Picture for Wayne Xiong

Wayne Xiong

PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling

Add code
Jun 04, 2024
Viaarxiv icon

Interactive Editing for Text Summarization

Add code
Jun 05, 2023
Figure 1 for Interactive Editing for Text Summarization
Figure 2 for Interactive Editing for Text Summarization
Figure 3 for Interactive Editing for Text Summarization
Figure 4 for Interactive Editing for Text Summarization
Viaarxiv icon

Momentum Calibration for Text Generation

Add code
Dec 08, 2022
Figure 1 for Momentum Calibration for Text Generation
Figure 2 for Momentum Calibration for Text Generation
Figure 3 for Momentum Calibration for Text Generation
Figure 4 for Momentum Calibration for Text Generation
Viaarxiv icon

Z-Code++: A Pre-trained Language Model Optimized for Abstractive Summarization

Add code
Aug 21, 2022
Figure 1 for Z-Code++: A Pre-trained Language Model Optimized for Abstractive Summarization
Figure 2 for Z-Code++: A Pre-trained Language Model Optimized for Abstractive Summarization
Figure 3 for Z-Code++: A Pre-trained Language Model Optimized for Abstractive Summarization
Figure 4 for Z-Code++: A Pre-trained Language Model Optimized for Abstractive Summarization
Viaarxiv icon

Advances in Online Audio-Visual Meeting Transcription

Add code
Dec 10, 2019
Figure 1 for Advances in Online Audio-Visual Meeting Transcription
Figure 2 for Advances in Online Audio-Visual Meeting Transcription
Figure 3 for Advances in Online Audio-Visual Meeting Transcription
Figure 4 for Advances in Online Audio-Visual Meeting Transcription
Viaarxiv icon

Progressive Joint Modeling in Unsupervised Single-channel Overlapped Speech Recognition

Add code
Oct 20, 2017
Figure 1 for Progressive Joint Modeling in Unsupervised Single-channel Overlapped Speech Recognition
Figure 2 for Progressive Joint Modeling in Unsupervised Single-channel Overlapped Speech Recognition
Figure 3 for Progressive Joint Modeling in Unsupervised Single-channel Overlapped Speech Recognition
Figure 4 for Progressive Joint Modeling in Unsupervised Single-channel Overlapped Speech Recognition
Viaarxiv icon