21 citations · 24 across the 7 of their papers we have counts for
8 papers
Routing Should Pay for Itself: Sparse Supervision for Economical LLM Routing
Guannan Lai, Gelin Bian, Hao-Xuan Ma +5
Large language model (LLM) routing reduces serving cost by assigning each query to an appropriate model while preserving response quality. Learning such a router, however, often re…
Learnware of Language Models: Specialized Small Language Models Can Do Big
Zhi-Hao Tan, Zi-Chen Zhao, Hao-Yu Shi +4
The learnware paradigm offers a novel approach to machine learning by enabling users to reuse a set of well-trained models for tasks beyond the models' original purposes. It elimin…
Beimingwu: A Learnware Dock System
Zhi-Hao Tan, Jian-Dong Liu, Xiao-Dong Bi +7
The learnware paradigm proposed by Zhou [2016] aims to enable users to reuse numerous existing well-trained models instead of building machine learning models from scratch, with th…
Matrix Information Theory for Self-Supervised Learning
Yifan Zhang, Zhiquan Tan, Jingqin Yang +2
The maximum entropy encoding framework provides a unified perspective for many non-contrastive learning methods like SimSiam, Barlow Twins, and MEC. Inspired by this framework, we…
RelationMatch: Matching In-batch Relationships for Semi-supervised Learning
Yifan Zhang, Jingqin Yang, Zhiquan Tan +1
Semi-supervised learning has emerged as a pivotal approach for leveraging scarce labeled data alongside abundant unlabeled data. Despite significant progress, prevailing SSL method…
SEAL: Simultaneous Label Hierarchy Exploration And Learning
Zhiquan Tan, Zihao Wang, Yifan Zhang
Label hierarchy is an important source of external knowledge that can enhance classification performance. However, most existing methods rely on predefined label hierarchies that m…
Contrastive Learning Is Spectral Clustering On Similarity Graph
Zhiquan Tan, Yifan Zhang, Jingqin Yang +1
Contrastive learning is a powerful self-supervised learning method, but we have a limited theoretical understanding of how it works and why it works. In this paper, we prove that c…
Learnware: Small Models Do Big
Zhi-Hua Zhou, Zhi-Hao Tan
There are complaints about current machine learning techniques such as the requirement of a huge amount of training data and proficient training skills, the difficulty of continual…