Picture for Zhifeng Kong

Zhifeng Kong

Synthio: Augmenting Small-Scale Audio Classification Datasets with Synthetic Data

Add code
Oct 02, 2024
Viaarxiv icon

A Geometry-Aware Algorithm to Learn Hierarchical Embeddings in Hyperbolic Space

Add code
Jul 23, 2024
Viaarxiv icon

Improving Text-To-Audio Models with Synthetic Captions

Add code
Jun 18, 2024
Viaarxiv icon

Audio Dialogues: Dialogues dataset for audio and music understanding

Add code
Apr 11, 2024
Viaarxiv icon

Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities

Add code
Feb 02, 2024
Viaarxiv icon

CleanUNet 2: A Hybrid Speech Denoising Model on Waveform and Spectrogram

Add code
Sep 12, 2023
Viaarxiv icon

Data Redaction from Conditional Generative Models

Add code
May 18, 2023
Viaarxiv icon

Can Membership Inferencing be Refuted?

Add code
Mar 08, 2023
Viaarxiv icon

Approximate Data Deletion in Generative Models

Add code
Jun 29, 2022
Figure 1 for Approximate Data Deletion in Generative Models
Figure 2 for Approximate Data Deletion in Generative Models
Figure 3 for Approximate Data Deletion in Generative Models
Figure 4 for Approximate Data Deletion in Generative Models
Viaarxiv icon

Forgetting Data from Pre-trained GANs

Add code
Jun 29, 2022
Figure 1 for Forgetting Data from Pre-trained GANs
Figure 2 for Forgetting Data from Pre-trained GANs
Figure 3 for Forgetting Data from Pre-trained GANs
Figure 4 for Forgetting Data from Pre-trained GANs
Viaarxiv icon