这次论文俱乐部聊了ParallelKittens和Intelligence Per Watt，都跟AI计算效率相关，适合关注推理硬件的朋友。
Stanford AI Lab组织了一次论文俱乐部活动，由Francois Chaubard主持，聚焦AI推理硬件与系统自动化。Stuart Sul（Stanford/Cursor）介绍了ParallelKittens论文，探讨并行计算架构。Avanika Narayan和Jon Saad-Falcon分享了Intelligence Per Watt论文，衡量本地AI的智能效率。Misha Smelyanskiy（Nvidia/NewCo）阐述了AI推理需要异构硬件的观点。活动还涉及CUDA教学和机器人主题预告。
Great paper club lineup organized by @FrancoisChauba1!
Great paper club lineup organized by @FrancoisChauba1 ! Francois Chaubard @FrancoisChauba1 Great YC Paper Club Kernels/Chips edition last night. Papers: 1 Stuart Sul (Stanford/Cursor) - ParallelKittens ( arxiv.org/pdf/2511.13940 ) 2 Avanika Narayan and Jon Saad-Falcon (Stanford) - Intelligence Per Watt: Measuring Intelligence Efficiency of Local AI ( arxiv.org/pdf/2511.07885 ) 3 Mark Saroufim (Core Automation) - To automate research we must automate systems (no paper) 4 Misha Smelyanskiy (Nvidia/NewCo) - Why AI Inference Needs Heterogeneous Hardware (no paper) 5 Brennan Shacklett (Stanford) - An Extensible, Data-Oriented Architecture for High-Performance, Many-World Simulation ( madrona-engine.github.io/shacklett_sigg… ) pic of @marksaroufim teaching CUDA! next one on robotics.. who should we invite to present? 🔗 View Quoted Tweet 💬 0 🔄 0 ❤️ 1 👀 1334 📊 1 ⚡