1
2
Recognition-Conditioned Reasoning: A Training-Free Multimodal-LLM Pipeline for Fine-Grained Micro-Action Understanding
无需训练的多模态大模型流水线，精准解析微动作语义，ACM Multimedia 2026亮点工作
arXiv:2608.21022v1 Announce Type: new Abstract: Micro-actions are subtle, short, low-amplitude body movements, such as a fidgeting hand or a slight he…
3
Classifying AI Crawlers and AI Chat User Fetches from Server Logs
只要分析服务器日志，就能精准区分 AI 爬虫与 AI 聊天用户的抓取行为，告别传统 JS 统计盲区，让流量来源一清二楚。
Article URL: https://canonry.ai/blog/classifying-ai-crawlers-user-fetches-server-logs Comments URL: https://news.ycombinator.com/item?id=49294267 Poin…
4
STELLA: Efficient Sensor-to-LLM Translation for On-Device Human Activity Recognition
端侧传感器直连大模型，让人体活动识别更高效精准，边缘智能新方案值得一看。
arXiv:2607.03089v1 Announce Type: cross Abstract: HAR is increasingly expected to run continuously on edge devices, yet recent LLM-based methods remai…