Efficiency optimization of large-scale language models based on deep learning in natural language processing tasksby…
Overcoming Data and Model Heterogeneities in Decentralized Federated Learning via Synthetic Anchorsby Chun-Yin Huang, Kartik…
Hierarchical Selective Classificationby Shani Goren, Ido Galil, Ran El-YanivFirst submitted to arxiv on: 19 May…
Densely Distilling Cumulative Knowledge for Continual Learningby Zenglin Shi, Pei Liu, Tong Su, Yunpeng Wu,…
AdaKD: Dynamic Knowledge Distillation of ASR models using Adaptive Loss Weightingby Shreyan Ganguly, Roshan Nayak,…
GLiRA: Black-Box Membership Inference Attack via Knowledge Distillationby Andrey V. Galichin, Mikhail Pautov, Alexey Zhavoronkin,…
From Algorithm to Hardware: A Survey on Efficient and Safe Deployment of Deep Neural Networksby…
Sub-goal Distillation: A Method to Improve Small Language Agentsby Maryam Hashemzadeh, Elias Stengel-Eskin, Sarath Chandar,…
Error Exponent in Agnostic PAC Learningby Adi Hendel, Meir FederFirst submitted to arxiv on: 1…
Why does Knowledge Distillation Work? Rethink its Attention and Fidelity Mechanismby Chenqi Guo, Shiwei Zhong,…