Session

· Contributors · Organizations · Search Program · Flagged · My Recommendations · Happening Now

Research Manuscript

: Efficient & Edge-Ready AI Systems

Session Chairs

DescriptionThis session describes strategies for model compression, pruning, sparsity, distillation, efficient inference, edge deployment, and optimization for LLMs and other related neural architectures.

Event Type

Research Manuscript

TimeTuesday, July 283:30pm - 5:30pm PDT

LocationMtg Room 101A

Topics

Tracks

Similar Sessions

RM Poster Session Six

RM Poster Session Seven

RM Poster Session Eight

Presentations

3:30pm - 3:42pm PDT	Pegasus: Personalized and Communication-Efficient Mixture-of-Experts System for Distributed Edge LLM Inference Authors Zhixuan Liao Kongyange Zhao Tao Ouyang Liekang Zeng Siqi Luo Xu Chen
3:42pm - 3:54pm PDT	On-Demand Multi-Task Sparsity for Efficient Large-Model Deployment on Edge Devices Authors Lianming Huang Haibo Hu Qiao Li Nan Guan Chun Jason Xue
3:54pm - 4:06pm PDT	Sharedkd: Gradient-Guided Dynamic Student Discovery Inside a Single 3D Object Detector Authors Hyunjoon Cho Sangho An HYUNSUNG PARK Jangho Kim
4:06pm - 4:18pm PDT	Pefoo-L: A General Framework for Preconditioned Forward-Only Optimizer Enabling LLM Fine-Tuning on the Edge Authors Yuanfang Wang Yu Li Zhinan Qin
4:18pm - 4:30pm PDT	Scoutattention: Efficient KV Cache Offloading via Layer-Ahead CPU Pre-Computation for LLM Inference Authors Qiuyang Zhang Kai Zhou Ding Tang Kai Lu Cheng Li Zhenyu Yang Peng Xu Jiguang Wan
4:30pm - 4:42pm PDT	Ultrasketchllm: Sub-1-Bit LLM Compression via Sketch and Hardware-Friendly Operators Authors Sunan Zou Xueting Sun Ziyun Zhang Guojie Luo
4:42pm - 4:54pm PDT	Think Before You Prune: Self-Reflective Structured Pruning for Reasoning Language Models Authors Ziyan Wang Enmao Diao Qi Le Pu Wang Guanchu Wang Minwoo Lee Shu-ping Yeh Li Yang
4:54pm - 5:06pm PDT	ACE-NAS: A Zero-Cost NAS Framework for Co-Design of Architecture and Encoding in Spiking Neural Networks Authors Mingyu Qin Liangming Fang Wei Liu Jinghai Wang shanlin xiao
5:06pm - 5:18pm PDT	Hardware-Aware Neural Architecture Search for Real-Time BEV-Based 3D Object Detection Authors Jisup Lee Soonhoi Ha Jeongwon Her
5:18pm - 5:30pm PDT	TACo: Training-Free, Hardware-Aware ViT Architecture Search with a Hypervolume-Based Unified Zero-Cost Score Author Eunji Kwon

63dac.conference-program.com