跳到正文
原文
omarsar0· @omarsar0 · X·· 7 小时前AI 评分43

ElorianAI 首款 VLM Glimpse 棋盘测试胜 Gemini 3.8 Flash

AI 导读

ElorianAI 发布首款视觉语言模型 Glimpse,在 10 个棋盘俯拍图的同提示词对比测试中取得 8/10 全对,Gemini 3.8 Flash 为 5/10。该测试由人工核验,展示 Glimpse 能整帧读对棋盘而非只读对大部分,可把原始机器人视频转成训练数据。作者称其体现的是 Visual Thinking,而非把视觉识别转成文字。

正文 · 原文

Pay attention to this new wave of VLMs.

Glimpse is the first model from @ElorianAI, the brains that led Google's Gemini and Apple's MM-1.

Quick test: 10 game boards from an overhead camera. Same prompt, same image, two models, hand-checked.

Glimpse: 8/10 boards fully correct.

Gemini 3.8 Flash: 5/10.

This is what data labeling looks like. Getting the whole frame right, not just most of it, turns raw robot footage into training data.

This is powerful Visual Thinking, not just visual recognition translated into text.

来源:omarsar0 · x.com