge.com/zh-CN/news/268352812.md)
  - [en](https://longbridge.com/en/news/268352812.md)
  - [zh-HK](https://longbridge.com/zh-HK/news/268352812.md)
generator: "portal-rs"
---

# SenseTime releases NEO architecture, expected to be the industry's first to achieve deep integration of native multimodal architecture

SenseTime Technology (00020.HK) announced the official release and open-source of the new multimodal model architecture "NEO," developed in collaboration with the S-Lab of Nanyang Technological University. It is expected to be the industry's first available native multimodal architecture (Native VLM) that achieves deep integration. Starting from fundamental principles, NEO is designed with innovation specifically for multimodality, achieving deep integration at the core architecture level, resulting in a breakthrough in performance, efficiency, and versatility. This lays a new architectural foundation for the SenseNova multimodal model and marks the entry of AI multimodal technology into a new era of "native architecture."

SenseTime stated that the NEO architecture is centered around extreme efficiency and deep integration. Through fundamental innovations in three key dimensions: attention mechanisms, positional encoding, and semantic mapping, the model inherently possesses the ability to unify the processing of visual and language data. Additionally, with the innovative Pre-Buffer & Post-LLM dual-stage integration training strategy, NEO can absorb the complete language reasoning capabilities of the original LLM while building strong visual perception capabilities from scratch, addressing the issue of impaired language abilities in traditional cross-modal training.

SenseTime aims to drive the development of NEO into a scalable and reusable next-generation AI infrastructure through open-source collaboration and scenario implementation, thereby promoting the industrial application of native multimodal technology from the laboratory to widespread use

### Related Stocks

- [00020.HK](https://longbridge.com/en/quote/00020.HK.md)

## Related News & Research

- [SenseTime open-sources 8B multimodal model with native 4K image output](https://longbridge.com/en/news/296573745.md)
- [ACE Robotics CEO says robot brains will have 'ChatGPT moment' by end of 2027](https://longbridge.com/en/news/296600476.md)
- [Champion Real Estate Investment Trust: Rental and distributable income fell, but property values and liquidity remain robust](https://longbridge.com/en/news/296332233.md)
- [JDC: Record growth in turnover and EBITDA, with strong outlook driven by new regulation and AI](https://longbridge.com/en/news/296247395.md)
- [Smoore International declares interim dividend of HKD 0.2 per share](https://longbridge.com/en/news/296363377.md)

---
> **Disclaimer: This article is for reference only and does not constitute any investment advice.**