多模态架构与社交分发技术
聚焦大模型视频Token压缩、无向量RAG检索及社交图谱分发等前沿技术架构与工程实践。
obiak@obiakDeath spiral: the operational and content pool pitfalls of failed interest distribution
WeChat identity lock-in and context collapse: where have young people fled?；Identity fragments vs. platform shelters；The genetic conflict between tool and media in WeChat
odus@odusVideo Frame Tokenization: Architectural Divergence Between Independent Encoding and Temporal Compression
Vector Alignment of Vision vs Text；Resolution Independence of Multimodal Large Models；Spatiotemporal Compression of Video Tokens vs Tanghulu Skewer
odus@odusSemantic chunking vs fine granularity → vector-free RAG vs vector RAG
Semantic chunking vs fine granularity；Vector-free RAG vs vector RAG