从后排放映：印度语数据、视频 token、PDF 解析与视觉 OCR 干货合集
From the back row: - Well under one percent of the web crawl frontier models learn from is in an In...
一次看完五个视觉与 OCR 实战案例：Sarvam 读了 13 万亿 token，Reducto 解析 PDF 能提分省 token，Noyan 花几美元训检测器，做法都够具体。
Sarvam 的文档模型在看到任何图像前先读了 13 万亿 token 文本，上线四个月已数字化 3500 万页。Perceptron AI 针对一小时视频约百万视觉 token、监督信号仅约 2% 的问题，让模型自己决定读取哪些 token。Reducto 发现把 PDF 页面先解析再喂给前沿模型，可将约 30% 的 PDF 决策基准成绩提升并减少推理 token。Merve Noyan 用大开源模型标注图像、两个小模型筛选框、再训练检测器，成本仅 3-4 美元。Meta 的三智能体审核管线通过压缩相似帧、缓存热门视频判定结果来过滤大部分视频。
From the back row: - Well under one percent of the web crawl frontier models learn from is in an In...
From the back row: - Well under one percent of the web crawl frontier models learn from is in an Indian language. Sarvam's document model read thirteen trillion tokens of text before it saw a pixel, and four months after launch it is digitizing 35 million pages. - Feed a model an hour of video and roughly a million visual tokens go in. The only ground truth is a transcript or a few labeled frames, so it learns from about two percent of them. Perceptron AI's fix is a model that decides which tokens to read. - A frontier model scores about thirty percent on a data lab's benchmark of decisions made from PDFs. Reducto found that handing models a parsed version of the page lifted their scores and cut their reasoning tokens. - Merve Noyan's pipeline labels images with a big open model, has two smaller models judge the boxes, and trains a detector on the survivors, for three or four dollars. Her coding agent made extra training images by flipping traffic signs left to right, until told not to. - Meta keeps most videos out of its three agent review pipeline. It compresses similar frames, caches verdicts on viral videos, and lets creators with a strong record skip it on metadata alone. Vision & OCR playlist: youtube.com/watch?v=RQi7x-… 💬 1 🔄 0 ❤️ 2 👀 390 📊 2 ⚡
