[Distinguished Lecture Series] LIA: A Single-GPU LLM Inference Acceleration with Cooperative AMX-Enabled CPU-GPU Computation and CXL OffloadingNam Sung Kim|UIUC ECE2025/5/07 Wed 11:00 AM|302동 105호
[Distinguished Lecture Series] Calibrated variant classification for clinical utilityPredrag Radivojac|International Society for Computational Biology, Northeastern University 2025/4/24 Thu 10:30 AM|302동 209호
Accelerating Vector Similarity Search with Near-Storage Processing조형민 교수|성균관대학교2025/1/23 Thu 01:00 PM|301동 203호
Safe and high-performance concurrent memory reclamationJaehwang Jung|KAIST CP2024/12/13 Fri 02:00 PM|302동 209호
A Product of Shape and Sequence Abstractions, and its application to OS verificationXavier Rival|Ecole Normale Superieure2024/11/20 Wed 03:30 PM|302동 311-1호
Natural Language Meets Code: The State-of-the-art and Future Directions in LLM-based Debugging강성민(Sungmin Kang)|COINSE research group2024/11/01 Fri 02:00 PM|302동 209호
Domain-specific HW/SW design for the data center applicationEyee Hyun Nam (CEO/CTO of Fadu)|Fadu Co, Ltd, Korea2024/10/14 Mon 04:00 PM|302동 107호
Datacenter Networking for ML and The Stories of Stragglers김창훈 (Chang Kim)|Google2024/10/02 Wed 03:00 PM|302동 311-1호
Continuing performance scaling of complex analytics with secondary storage and accelerators: Case study with genomicsSang-Woo Jun|Univ. of California, Irvine2024/9/23 Mon 10:30 AM|302동 309-1호
