[PDF][PDF] The efficiency spectrum of large language models: An algorithmic survey

T Ding, T Chen, H Zhu, J Jiang, Y Zhong… - arXiv preprint arXiv …, 2023 - researchgate.net
The rapid growth of Large Language Models (LLMs) has been a driving force in
transforming various domains, reshaping the artificial general intelligence landscape …

Dream: Diffusion rectification and estimation-adaptive models

J Zhou, T Ding, T Chen, J Jiang… - Proceedings of the …, 2024 - openaccess.thecvf.com
We present DREAM a novel training framework representing Diffusion Rectification and
Estimation-Adaptive Models requiring minimal code changes (just three lines) yet …

Lorashear: Efficient large language model structured pruning and knowledge recovery

T Chen, T Ding, B Yadav, I Zharkov, L Liang - arXiv preprint arXiv …, 2023 - arxiv.org
Large Language Models (LLMs) have transformed the landscape of artificial intelligence,
while their enormous size presents significant challenges in terms of computational costs …

OTOv3: Automatic Architecture-Agnostic Neural Network Training and Compression from Structured Pruning to Erasing Operators

T Chen, T Ding, Z Zhu, Z Chen, HT Wu… - arXiv preprint arXiv …, 2023 - arxiv.org
Compressing a predefined deep neural network (DNN) into a compact sub-network with
competitive performance is crucial in the efficient machine learning realm. This topic spans …

S3Editor: A Sparse Semantic-Disentangled Self-Training Framework for Face Video Editing

G Wang, T Chen, K Ghasedi, HT Wu, T Ding… - arXiv preprint arXiv …, 2024 - arxiv.org
Face attribute editing plays a pivotal role in various applications. However, existing methods
encounter challenges in achieving high-quality results while preserving identity, editing …