According to KREA AI (@krea_ai), the company will participate in the Realtime Video AI Summit in San Francisco next Monday, where Sangwu will present their upcoming real-time video model. This event highlights KREA AI's focus on advancing real-time video processing technology using artificial intelligence, which can benefit industries such as live streaming, video conferencing, and content creation. The announcement underscores the increasing demand for low-latency, high-quality AI video solutions and signals new business opportunities in real-time video analytics and generative video applications (Source: twitter.com/krea_ai/status/1980046561896956102).

According to @ak92501 on Twitter, researchers have launched STORM, a novel text-video model that reduces video input size to just one-eighth of the usual requirement while still achieving state-of-the-art performance scores. The STORM architecture integrates mamba layers between a SigLIP vision encoder and a Qwen2-VL language model. These mamba layers effectively aggregate temporal information across video frames, allowing the model to maintain accuracy and efficiency. This development highlights significant business opportunities for companies dealing with video content processing and AI-driven video analytics, as it enables faster, more resource-efficient AI deployments without sacrificing output quality (source: @ak92501, Twitter).