activity
20152023
most citedSpectral Temporal Graph Neural Network for Multivariate Time-series Forecasting

116 citations · 797 across the 52 of their papers we have counts for

collaborators
Showing 2023Show all

10 papers · 1 filter

cs.LG2023★ 19 cited

Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time

Zichang Liu, Jue Wang, Tri Dao +8

Large language models (LLMs) with hundreds of billions of parameters have sparked a new wave of exciting AI applications. However, they are computationally expensive at inference t…

cs.DC2023★ 24 cited

Towards General and Efficient Online Tuning for Spark

Yang Li, Huaijun Jiang, Yu Shen +8

The distributed data analytic system -- Spark is a common choice for processing massive volumes of heterogeneous data, while it is challenging to tune its parameters to achieve hig…

cs.LG2023

BenchTemp: A General Benchmark for Evaluating Temporal Graph Neural Networks

Qiang Huang, Jiawei Jiang, Xi Susie Rao +10

To handle graphs in which features or connectivities are evolving over time, a series of temporal graph neural networks (TGNNs) have been proposed. Despite the success of these TGN…

cs.CV2023

Unsupervised Prototype Adapter for Vision-Language Models

Yi Zhang, Ce Zhang, Xueting Hu +1

Recently, large-scale pre-trained vision-language models (e.g. CLIP and ALIGN) have demonstrated remarkable effectiveness in acquiring transferable visual representations. To lever…

cs.CL2023★ 4 cited

Skill-it! A Data-Driven Skills Framework for Understanding and Training Language Models

Mayee F. Chen, Nicholas Roberts, Kush Bhatia +4

The quality of training data impacts the performance of pre-trained large language models (LMs). Given a fixed budget of tokens, we study how to best select data that leads to good…

cs.LG2023

Improving Retrieval-Augmented Large Language Models via Data Importance Learning

Xiaozhong Lyu, Stefan Grafberger, Samantha Biegel +4

Retrieval augmentation enables large language models to take advantage of external knowledge, for example on tasks like question answering and data imputation. However, the perform…