←Search results

Search “Video”

By relevance · Total 457 results Clear search

Wednesday

  10. Story1 reports · 1 facts

    Google Research releases a multi-agent framework for AI video co-directors

    Google Research has released a multi-agent framework for automatically generating temporally coherent long-form video narratives, aimed at alleviating identity drift and cascading failure issues in existing linear pipelines. The framework is built on Gemini and Veo and comprises four parts: AI video co-director, CANVAS, A2RD, and VQQA, which are respectively responsible for creative orchestration, visual storyboarding, long-duration generation, and closed-loop optimization. Evaluations show that AI video co-director achieves a peak quality score of 81.4 on GenAD-Bench, and A2RD can generate ten-minute-long videos while maintaining character and environment consistency. No further progress has been disclosed at present.

    Google Research has released a multi-agent framework for automatically generating temporally coherent long-form video narratives, aimed at alleviating identity drift and cascading failure issues in existing linear pipelines. The framework is built on Gemini and Veo and comprises four parts: AI video co-director, CANVAS, A2RD, and VQQA, which are respectively responsible for creative orchestration, visual storyboarding, long-duration generation, and closed-loop optimization. Evaluations show that

    Matched fieldsTitle

Monday

Tuesday

Thursday

  1. FactRelated story

    English translation is being prepared.

    Google Research has released a multi-agent framework for automatically generating temporally coherent long-form video narratives, aimed at alleviating identity drift and cascading failure issues in existing linear pipelines. The framework is built on Gemini and Veo and comprises four parts: AI video co-director, CANVAS, A2RD, and VQQA, which are respectively responsible for creative orchestration, visual storyboarding, long-duration generation, and closed-loop optimization. Evaluations show that AI video co-director achieves a peak quality score of 81.4 on GenAD-Bench, and A2RD can generate ten-minute-long videos while maintaining character and environment consistency. No further progress has been disclosed at present.

    Matched fieldsTitle

    View story:Google Research releases a multi-agent framework for AI video co-directors

Thursday

Sunday

  1. Story3 reports · 1 facts

    Nikon Disqualifies AI-Processed Video Winner

    Nikon has determined that the winning video in the Small World In Motion microphotography competition used generative AI in its composition, violating the competition rules, and has disqualified the entry. The winner was Dr. Xu Ning of Tsinghua University in China; the video he submitted showed cilia movement in the airway of a child with PCD. He admitted to using AI but believed it complied with the rules and cooperated with the investigation. Several scientists and former judges had previously questioned the video's authenticity on LinkedIn, with Robert Hirst of the University of Leicester saying he could tell at a glance that the video was fabricated. Nikon said it will re-examine the competition's rules and procedures, and stated that the disqualification does not represent a judgment on his professional reputation, scientific contributions, or intentions.

    Nikon has determined that the winning video in the Small World In Motion microphotography competition used generative AI in its composition, violating the competition rules, and has disqualified the entry. The winner was Dr. Xu Ning of Tsinghua University in China; the video he submitted showed cilia movement in the airway of a child with PCD. He admitted to using AI but believed it complied with the rules and cooperated with the investigation. Several scientists and former judges had previously

    Matched fieldsTitle

Tuesday