1
赛豆科技全新品牌“AIVA”被指与“AVATR”相似，阿维塔官方发声称是荣幸也是警示
IT之家 6 月 9 日消息，阿维塔官方刚刚发文，称看到市场上出现某品牌名称在设计上与阿维塔极为相似。 今天，我们看到市场上出现某品牌名称在设计上与阿维塔极为相似，我们将其视为一种荣幸，但更视为一种警示： 中国汽车不能走 "Ctrl+C Ctrl+V" 之路、不能走不正确的‘逆向研发’的老路 。 被…
2
Inverse Depth Scaling From Most Layers Being Similar
颠覆深度缩放传统认知：层间相似性导致“越深越差”的逆缩放现象，ICML 2026最新发现。
arXiv:2602.05970v2 Announce Type: replace Abstract: Neural scaling laws relate loss to model size in large language models (LLMs), yet depth and width…
3
HAPS: Rethinking Image Similarity for Virtual Staining
重新定义图像相似度度量，HAPS方法为虚拟染色带来更精准的匹配与生成效果。
arXiv:2605.20362v1 Announce Type: new Abstract: Virtual staining of histopathology images (e.g., H&E-IHC) is an emerging tool in digital pathology…
4
PostgreSQL ext makes LLM available as an index for similarity searches,inference
PostgreSQL扩展pg_infer，让LLM模型知识直接作为索引，实现相似度搜索和推理，开源且用Rust编写。
Article URL: https://codeberg.org/gregburd/pg_infer Comments URL: https://news.ycombinator.com/item?id=48180290 Points: 1 # Comments: 0
5
SEED: Targeted Data Selection by Weighted Independent Set
由相似图构建加权独立集，平衡样本质量与多样性，为高效数据选择提供新框架。
arXiv:2605.15691v1 Announce Type: new Abstract: Data selection seeks to identify a compact yet informative subset from large-scale training corpora, b…
6
From Layers to Networks: Comparing Neural Representations via Diffusion Geometry
利用扩散几何从多视角学习比较神经表征，揭示网络与层间相似性，关键创新在于将多视图工具引入表征分析。
arXiv:2605.15901v1 Announce Type: new Abstract: Diffusion geometry is a manifold learning framework that uses random walks defined by Markov transitio…