AuraTracer智迹闻
中文

EVENT DOSSIER

The domestic video deep reasoning model VLX-VR has been released

2026-09-04 08:00 Models 🔥 42.2 heat score
1sources
1days unfolding
42.2heat score
5mentions

Coverage · reports per dayLANGUAGE SPLIT

Entity relations
Columbia University × G…1Columbia University × M…1Columbia University × O…1Columbia University × V…1Google DeepMind × MINER…1Google DeepMind × OmAI …1

SignalsSIGNALS

Keyword heat
  • OmAI Link Exchange1
  • VLX-VR1
  • Google DeepMind1
  • Columbia University1
  • MINERVA1

All reports (1)SOURCES

科技日报·要闻滚动 zh 2026-09-04 08:00

The domestic video deep reasoning model VLX-VR has been released

On September 1, Hangzhou Lianhui Technology Co., Ltd. officially released the video reasoning model VLX-VR. This model ranked first on the video reasoning benchmark MINERVA jointly developed by Google DeepMind and Columbia University, with an accuracy rate of 78.8% in video问答 tasks, surpassing international flagship models such as Google Gemini 3.5 and OpenAI GPT-4.1. VLX-VR achieves a logic consistency of 96.2%, and its accuracy increases not decreases with time for video lengths ranging from 5 to 15 minutes, reaching a maximum of 80.92%. This release is a continuation of OmAI Lianhui’s technical achievements; previously, in February 2025, the company opened-sourced the visual reasoning model VLM-R1 on GitHub, introducing the强化 learning reasoning framework of DeepSeek-R1 into the visual domain for the first time. As a fundamental ability for physical AI to perceive the world, progress in video reasoning capabilities coincides with the accelerated standardization process of China’s robotics industry.