Picture for Kai Shen

Kai Shen

Ask Questions with Double Hints: Visual Question Generation with Answer-awareness and Region-reference

Add code
Jul 06, 2024
Viaarxiv icon

T2S-GPT: Dynamic Vector Quantization for Autoregressive Sign Language Production from Text

Add code
Jun 11, 2024
Figure 1 for T2S-GPT: Dynamic Vector Quantization for Autoregressive Sign Language Production from Text
Figure 2 for T2S-GPT: Dynamic Vector Quantization for Autoregressive Sign Language Production from Text
Figure 3 for T2S-GPT: Dynamic Vector Quantization for Autoregressive Sign Language Production from Text
Figure 4 for T2S-GPT: Dynamic Vector Quantization for Autoregressive Sign Language Production from Text
Viaarxiv icon

RALL-E: Robust Codec Language Modeling with Chain-of-Thought Prompting for Text-to-Speech Synthesis

Add code
Apr 06, 2024
Viaarxiv icon

NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models

Add code
Mar 05, 2024
Figure 1 for NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models
Figure 2 for NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models
Figure 3 for NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models
Figure 4 for NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models
Viaarxiv icon

PromptTTS 2: Describing and Generating Voices with Text Prompt

Add code
Sep 05, 2023
Figure 1 for PromptTTS 2: Describing and Generating Voices with Text Prompt
Figure 2 for PromptTTS 2: Describing and Generating Voices with Text Prompt
Figure 3 for PromptTTS 2: Describing and Generating Voices with Text Prompt
Figure 4 for PromptTTS 2: Describing and Generating Voices with Text Prompt
Viaarxiv icon

NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers

Add code
May 04, 2023
Figure 1 for NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers
Figure 2 for NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers
Figure 3 for NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers
Figure 4 for NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers
Viaarxiv icon

Deep Learning Predicts Prevalent and Incident Parkinson's Disease From UK Biobank Fundus Imaging

Add code
Feb 17, 2023
Figure 1 for Deep Learning Predicts Prevalent and Incident Parkinson's Disease From UK Biobank Fundus Imaging
Figure 2 for Deep Learning Predicts Prevalent and Incident Parkinson's Disease From UK Biobank Fundus Imaging
Figure 3 for Deep Learning Predicts Prevalent and Incident Parkinson's Disease From UK Biobank Fundus Imaging
Figure 4 for Deep Learning Predicts Prevalent and Incident Parkinson's Disease From UK Biobank Fundus Imaging
Viaarxiv icon

A Study on ReLU and Softmax in Transformer

Add code
Feb 13, 2023
Figure 1 for A Study on ReLU and Softmax in Transformer
Figure 2 for A Study on ReLU and Softmax in Transformer
Figure 3 for A Study on ReLU and Softmax in Transformer
Figure 4 for A Study on ReLU and Softmax in Transformer
Viaarxiv icon

Mask the Correct Tokens: An Embarrassingly Simple Approach for Error Correction

Add code
Nov 23, 2022
Figure 1 for Mask the Correct Tokens: An Embarrassingly Simple Approach for Error Correction
Figure 2 for Mask the Correct Tokens: An Embarrassingly Simple Approach for Error Correction
Figure 3 for Mask the Correct Tokens: An Embarrassingly Simple Approach for Error Correction
Figure 4 for Mask the Correct Tokens: An Embarrassingly Simple Approach for Error Correction
Viaarxiv icon

Scenario-based Multi-product Advertising Copywriting Generation for E-Commerce

Add code
May 21, 2022
Figure 1 for Scenario-based Multi-product Advertising Copywriting Generation for E-Commerce
Figure 2 for Scenario-based Multi-product Advertising Copywriting Generation for E-Commerce
Figure 3 for Scenario-based Multi-product Advertising Copywriting Generation for E-Commerce
Figure 4 for Scenario-based Multi-product Advertising Copywriting Generation for E-Commerce
Viaarxiv icon