General framework for online-to-nonconvex conversion: Schedule-free SGD is also effective for nonconvex optimizationby Kwangjun Ahn,…
Zeroth-Order Adaptive Neuron Alignment Based Pruning without Re-Trainingby Elia Cunegatti, Leonardo Lucio Custode, Giovanni IaccaFirst…
Universal Response and Emergence of Induction in LLMsby Niclas LuickFirst submitted to arxiv on: 11…
Research on an intelligent fault diagnosis method for nuclear power plants based on ETCN-SSA combined…
PDC & DM-SFT: A Road for LLM SQL Bug-Fix Enhancingby Yiwen Duan, Yonghong Yu, Xiaoming…
Sketched Adaptive Federated Deep Learning: A Sharp Convergence Analysisby Zhijie Chen, Qiaobo Li, Arindam BanerjeeFirst…
White-Box Diffusion Transformer for single-cell RNA-seq generationby Zhuorui Cui, Shengze Dong, Ding LiuFirst submitted to…
Model Partition and Resource Allocation for Split Learning in Vehicular Edge Networksby Lu Yu, Zheng…
MP-PINN: A Multi-Phase Physics-Informed Neural Network for Epidemic Forecastingby Thang Nguyen, Dung Nguyen, Kha Pham,…
ScaleKD: Strong Vision Transformers Could Be Excellent Teachersby Jiawei Fan, Chao Li, Xiaolong Liu, Anbang…