Close

Session

Research Manuscript
: Smarter Systems: The Future of Hardware Efficiency in AI
Session Chairs
Chenhui Deng
Nvidia
Liu Cheng
Chinese Academy of Sciences
University of Chinese Academy of Sciences
DescriptionThis session focuses on improving the efficiency of memory and hardware in machine learning systems. Papers presented here cover methods for optimizing hardware components and memory usage, as well as innovative strategies for applying quantization and pruning techniques to neural networks and recommendation systems, to reduce computational costs and power consumption.
Event Type
Research Manuscript
TimeTuesday, June 2410:30am - 12:00pm PDT
Location3001, Level 3
Topics
AI
Tracks
AI1: AI/ML Algorithms
Similar Sessions
Optimizing Large Language Models: Speed, Size, and Smarts
Everything About LLM and Transformer Accelerators
Balancing Speed and Memory: Advancing LLM Acceleration
Presentations
10:30am - 10:45am PDTSpeculative Decoding for Verilog: Speed and Quality, All in One
Authors
Changran Xu
Yi Liu
Yunhao Zhou
Shan Huang
Ningyi Xu
Qiang Xu
AI1: AI/ML Algorithms
10:45am - 11:00am PDTPARO: Hardware-software Co-design with Pattern-aware Reorder-based Attention Quantization in Video Generation Models
Authors
Xinhao Yang
Tianchen Zhao
Hongyi Wang
Wenheng Ma
Shulin Zeng
Zhenhua Zhu
Xuefei Ning
Huazhong Yang
Yu Wang
AI1: AI/ML Algorithms
11:00am - 11:15am PDTHybrid Embedding Framework for Memory-Efficient Recommendation Systems
Authors
Seungjin Yang
Hyuk-Jae Lee
Chae Eun Rhee
AI1: AI/ML Algorithms
11:15am - 11:30am PDTMixed-Precision Quantization for Deep Vision Models with Integer Quadratic Programming
Authors
Zihao Deng
Sayeh Sharify
Xin Wang
Michael Orshansky
AI1: AI/ML Algorithms
11:30am - 11:45am PDTMaximizing Energy Efficiency in Spiking Neural Networks: A Dynamic Joint Pruning Framework
Authors
Shuo Chen
Zeshi Liu
Haihang You
AI1: AI/ML Algorithms
11:45am - 12:00pm PDTDCDiff: : Enhancing JPEG Compression via Diffusion-based DC Coefficients Estimation
Authors
ZIYUAN ZHANG
Han Qiu
Tianwei Zhang
Bin Chen
Chao Zhang
AI1: AI/ML Algorithms