Reading archive

Paper Summaries

A full list of paper summary notes mirrored from my private research repository. Each entry opens as an internal reading page without rewriting the content.

Summary collection

Available summaries

CellE: Automated Standard Cell Library Extension via Equality Saturation

This note summarizes how standard cell library extension (`SCLX`) can more systematically discover composite cells that post-mapping netlist mining tends to miss.

Authors

Yi Ren, Yukun Wang, Xiang Meng, Guoyao Cheng, Baokang Peng, Lining Zhang, Yibo Lin, Runsheng Wang, Guangyu Sun

Publication

63rd ACM/IEEE Design Automation Conference (DAC ’26), 2026-07-26 to 2026-07-29

ContextWhatWhy

Read summary

Towards end-to-end automation of AI research

This note summarizes how far AI agents can automate the full machine learning research lifecycle end to end.

Authors

Chris Lu, Cong Lu, Robert Tjarko Lange, Yutaro Yamada, Shengran Hu, Jakob Foerster, David Ha, Jeff Clune

Publication

Nature, 2026-03-26

ContextWhatWhy

Read summary

An On-Device Generative AI Focused Neural Processing Unit in 4nm Flagship Mobile SoC with Fan-Out Wafer-Level Package

This note summarizes an NPU architecture for handling on-device generative AI workloads in a mobile SoC.

Authors

Jun-Seok Park, Taehee Lee, Heonsoo Lee, Changsoo Park, Youngsang Cho, Mookyung Kang, Heeseok Lee, Jinwon Kang, Taeho Jeon, Dongwoo Lee, Yesung Kang, Kyungmok Kum, Geunwon Lee, Hongki Lee, Minkyu Kim, Suknam Kwon, Sung-beom Park, Dongkeun Kim, Chulmin Jo, HyukJun Chung, Ilryoung Kim, Jongyoul Lee

Publication

2025 IEEE International Solid-State Circuits Conference (ISSCC 2025), 2025-02-18

ContextWhatWhy

Read summary

SO3-Cell: Standard Cell Layout Automation Framework for Simultaneous Optimization of Topology, Placement, and Routing

This note summarizes an approach for handling topology, placement, and routing jointly rather than optimizing them separately during standard-cell layout automation for advanced VLSI nodes.

Authors

Chung-Kuan Cheng, Andrew B. Kahng, Byeonggon Kang, Seokhyeong Kang, Jakang Lee, Bill Lin

Publication

2025 IEEE/ACM International Conference on Computer-Aided Design (ICCAD), 2025

ContextWhatWhy

Read summary

The Llama 3 Herd of Models

This note summarizes how an open multilingual foundation language model release can jointly handle pre-training, post-training, tool use, long context, and safety.

Authors

Llama Team, AI @ Meta

Publication

arXiv, 2024-07-23

ContextWhatWhy

Read summary

NVCell 2: Routability-Driven Standard Cell Layout in Advanced Nodes with Lattice Graph Routability Model

This note summarizes an approach for improving both placement-stage routability prediction and routing-stage pin allocation during standard-cell synthesis in advanced nodes.

Authors

Chia-Tung Ho, Alvin Ho, Matthew Fojtik, Minsoo Kim, Shang Wei, Yaguang Li, Brucek Khailany, Haoxing Ren

Publication

Proceedings of the 2023 International Symposium on Physical Design (ISPD ’23), 2023-03-26 to 2023-03-29

ContextWhatWhy

Read summary

A Multi-Mode 8K-MAC HW-Utilization-Aware Neural Processing Unit with a Unified Multi-Precision Datapath in 4nm Flagship Mobile SoC

This note summarizes how a mobile/embedded NPU handles mixed precision, low latency, and always-on requirements within one architecture.

Authors

Jun-Seok Park, Changsoo Park, Suknam Kwon, Hyeong-Seok Kim, Taeho Jeon, Yesung Kang, Heonsoo Lee, Dongwoo Lee, James Kim, YoungJong Lee, Sangkyu Park, Jun-Woo Jang, SangHyuck Ha, MinSeong Kim, Jihoon Bang, Suk Hwan Lim, Inyup Kang

Publication

2022 IEEE International Solid-State Circuits Conference (ISSCC 2022), 2022-02-23

ContextWhatWhy

Read summary

Softermax: Hardware/Software Co-Design of an Efficient Softmax for Transformers

This note summarizes the softmax bottleneck in Transformer inference from a hardware/software co-design perspective.

Authors

Jacob R. Stevens, Rangharajan Venkatesan, Steve Dai, Brucek Khailany, Anand Raghunathan

Publication

arXiv, 2021-03-16

ContextWhatWhy

Read summary