1
Douyin Multimodal Embedding Model Technical Report
抖音多模态嵌入模型技术报告，揭秘工业级搜索推荐背后的向量表示学习。
arXiv:2608.02148v1 Announce Type: cross Abstract: Multimodal representation learning is a cornerstone of modern AI. By encoding multimodal queries and…
2
Select or Project? Evaluating Lower-dimensional Vectors for LLM Training Data Explanations
降维向量能否讲清大模型训练数据？这篇论文给出了实证对比，值得关注。
arXiv:2601.16651v3 Announce Type: replace Abstract: Gradient-based methods for instance-based explanation for large language models (LLMs) are hindere…
3
Vectors Are Not Neutral: Sensitive-Information Inference from Exported LLM Representations in Summarization
研究表明，LLM在摘要任务中导出的向量表示并不中立，会泄露敏感信息，引发隐私安全新担忧。
arXiv:2605.26433v1 Announce Type: new Abstract: Large language model (LLM) summarization systems may pass compact vector representations of private in…