- Видео 48
- Просмотров 8 705
Efficient and Intelligent Computing Lab
США
Добавлен 10 янв 2021
The EIC lab in the School of Computer Science at Georgia Tech focuses on developing efficient machine learning systems via cross-layer innovations from algorithm to architecture down to chip design, aiming to promote green AI and enable ubiquitous machine learning powered intelligence.
2024NeurIPS AmoebaLLM
[NeurIPS 2024] "AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment" by Yonggan Fu, Zhongzhi Yu, Junwei Li, Jiayi Qian, Yongan Zhang, Xiangchi Yuan, Dachuan Shi, Roman Yakunin, and Yingyan (Celine) Lin.
Paper: arxiv.org/pdf/2411.10606
Github: github.com/GATECH-EIC/AmoebaLLM
Paper: arxiv.org/pdf/2411.10606
Github: github.com/GATECH-EIC/AmoebaLLM
Просмотров: 50
Видео
2024ECCV Oral Paper: Omni-Recon
Просмотров 72День назад
[ECCV 2024 Oral] "Omni-Recon: Harnessing Image-based Rendering for General-Purpose Neural Radiance Fields" by Yonggan Fu, Huaizhi Qu, Zhifan Ye, Chaojian Li, Kevin Zhao, and Yingyan (Celine) Lin. Paper: arxiv.org/pdf/2403.11131 Github: github.com/GATECH-EIC/Omni-Recon
2024 ICML Enhancing Large Language Models without Training through Attention Calibration
Просмотров 922 месяца назад
[2024 ICML] Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration
2024DAC EDGE-LLM
Просмотров 1362 месяца назад
[2024 DAC] EDGE-LLM: Enabling Efficient Large Language Model Adaptation on Edge Devices via Layerwise Unified Compression and Adaptive Layer Tuning and Voting
2024ICML Linearized-LLM
Просмотров 1032 месяца назад
[ICML 2024] "When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models" by Haoran You, Yichao Fu, Zheng Wang, Amir Yazdanbakhsh, and Yingyan (Celine) Lin.
MG-Verilog: Multi-grained Dataset Towards Enhanced LLM-assisted Verilog Generation
Просмотров 1195 месяцев назад
Demonstration of generating multi-grained descriptions for the customized Verilog code repo using MG-Verilog
2023ICML Master-ASR
Просмотров 98Год назад
[ICML 2023] "Master-ASR: Achieving Multilingual Scalability and Low-Resource Adaptation in ASR with Modular Learning" by Zhongzhi Yu, Yang Zhang, Kaizhi Qian, Cheng Wan, Yonggan Fu, Yongan Zhang, Yingyan (Celine) Lin.
2023ICML NeRFool
Просмотров 194Год назад
[ICML 2023] "NeRFool: Uncovering the Vulnerability of Generalizable Neural Radiance Fields against Adversarial Perturbations" by Yonggan Fu, Ye Yuan, Souvik Kundu, Shang Wu, Shunyao Zhang, Yingyan (Celine) Lin.
2023ISCA Instant-3D (Lightning Talk)
Просмотров 141Год назад
[ISCA 2023] "Instant-3D: Instant Neural Radiance Field Training Towards On-Device AR/VR 3D Reconstruction" by Sixu Li*, Chaojian Li*, Wenbo Zhu, Boyang (Tony) Yu, Yang (Katie) Zhao, Cheng Wan, Haoran You, Huihong Shi, Yingyan (Celine) Lin.
2023ISCA Gen-NeRF (Lightning Talk)
Просмотров 183Год назад
[ISCA 2023] "Gen-NeRF: Efficient and Generalizable Neural Radiance Fields via Algorithm-Hardware Co-Design" by Yonggan Fu, Zhifan Ye, Jiayi Yuan, Shunyao Zhang, Sixu Li, Haoran You, Yingyan (Celine) Lin.
[2023 CVPR] Hint-Aug
Просмотров 114Год назад
[2023 CVPR] "Hint-Aug: Drawing Hints From FViTs Towards Boosted Few-Shot Parameter-Efficient Tuning", by Zhongzhi Yu, Shang Wu, Yonggan Fu, Shunyao Zhang, and Yingyan (Celine) Lin.
2023CVPR AutoCARD
Просмотров 253Год назад
[CVPR 2023] "Auto-CARD: Efficient and Robust Codec Avatar Driving for Real-time Mobile Telepresence" by Yonggan Fu, Yuecheng Li, Chenghui Li, Jason Saragih, Peizhao Zhang, Xiaoliang Dai, Yingyan (Celine) Lin.
2023CVPR Castling-ViT
Просмотров 182Год назад
[CVPR 2023] Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention During Vision Transformer Inference
2023HPCA ViTCoD
Просмотров 623Год назад
[HPCA 2023] "ViTCoD: Vision Transformer Acceleration via Dedicated Algorithm and Accelerator Co-Design" by Haoran You, Zhanyi Sun, Huihong Shi, Zhongzhi Yu, Yang Zhao, Yongan Zhang, Chaojian Li, Baopu Li, Yingyan Lin.
2022ICCAD RT-NeRF
Просмотров 427Год назад
[ICCAD 2022] "RT-NeRF: Real-Time On-Device Neural Radiance Fields Towards Immersive AR/VR Rendering" by Chaojian Li, Sixu Li, Yang Zhao, Wenbo Zhu, Yingyan Lin.
[ICLR 2022] PipeGCN: Efficient Full-Graph Training of GCNs with Pipelined Feature Communication
Просмотров 3462 года назад
[ICLR 2022] PipeGCN: Efficient Full-Graph Training of GCNs with Pipelined Feature Communication
How did you apply the color and density perturbations? These are the output of NeRF's network so are you testing the vulnerability of alpha-compositing?
Pᵣₒmₒˢᵐ 👌
Can u help with code I want to run n check this is cool