Summary of A Kernel Perspective on Distillation-based Collaborative Learning, by Sejun Park et al.
A Kernel Perspective on Distillation-based Collaborative Learningby Sejun Park, Kihun Hong, Ganguk HwangFirst submitted to…
Summary of Bonsai: Gradient-free Graph Distillation For Node Classification, by Mridul Gupta and Samyak Jain and Vansh Ramani and Hariprasad Kodamana and Sayan Ranu
Bonsai: Gradient-free Graph Distillation for Node Classificationby Mridul Gupta, Samyak Jain, Vansh Ramani, Hariprasad Kodamana,…
Summary of Model Mimic Attack: Knowledge Distillation For Provably Transferable Adversarial Examples, by Kirill Lukyanov et al.
Model Mimic Attack: Knowledge Distillation for Provably Transferable Adversarial Examplesby Kirill Lukyanov, Andrew Perminov, Denis…
Summary of Hybrid Memory Replay: Blending Real and Distilled Data For Class Incremental Learning, by Jiangtao Kong et al.
Hybrid Memory Replay: Blending Real and Distilled Data for Class Incremental Learningby Jiangtao Kong, Jiacheng…
Summary of Adversarial Score Identity Distillation: Rapidly Surpassing the Teacher in One Step, by Mingyuan Zhou and Huangjie Zheng and Yi Gu and Zhendong Wang and Hai Huang
Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One Stepby Mingyuan Zhou, Huangjie Zheng,…
Summary of Matryoshkakv: Adaptive Kv Compression Via Trainable Orthogonal Projection, by Bokai Lin et al.
MatryoshkaKV: Adaptive KV Compression via Trainable Orthogonal Projectionby Bokai Lin, Zihao Zeng, Zipeng Xiao, Siqi…
Summary of Optimizing Yolov5s Object Detection Through Knowledge Distillation Algorithm, by Guanming Huang et al.
Optimizing YOLOv5s Object Detection through Knowledge Distillation algorithmby Guanming Huang, Aoran Shen, Yuxiang Hu, Junliang…
Summary of Ddil: Improved Diffusion Distillation with Imitation Learning, by Risheek Garrepalli et al.
DDIL: Improved Diffusion Distillation With Imitation Learningby Risheek Garrepalli, Shweta Mahajan, Munawar Hayat, Fatih PorikliFirst…
Summary of Position: On-premises Llm Deployment Demands a Middle Path: Preserving Privacy Without Sacrificing Model Confidentiality, by Hanbo Huang et al.
Position: On-Premises LLM Deployment Demands a Middle Path: Preserving Privacy Without Sacrificing Model Confidentialityby Hanbo…
Summary of Dreamsteerer: Enhancing Source Image Conditioned Editability Using Personalized Diffusion Models, by Zhengyang Yu et al.
DreamSteerer: Enhancing Source Image Conditioned Editability using Personalized Diffusion Modelsby Zhengyang Yu, Zhaoyuan Yang, Jing…