Featured Project – CoCoSys

CoCoSys: Co-Design of Cognitive Systems Background A figure illustrating the overview of the different themes in CoCoSys. CoCoSys aims to develop the next generation of human-AI systems by advancing algorithms, specialized hardware, and collective intelligence. These innovations will be applied to collaborative robots, digital assistants, and mixed-reality systems, which require responsiveness, energy efficiency, and trustworthiness. […]

Featured Project – THOR

THOR: Targeted Hybrid Oncotherapeutic Regulation “This work will be a pillar in this Administrationโ€™s ambitious and important goal to cut the cancer death rate in half in 25 yearsโ€ – Xavier Becerra, the United States Secretary of Health and Human Services. A prototype of an implant device to treat ovarian, pancreatic, and other difficult-to-treat cancers. […]

ICCAD Contest on LLM-Assisted Hardware Code Generation Has Been Launched!

๐Ÿ“ฃ ๐‚๐š๐ฅ๐ฅ ๐Ÿ๐จ๐ซ ๐๐š๐ซ๐ญ๐ข๐œ๐ข๐ฉ๐š๐ญ๐ข๐จ๐ง: ๐‹๐‹๐Œ๐Ÿ’๐‡๐–๐ƒ๐ž๐ฌ๐ข๐ ๐ง ๐‚๐จ๐ง๐ญ๐ž๐ฌ๐ญ @ ๐ˆ๐‚๐‚๐€๐ƒ ๐Ÿ๐ŸŽ๐Ÿ๐Ÿ’! We are thrilled to announce the launch of the LLM4HWDesign Contest @ ICCAD 2024, organized by the EIC Lab @ GaTech and Nvidia! Goal We aim to harness community efforts to develop an open-source, large-scale, high-quality dataset that facilitates innovations in large language model (LLM)-based hardware […]

Two Papers on Efficient Large Language Models Were Presented at ICML 2024!

๐Ÿ“ข [๐ˆ๐‚๐Œ๐‹ ๐Ÿ๐ŸŽ๐Ÿ๐Ÿ’] If you are interested in faster and more energy-efficient large language models (LLMs), we invite you to check out the following two papers we presented at ICML 2024! Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration Motivation The attention mechanism is crucial in LLMs, yet […]

MG-Verilog (Dataset Released) Won the Best Paper Award at the First IEEE International Workshop on LLM-Aided Design (LAD’24)!

๐Ÿš€ We are excited to release the ๐— ๐—š-๐—ฉ๐—ฒ๐—ฟ๐—ถ๐—น๐—ผ๐—ด dataset for LLM-assisted Verilog code generation, as presented in our paper, “๐— ๐—š-๐—ฉ๐—ฒ๐—ฟ๐—ถ๐—น๐—ผ๐—ด: ๐— ๐˜‚๐—น๐˜๐—ถ-๐—ด๐—ฟ๐—ฎ๐—ถ๐—ป๐—ฒ๐—ฑ ๐——๐—ฎ๐˜๐—ฎ๐˜€๐—ฒ๐˜ ๐—ง๐—ผ๐˜„๐—ฎ๐—ฟ๐—ฑ๐˜€ ๐—˜๐—ป๐—ต๐—ฎ๐—ป๐—ฐ๐—ฒ๐—ฑ ๐—Ÿ๐—Ÿ๐— -๐—ฎ๐˜€๐˜€๐—ถ๐˜€๐˜๐—ฒ๐—ฑ ๐—ฉ๐—ฒ๐—ฟ๐—ถ๐—น๐—ผ๐—ด ๐—š๐—ฒ๐—ป๐—ฒ๐—ฟ๐—ฎ๐˜๐—ถ๐—ผ๐—ป,” which won ๐˜๐—ต๐—ฒ ๐—•๐—ฒ๐˜€๐˜ ๐—ฃ๐—ฎ๐—ฝ๐—ฒ๐—ฟ ๐—”๐˜„๐—ฎ๐—ฟ๐—ฑ at the First IEEE International Workshop on LLM-Aided Design (LAD’24)! Please feel free to try our ready-to-use dataset at HuggingFace. Motivation The […]