activity
20242026
most citedRetrieval Augmented Time Series Forecasting

2 citations · 3 across the 16 of their papers we have counts for

collaborators
Showing 2024Show all

12 papers · 1 filter

cs.LG2024

Selective Attention: Enhancing Transformer through Principled Context Control

Xuechen Zhang, Xiangyu Chang, Mingchen Li +3

The attention mechanism within the transformer architecture enables the model to weigh and combine tokens based on their relevance to the query. While self-attention has enjoyed ma…

cs.CL2024

Efficient Contextual LLM Cascades through Budget-Constrained Policy Learning

Xuechen Zhang, Zijian Huang, Ege Onur Taga +3

Recent successes in natural language processing have led to the proliferation of large language models (LLMs) by multiple providers. Each LLM offering has different inference accur…

cs.LG2024

CONTRAST: Continual Multi-source Adaptation to Dynamic Distributions

Sk Miraj Ahmed, Fahim Faisal Niloy, Xiangyu Chang +3

Adapting to dynamic data distributions is a practical yet challenging task. One effective strategy is to use a model ensemble, which leverages the diverse expertise of different mo…

cs.LG2024

Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition

Zheyang Xiong, Ziyang Cai, John Cooper +11

Large Language Models (LLMs) have demonstrated remarkable in-context learning (ICL) capabilities. In this study, we explore a surprising phenomenon related to ICL: LLMs can perform…

cs.LG2024

Fine-grained Analysis of In-context Linear Estimation: Data, Architecture, and Beyond

Yingcong Li, Ankit Singh Rawat, Samet Oymak

Recent research has shown that Transformers with linear attention are capable of in-context learning (ICL) by implementing a linear estimator through gradient descent steps. Howeve…

cs.LG2024

On the Power of Convolution Augmented Transformer

Mingchen Li, Xuechen Zhang, Yixiao Huang +1

The transformer architecture has catalyzed revolutionary advances in language modeling. However, recent architectural recipes, such as state-space models, have bridged the performa…