CLIP-Embed-KD: Computationally Efficient Knowledge Distillation Using Embeddings as Teachersby Lakshmi NairFirst submitted to arxiv on:…
What Happens When Small Is Made Smaller? Exploring the Impact of Compression on Small Data…
Improve Knowledge Distillation via Label Revision and Data Selectionby Weichao Lan, Yiu-ming Cheung, Qing Xu,…
On the Surprising Efficacy of Distillation as an Alternative to Pre-Training Small Modelsby Sean Farhat,…
Knowledge Distillation-Based Model Extraction Attack using GAN-based Private Counterfactual Explanationsby Fatima Ezzeddine, Omran Ayoub, Silvia…
Goldfish: An Efficient Federated Unlearning Frameworkby Houzhe Wang, Xiaojie Zhu, Chi Chen, Paulo Esteves-VeríssimoFirst submitted…
Foundation Models for Structural Health Monitoringby Luca Benfenati, Daniele Jahier Pagliari, Luca Zanatta, Yhorman Alexander…
Orchestrate Latent Expertise: Advancing Online Continual Learning with Multi-Level Supervision and Reverse Self-Distillationby HongWei Yan,…
JEP-KD: Joint-Embedding Predictive Architecture Based Knowledge Distillation for Visual Speech Recognitionby Chang Sun, Hong Yang,…
Oh! We Freeze: Improving Quantized Knowledge Distillation via Signal Propagation Analysis for Large Language Modelsby…