The Center for the Co-Design of Cognitive Systems (CoCoSys) held its second annual review at Georgia Tech on March 12-13, 2024, highlighting research projects conducted through the Center over the past year. “At the recent CoCoSys Year 2 Annual Review, we learned how CoCoSys researchers are inventing the future by combining neural, symbolic, and probabilistic […]
The paper titled “8-bit Transformer Inference and Fine-tuning for Edge Accelerators,” authored by Jeffrey Yu, Kartik Prabhu, Yonatan Urman, Robert M. Radway, Eric Han, and Priyanka Raina will be presented at ASPLOS 2024. The work has fully open-sourced its code and received all three artifact evaluation badges from ASPLOS: “Artifacts Available,” “Artifacts Evaluated,” and “Results […]
“Sloan Research Fellowships are extraordinarily competitive awards involving the nominations of the most inventive and impactful early-career scientists across the U.S. and Canada,” said Adam F. Falk, president of the Alfred P. Sloan Foundation, in the announcement. “We look forward to seeing how fellows take leading roles in shaping the research agenda within their respective […]
Chaojian Li from PI Celine Lin’s group won first place at the Georgia Tech College of Computing (CoC) Graduate Poster Symposium with the poster titled ”’On-Device AR/VR 3D Reconstruction and Rendering.” The event, hosted by the Graduate Student Associations in partnership with the CoC, took place on January 26, 2024, at Georgia Tech. Chaojian presented […]
Yonggan Fu and Chaojian Li from PI Celine Lin’s group held a tutorial session entitled “Dive Deep into Real-Time Neural Rendering” at NVIDIA GTC, which took place at the San Jose McEnery Convention Center on March 21. Specifically, they comprehensively reviewed existing efficient neural rendering techniques and introduced three techniques developed by Lin’s group, which […]
PI Tushar Krishna co-organized a 2-day summit focusing on Post-Moore computing at Georgia Tech on Feb 8-9, 2024, at the Georgia Tech campus. The summit had over 150 attendees, with invited speakers from several universities, national labs, and industry sharing their perspectives on topics ranging from algorithm, software, architecture, circuits, and novel devices.
The Center for Language and Speech Processing at Johns Hopkins University has a long-running seminar series where researchers from academia and industry are invited to present their latest work. Professor Larry Heck from the Georgia Institute of Technology and a Co-PI on the CoCoSys effort in JUMP 2.0 will present on “Next Generation Virtual Assistants: […]
A 65nm CMOS/RRAM test chip has been successfully fabricated and is now under testing. This test chip achieves digital-assisted analog in-memory computing (IMC). Leveraging the ensemble of RRAM IMC and digital SRAM, this design fully recovers the IMC accuracy under device variations and limited ADC precision, with high area efficiency. The chip is fabricated through […]
Priyanka Raina (Stanford) received the NSF CAREER award for her proposal, “A Framework for Co-design and Optimization of Programmable Hardware Accelerators and Compilers.” The National Science Foundation (NSF) Faculty Early Career Development (CAREER) Program is a foundation-wide activity that offers the NSF’s most prestigious awards in support of early-career faculty who have the potential to […]
PI Priyanka Raina (Stanford) presented an invited talk titled “Co-design of Programmable Hardware Accelerators and Compilers for Future Heterogeneous Computing Systems” at the International Solid-State Circuits Conference (ISSCC) 2023 held in San Francisco, California, on February 23, 2023. Priyanka’s talk was part of a forum on “The Future of Heterogeneous Multi-Core Architectures for AI and […]