Elorian’s first AI model wants to reason with images, not just about them

Elorian, the Palo Alto AI startup that raised a $55 million seed round at a $300 million valuation before it launched a product, released its first model on Friday, TechCrunch has exclusively learned. The model, Glimpse, is launching as a research preview with API access and a chat interface is waitlist-only, so for now it’s a results table and a thesis.

总部位于帕洛阿尔托的AI初创公司Elorian在产品发布前就以3亿美元的估值完成了5500万美元的种子轮融资。据TechCrunch独家获悉，该公司于周五发布了其首个模型。该模型名为Glimpse，目前以研究预览版形式推出，提供API访问权限，而聊天界面则仅限候补名单用户使用，因此目前它主要表现为一份结果表和一份理论说明。

The thesis? Today’s AI models, for all their skill with language and code, still can’t really see. Most multimodal models look at an image once, convert it to tokens, and then reason about it in text — like describing a photo from memory. Glimpse keeps going back to the source. Mid-reasoning, it can crop into a region, pull specific frames from a video, or run code to measure or compare what it’s looking at, a mechanism Elorian calls a “visual scratch space.” Think of someone pinching to zoom on a phone photo to double-check what they thought they saw.

其核心理论是什么？当今的AI模型尽管在语言和代码方面表现出色，但仍然无法真正“看见”。大多数多模态模型在查看图像时只看一次，将其转换为标记（tokens），然后用文本进行推理——就像凭记忆描述照片一样。而Glimpse会不断回到源头。在推理过程中，它可以裁剪特定区域、从视频中提取特定帧，或运行代码来测量或比较它所看到的内容，Elorian将这种机制称为“视觉草稿空间”。这就像有人在手机上放大照片，以仔细核对他们所看到的内容。

For former Google DeepMind researcher and Elorian CEO Andrew Dai, one of the clearest signs that AI still couldn’t really see came on game night. Last year he photographed a board game he’d just finished with friends and asked a frontier model who was winning. It couldn’t say. Board games “each have their own visual language, each have their own iconography, symbols,” he told TechCrunch. “To an adult, it’s quite easy to understand what’s going on with minimal text, but these models aren’t able to intuit what the symbols mean.”

对于前谷歌DeepMind研究员、Elorian首席执行官Andrew Dai来说，AI无法真正“看见”的最明显迹象出现在一个游戏之夜。去年，他拍下了一张与朋友刚玩完的棋盘游戏照片，并询问一个前沿模型谁在领先，但模型无法回答。他告诉TechCrunch，棋盘游戏“都有各自的视觉语言、图标和符号”。“对于成年人来说，即使文字很少，也很容易理解发生了什么，但这些模型无法直观地理解这些符号的含义。”

“Humans can look at Ikea diagrams, with no text, and assemble Ikea furniture, right? Why can’t AI models?” he said. The approach isn’t completely new — OpenAI added crop-and-zoom during reasoning to its o-series models in 2025 — but Elorian’s pitch is that it built the whole model around it, cheaply. The company says a small team trained Glimpse on a few hundred GPUs and that the model is substantially smaller than the frontier systems it’s benchmarked against.

“人类可以看着没有文字的宜家图纸组装家具，对吧？为什么AI模型做不到？”他说。这种方法并非完全创新——OpenAI在2025年为其o系列模型增加了推理过程中的裁剪和缩放功能——但Elorian的卖点在于它围绕这一功能构建了整个模型，且成本低廉。该公司表示，一个小团队仅用几百个GPU就训练出了Glimpse，而且该模型比其对标的前沿系统要小得多。

Glimpse costs $0.60 per million tokens in and $3 per million tokens out — cheaper than mid-level models like Sonnet and Sol but more expensive than lightweight models like Haiku and Luna. But according to Elorian’s evaluations, Glimpse outperforms even GPT-6 Astra on scientific chart reasoning and short-form video captioning, with competitive results on other visual reasoning tasks.

Glimpse的定价为每百万输入标记0.60美元，每百万输出标记3美元——这比Sonnet和Sol等中端模型便宜，但比Haiku和Luna等轻量级模型贵。然而，根据Elorian的评估，Glimpse在科学图表推理和短视频字幕生成方面甚至超过了GPT-6 Astra，在其他视觉推理任务上也表现出竞争力。

Elorian came out of stealth six months ago with a round co-led by Striker Venture Partners, Menlo Ventures, and Altimeter Capital, with participation from Nvidia and Google chief scientist Jeff Dean. The initial targets are companies sitting on lots of video: robotics firms, scientific labs, media, and creative companies. Longer term, Elorian wants to move from seeing to doing. That means building a model of a scene using that to choose an action, including directly controlling robots. Next year, Dai said, the company aims to build “the world’s best visual reasoning model,” one that leads on every visual reasoning test.

Elorian在六个月前结束隐身状态，其融资由Striker Venture Partners、Menlo Ventures和Altimeter Capital共同领投，英伟达和谷歌首席科学家Jeff Dean也参与其中。其初步目标是那些拥有大量视频数据的公司：机器人公司、科学实验室、媒体和创意公司。从长远来看，Elorian希望从“看见”转向“行动”。这意味着构建一个场景模型，并利用它来选择行动，包括直接控制机器人。Dai表示，公司明年的目标是打造“全球最强的视觉推理模型”，使其在每一项视觉推理测试中都处于领先地位。