Picture for Qingkai Fang

Qingkai Fang

BayLing 2: A Multilingual Large Language Model with Efficient Language Alignment

Add code
Nov 25, 2024
Viaarxiv icon

LLaMA-Omni: Seamless Speech Interaction with Large Language Models

Add code
Sep 10, 2024
Figure 1 for LLaMA-Omni: Seamless Speech Interaction with Large Language Models
Figure 2 for LLaMA-Omni: Seamless Speech Interaction with Large Language Models
Figure 3 for LLaMA-Omni: Seamless Speech Interaction with Large Language Models
Figure 4 for LLaMA-Omni: Seamless Speech Interaction with Large Language Models
Viaarxiv icon

Can We Achieve High-quality Direct Speech-to-Speech Translation without Parallel Speech Data?

Add code
Jun 11, 2024
Viaarxiv icon

CTC-based Non-autoregressive Textless Speech-to-Speech Translation

Add code
Jun 11, 2024
Viaarxiv icon

A Non-autoregressive Generation Framework for End-to-End Simultaneous Speech-to-Any Translation

Add code
Jun 11, 2024
Viaarxiv icon

StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learning

Add code
Jun 05, 2024
Viaarxiv icon

Bridging the Gap between Synthetic and Authentic Images for Multimodal Machine Translation

Add code
Oct 20, 2023
Viaarxiv icon

DASpeech: Directed Acyclic Transformer for Fast and High-quality Speech-to-Speech Translation

Add code
Oct 11, 2023
Viaarxiv icon

BayLing: Bridging Cross-lingual Alignment and Instruction Following through Interactive Translation for Large Language Models

Add code
Jun 21, 2023
Viaarxiv icon

CMOT: Cross-modal Mixup via Optimal Transport for Speech Translation

Add code
May 25, 2023
Viaarxiv icon