1
CakewordAI
手指一戳，万物皆可学：指哪学哪的多语言AI学习神器，让语言学习变成游戏。
Point at anything to learn its name in any language Discussion | Link
2
Free-Grained Hierarchical Visual Recognition
直面现实标注不完整的层级识别难题，提出自由粒度方法让模型灵活适配不同精细度的类别标签。
arXiv:2510.14737v3 Announce Type: replace Abstract: Hierarchical image recognition seeks to predict class labels along a semantic taxonomy, from broad…
3
RAR: Retrieving And Ranking Augmented MLLMs for Visual Recognition
提出检索与排序增强多模态大模型，精准攻克CLIP细粒度视觉识别短板
arXiv:2403.13805v2 Announce Type: replace-cross Abstract: CLIP (Contrastive Language-Image Pre-training) uses contrastive learning from noise image-te…