rohanpaul_ai· @rohanpaul_ai · X·· 2 小时前AI 评分
Elorian 推出 Glimpse 视频推理模型
Elorian 推出视频理解模型 Glimpse，通过对比场景在不同时间点的变化进行推理，变化小或快时会回溯源视频细看。Elorian 称之为"视觉思考"，即基于帧的观察进行推理。Glimpse 在推理中可返回源视频、裁剪区域、提取特定帧或运行代码测量比较，Elorian 称该机制为"视觉草稿空间"。
Understanding a video means comparing moments, and models are getting much better at it.
Glimpse from @ElorianAI checks how a scene changes from one point in time to another, and goes back for a closer look when the change is small or fast.
Elorian calls this visual thinking: reasoning over what the model observes, grounded in the frames.
Glimpse can return to the source during reasoning, crop into an area, extract specific video frames or run code to measure or compare what it sees, a mechanism Elorian calls a “visual scratch space.”
来源：rohanpaul_ai · x.com