most citedOne-for-All: Bridge the Gap Between Heterogeneous Architectures in Knowledge Distillation

31 citations · 73 across the 8 of their papers we have counts for

collaborators

8 papers

cs.CV2024

Token Compensator: Altering Inference Cost of Vision Transformer without Re-Tuning

Shibo Jie, Yehui Tang, Jianyuan Guo +3

Token compression expedites the training and inference of Vision Transformers (ViTs) by reducing the number of the redundant tokens, e.g., pruning inattentive tokens or merging sim…

cs.LG2024

ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking

Wenshuo Li, Xinghao Chen, Han Shu +2

Large language models (LLM) have recently attracted significant attention in the field of artificial intelligence. However, the training process of these models poses significant c…

cs.CV202417 cited

GhostNetV3: Exploring the Training Strategies for Compact Models

Zhenhua Liu, Zhiwei Hao, Kai Han +2

Compact neural networks are specially designed for applications on edge devices with faster inference speed yet modest performance. However, training strategies of compact models a…

cs.CL20246 cited

DenseMamba: State Space Models with Dense Hidden Connection for Efficient Large Language Models

Wei He, Kai Han, Yehui Tang +4

Large language models (LLMs) face a daunting challenge due to the excessive computational and memory requirements of the commonly used Transformer architecture. While state space m…

cs.LG202414 cited

A Survey on Transformer Compression

Yehui Tang, Yunhe Wang, Jianyuan Guo +4

Transformer plays a vital role in the realms of natural language processing (NLP) and computer vision (CV), specially for constructing large language models (LLM) and large vision…

cs.CL20231 cited

PanGu-: Enhancing Language Model Architectures via Nonlinearity Compensation

Yunhe Wang, Hanting Chen, Yehui Tang +17

The recent trend of large language models (LLMs) is to increase the scale of both model size (\aka the number of parameters) and dataset to achieve better generative ability, which…