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
How AI memory systems break at scale
AI记忆系统在规模化后因多轮会话导致偏移严重，关键修复不在嵌入模型而在于检索信号，揭示深度学习中的隐藏瓶颈。
Article URL: https://tenureai.dev/writing/how-ai-memory-breaks-at-scale/ Comments URL: https://news.ycombinator.com/item?id=48565584 Points: 3 # Comme…
3
Classical RAG vs Agentic RAG: a practical decision guide
经典RAG与Agentic RAG优劣对比，帮你避开“检索坑”做出明智选择
"Should I use RAG or an agent?" comes up in almost every LLM project I work on. The honest answer is that they are not competing choices. Classical RA…
4
Show HN: Memory for LLM apps that cuts input tokens up to 80% (avg 68%)
GitHub开源项目，让LLM应用拥有长期记忆，同时将输入token平均削减68%，大幅降低API成本。
Article URL: https://github.com/Tem-Degu/streetai-memory Comments URL: https://news.ycombinator.com/item?id=48249509 Points: 1 # Comments: 0
5
Experimenting with graph-based semantic memory for AI agents
开源AI代理图语义记忆项目，整合SQLite、llama.cpp、BGE-M3等，30秒可安装体验。
Article URL: https://github.com/AEndrix03/Graft Comments URL: https://news.ycombinator.com/item?id=48216282 Points: 4 # Comments: 0