Best Practices for Generative AI with LLMs on a Supercomputer황순욱 (Soonwook Hwang)|National Supercomputing Center of Korea, KISTI2024/2/21 (수) 오후 02:00|302동 209호
[Distinguished Lecture Series] Algorithm-Centric Design of Reliable and Efficient Deep Learning Processing SystemsAlex Orailoglu|University of California, San Diego2024/2/08 (목) 오전 10:30|301동 204호
Understanding the Interactions Between Text and Visualizations김대현 (Dae Hyun Kim)|KAIST Interaction Lab2024/1/18 (목) 오후 02:00|302동 208호
Exploiting PCIe- and CXL-based Accelerators to Reduce Datacenter Memory Tax김남승 (Nam Sung Kim)|University of Illinois, Urbana-Champaign2024/1/10 (수) 오후 03:30|302동 209호
Expanding the Thinkable Territory by Building AI Tools Inspired by Optical Instruments서상호 (Sangho Suh)|University of Toronto, Dynamic Graphics Project (DGP) Lab2024/1/08 (월) 오후 02:00|302동 209호
[IPAI seminar] Techniques and Applications of Diffusion-based Image Generation and Translation주재걸 (Jaegul Cho)|KAIST2023/12/29 (금) 오전 10:00|301동 203호
Recent Trends of Fast Inference in Diffusion Models김동준 (Dongjun Kim)|KAIST2023/12/20 (수) 오전 11:00|302동 106호
Performance, Reliability, and Security in the CXL EraMattan Erez|University of Texas, Austin2023/12/20 (수) 오전 10:30|302동 208호
Cost-Effective LLM Inference Solution Using SK hynix's AiM (Accelerator-in-Memory)권용기|SK hynix Inc.2023/12/15 (금) 오전 11:00|302동 308호
Building An Efficient and Scalable Any-Modality Augmented Language Model문승환 (Seungwhan Moon)|Meta Reality Labs2023/12/14 (목) 오후 12:30|302동 209호
