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
Structuring Knowledge from Semi-Structured Personal Informatics Systems with Large Language Models김영호 (Young-Ho Kim)|NAVER AI Lab2023/12/07 (목) 오후 02:00|302동 209호
Content-Addressable Processing Engines: Toward Highly Programmable Processing-in-Memory ArchitecturesJosé F. Martínez|Cornell University2023/11/10 (금) 오후 02:00|302동 209호
Energy-Efficient Software Systems for Machine LearningJae-Won Chung|University of Michigan, Ann Arbor2023/10/31 (화) 오후 01:00|온라인 - https://snu-ac-kr.zoom.us/j/92087985295 ( PW: snuspl )
Quantum Machine Learning Trends: The Past, Present, and Future방정호 (Jeongho Bang)|ETRI2023/10/30 (월) 오후 02:00|302동 208호
Realizing Quantum Advantage Across Multiple ApplicationsKrishna V. Palem|Accelequant Inc. USA / Rice University2023/10/16 (월) 오후 02:00|302동 308호
Innovating Memory System Architecture by Breaking Conventions in Academic Research and Industry Practice김남승 (Nam Sung Kim)|University of Illinois, Urbana-Champaign2023/10/05 (목) 오후 02:00|302동 209호
SqueezeLLM: Breaking the Memory Wall with Quantization for Fast and Efficient LLM Inference김세훈 (Sehoon Kim)|UC Berkeley2023/9/21 (목) 오전 11:00|온라인
Co-Designing Algorithm-Architecture for Fast, Scalable, and Secure Large Language Models유민수 (Minsoo Rhu)|KAIST2023/9/14 (목) 오전 11:00|302동 209호