
phd @Tsinghua_Uni, intern @Apple, prev @SenseTime_AI, @MSFTResearch, @zhipu_ai
Joined November 2022
- Tweets10
- Following127
- Followers25
- Likes2
🚀 Can we build a VQ-VAE without training one?
Our ICML 2026 paper introduces Gaussian Quant (GQ):
✅ Train only a Gaussian VAE
✅ Convert it into a VQ-VAE without any additional training
✅ Random Gaussian noise codebook
Paper: arxiv.org/abs/2512.06609
Tongda Xu retweeted
Does GenAI create new knowledge? arxiv.org/abs/2602.06021 gives
* 1st explicit characterization of diffusion model's generalization
* more precise than offered by classical stat. learning theory
* systematic integration of various inductive biases (training+architecture+inference)
Introducing interpolated FID: an variant of reconstruction FID that is highly correlated to diffusion generation FID.
It is well known that VAE rFID is not correlated with diffusion gFID. We propose a simple variant that achieves correlation 0.9!
huggingface.co/papers/2603.0…
code: github.com/tongdaxu/Making-r…
paper: arxiv.org/abs/2603.05630
55
And to be appear in #ICLR2024
A year later we finally scale this idea up to 256^2 images. Though the technical approach is kind of different from DiffC. We use inversion to replace correlation communication to make a real codec.
Preprint: arxiv.org/abs/2401.08920
Code: github.com/tongdaxu/Idempote…
1
132
A year later we finally scale this idea up to 256^2 images. Though the technical approach is kind of different from DiffC. We use inversion to replace correlation communication to make a real codec.
Preprint: arxiv.org/abs/2401.08920
Code: github.com/tongdaxu/Idempote…
Replying to @lucastheis
We only require a single unconditionally trained diffusion model (used across bit-rates) where previous approaches use encoder and decoder transforms, entropy models, VGG, and adversarial models to achieve realism.








