no code implementations • 15 Feb 2024 • Kang He, Yinghan Long, Kaushik Roy
Prompt learning is susceptible to intrinsic bias present in pre-trained language models (LMs), resulting in sub-optimal performance of prompt-based zero/few-shot learning.
1 code implementation • 24 May 2023 • Yinghan Long, Sayeed Shafayet Chowdhury, Kaushik Roy
The segmented attention and lightweight RAF neurons ensure the efficiency of the proposed transformer.
Ranked #1 on Text Summarization on MediaSum
no code implementations • 14 Sep 2021 • Yinghan Long, Indranil Chakraborty, Gopalakrishnan Srinivasan, Kaushik Roy
Only data with high probabilities of belonging to hard classes would be sent to the extension block for prediction.
no code implementations • 21 May 2020 • Yinghan Long, Indranil Chakraborty, Kaushik Roy
The proposed network can be deployed in a distributed manner, consisting of quantized layers and early exits at the edge and full-precision layers on the cloud.