Lab Notes

Research is Magic

Priorities

•
Voice AI
•
Multimodal LLM
•
Diffusion
•
Evaluation

Papers

My Publications
5
R
Date
Paper Title
Rating
Authors
Field
Review Status
2026
RobustSpeechFlow
Open
Todo
2024
DualSpeech
Open
Completed
2023
NANSY++
Open
Todo
2021
GANSpeech
Open
Todo
2020
VocGAN
Open
Todo
Diffusion
5
R
Date
Paper Title
Rating
Authors
Field
Review Status
2026
Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis
Open
4 - Good
Hila Chefer
Flow Matching
SSL
In Progress
2024
Diffusion Forcing
Open
Todo
2025
No other representation component is needed: Diffusion transformers can provide representation guidance by themselves
Open
4 - Good
Dengyang Jiang, Mengmeng Wang
Diffusion
Todo
2026
SRA 2: Variational Autoencoder Self-Representation Alignment for Efficient Diffusion Training
Open
4 - Good
Mengmeng Wang
Diffusion
Todo
2025
Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think
Open
5 - Excellent
Sihyun Yu
Diffusion
Completed
Speech & Audio
10
R
Date
Paper Title
Rating
Authors
Field
Review Status
ETC
3
R
Date
Paper Title
Rating
Authors
Field
Review Status
2017
Attention Is All You Need
Open
6 - Outstanding
Vaswani et al.
Natural Language Processing
Completed
2013
Playing Atari with Deep Reinforcement Learning
Open
4 - Good
Mnih et al.
Reinforcement Learning
In Progress
2016
Deep Residual Learning for Image Recognition
Open
6 - Outstanding
He, Zhang, Ren, Sun
Computer Vision
Completed

Paper Gallery

My Publications
Speech & Audio
Diffusion
LLM
ETC