Alert button
Picture for Yifan Gong

Yifan Gong

Alert button

NOTSOFAR-1 Challenge: New Datasets, Baseline, and Tasks for Distant Meeting Transcription

Jan 16, 2024
Alon Vinnikov, Amir Ivry, Aviv Hurvitz, Igor Abramovski, Sharon Koubi, Ilya Gurvich, Shai Pe`er, Xiong Xiao, Benjamin Martinez Elizalde, Naoyuki Kanda, Xiaofei Wang, Shalev Shaer, Stav Yagev, Yossi Asher, Sunit Sivasankaran, Yifan Gong, Min Tang, Huaming Wang, Eyal Krupka

Viaarxiv icon

E$^{2}$GAN: Efficient Training of Efficient GANs for Image-to-Image Translation

Jan 11, 2024
Yifan Gong, Zheng Zhan, Qing Jin, Yanyu Li, Yerlan Idelbayev, Xian Liu, Andrey Zharkov, Kfir Aberman, Sergey Tulyakov, Yanzhi Wang, Jian Ren

Viaarxiv icon

Value FULCRA: Mapping Large Language Models to the Multidimensional Spectrum of Basic Human Values

Nov 15, 2023
Jing Yao, Xiaoyuan Yi, Xiting Wang, Yifan Gong, Xing Xie

Figure 1 for Value FULCRA: Mapping Large Language Models to the Multidimensional Spectrum of Basic Human Values
Figure 2 for Value FULCRA: Mapping Large Language Models to the Multidimensional Spectrum of Basic Human Values
Figure 3 for Value FULCRA: Mapping Large Language Models to the Multidimensional Spectrum of Basic Human Values
Figure 4 for Value FULCRA: Mapping Large Language Models to the Multidimensional Spectrum of Basic Human Values
Viaarxiv icon

Hybrid Attention-based Encoder-decoder Model for Efficient Language Model Adaptation

Sep 14, 2023
Shaoshi Ling, Guoli Ye, Rui Zhao, Yifan Gong

Figure 1 for Hybrid Attention-based Encoder-decoder Model for Efficient Language Model Adaptation
Figure 2 for Hybrid Attention-based Encoder-decoder Model for Efficient Language Model Adaptation
Figure 3 for Hybrid Attention-based Encoder-decoder Model for Efficient Language Model Adaptation
Figure 4 for Hybrid Attention-based Encoder-decoder Model for Efficient Language Model Adaptation
Viaarxiv icon

Adapting Large Language Model with Speech for Fully Formatted End-to-End Speech Recognition

Aug 03, 2023
Shaoshi Ling, Yuxuan Hu, Shuangbei Qian, Guoli Ye, Yao Qian, Yifan Gong, Ed Lin, Michael Zeng

Figure 1 for Adapting Large Language Model with Speech for Fully Formatted End-to-End Speech Recognition
Figure 2 for Adapting Large Language Model with Speech for Fully Formatted End-to-End Speech Recognition
Figure 3 for Adapting Large Language Model with Speech for Fully Formatted End-to-End Speech Recognition
Figure 4 for Adapting Large Language Model with Speech for Fully Formatted End-to-End Speech Recognition
Viaarxiv icon

Pre-training End-to-end ASR Models with Augmented Speech Samples Queried by Text

Jul 30, 2023
Eric Sun, Jinyu Li, Jian Xue, Yifan Gong

Viaarxiv icon

DualHSIC: HSIC-Bottleneck and Alignment for Continual Learning

Apr 30, 2023
Zifeng Wang, Zheng Zhan, Yifan Gong, Yucai Shao, Stratis Ioannidis, Yanzhi Wang, Jennifer Dy

Figure 1 for DualHSIC: HSIC-Bottleneck and Alignment for Continual Learning
Figure 2 for DualHSIC: HSIC-Bottleneck and Alignment for Continual Learning
Figure 3 for DualHSIC: HSIC-Bottleneck and Alignment for Continual Learning
Figure 4 for DualHSIC: HSIC-Bottleneck and Alignment for Continual Learning
Viaarxiv icon

Can Adversarial Examples Be Parsed to Reveal Victim Model Information?

Mar 15, 2023
Yuguang Yao, Jiancheng Liu, Yifan Gong, Xiaoming Liu, Yanzhi Wang, Xue Lin, Sijia Liu

Figure 1 for Can Adversarial Examples Be Parsed to Reveal Victim Model Information?
Figure 2 for Can Adversarial Examples Be Parsed to Reveal Victim Model Information?
Figure 3 for Can Adversarial Examples Be Parsed to Reveal Victim Model Information?
Figure 4 for Can Adversarial Examples Be Parsed to Reveal Victim Model Information?
Viaarxiv icon

Building High-accuracy Multilingual ASR with Gated Language Experts and Curriculum Training

Mar 01, 2023
Eric Sun, Jinyu Li, Yuxuan Hu, Yimeng Zhu, Long Zhou, Jian Xue, Peidong Wang, Linquan Liu, Shujie Liu, Edward Lin, Yifan Gong

Figure 1 for Building High-accuracy Multilingual ASR with Gated Language Experts and Curriculum Training
Figure 2 for Building High-accuracy Multilingual ASR with Gated Language Experts and Curriculum Training
Figure 3 for Building High-accuracy Multilingual ASR with Gated Language Experts and Curriculum Training
Figure 4 for Building High-accuracy Multilingual ASR with Gated Language Experts and Curriculum Training
Viaarxiv icon