Unverified50% confidenceFactExact time
ViDoRe is a visual document retrieval benchmark proposed by Illuin Tech, short for Visual Document Retrieval, specifically evaluating models' retrieval capability on image-based documents, and provides versions such as v1, v2, and v3.
1
Sources
50%
Confidence
Long-term
Relevance
10/13/2026
First Seen
Sources
Related Entities
Related Claims
Unverifiedllava-phi3 is a multimodal vision-language model (VLM) capable of understanding both image and text inputs simultaneously.65% similarUnverifiedV4-Flash-Vision-Exp can read screenshots, parse charts, and complete multimodal Agent tasks in combination with tool calling.64% similarUnverifiedC2PA规范已被纳入JPEG、PDF等主流文件格式标准，Photoshop、Lightroom等专业工具已原生支持内容凭证的生成与读取64% similarUnverifiedVideOCR 是专门针对视频字幕OCR场景设计的处理库，通过帧差分检测字幕变化、多帧结果融合去重并生成时间戳63% similarUnverifiedQwen VL的视觉编码器基于ViT（Vision Transformer）架构，将图像像素信息压缩编码为语言模型可理解的token序列62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1014369API
curl https://kongchang.com/api/v1/knowledge/claims/1014369MCP
get_claim(id=1014369)