Search Results for author:
Found 6 papers, 2 papers with code
KwaiYiiMath: Technical Report
Recent advancements in large language models (LLMs) have demonstrated remarkable abilities in handling a variety of natural language processing (NLP) downstream tasks, even on mathematical tasks requiring multi-step reasoning.
Ranked #87 on
Arithmetic Reasoning
on GSM8K
(using extra training data)
FedSkel: Efficient Federated Learning on Heterogeneous Systems with Skeleton Gradients Update
Federated learning aims to protect users' privacy while performing data analysis from different participants.
S2Engine: A Novel Systolic Architecture for Sparse Convolutional Neural Networks
Convolutional neural networks (CNNs) have achieved great success in performing cognitive tasks.
RoSearch: Search for Robust Student Architectures When Distilling Pre-trained Language Models
In order to overcome these security problems, RoSearch is proposed as a comprehensive framework to search the student models with better adversarial robustness when performing knowledge distillation.
SparseTrain: Exploiting Dataflow Sparsity for Efficient Convolutional Neural Networks Training
In this paper, \textit{SparseTrain} is proposed to accelerate CNN training by fully exploiting the sparsity.
Accelerating CNN Training by Pruning Activation Gradients
Sparsification is an efficient approach to accelerate CNN inference, but it is challenging to take advantage of sparsity in training procedure because the involved gradients are dynamically changed.
