most citedA Graph-Theoretic Framework for Understanding Open-World Semi-Supervised Learning

4 citations · 9 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CL20241 cited

Do Large Language Models Have Compositional Ability? An Investigation into Limitations and Scalability

Zhuoyan Xu, Zhenmei Shi, Yingyu Liang

Large language models (LLMs) have emerged as powerful tools for many AI problems and exhibit remarkable in-context learning (ICL) capabilities. Compositional ability, solving unsee…

cs.LG20241 cited

Towards Few-Shot Adaptation of Foundation Models via Multitask Finetuning

Zhuoyan Xu, Zhenmei Shi, Junyi Wei +3

Foundation models have emerged as a powerful tool for many AI problems. Despite the tremendous success of foundation models, effective adaptation to new tasks, particularly those w…

cs.LG20234 cited

A Graph-Theoretic Framework for Understanding Open-World Semi-Supervised Learning

Yiyou Sun, Zhenmei Shi, Yixuan Li

Open-world semi-supervised learning aims at inferring both known and novel classes in unlabeled data, by harnessing prior knowledge from a labeled set with known classes. Despite i…

cs.LG2023

Provable Guarantees for Neural Networks via Gradient Feature Learning

Zhenmei Shi, Junyi Wei, Yingyu Liang

Neural networks have achieved remarkable empirical performance, while the current theoretical analysis is not adequate for understanding their success, e.g., the Neural Tangent Ker…

cs.LG20232 cited

When and How Does Known Class Help Discover Unknown Ones? Provable Understanding Through Spectral Analysis

Yiyou Sun, Zhenmei Shi, Yingyu Liang +1

Novel Class Discovery (NCD) aims at inferring novel classes in an unlabeled set by leveraging prior knowledge from a labeled set with known classes. Despite its importance, there i…

cs.LG20231 cited

The Trade-off between Universality and Label Efficiency of Representations from Contrastive Learning

Zhenmei Shi, Jiefeng Chen, Kunyang Li +4

Pre-training representations (a.k.a. foundation models) has recently become a prevalent learning paradigm, where one first pre-trains a representation using large-scale unlabeled d…