Bowei Chen

Foundation Model @Tesla, prev Ph.D UW, MS CMU.

[Bowei Chen @bowei_chen_19]

We found that visual foundation encoder can be aligned to serve as tokenizers for latent diffusion models in image generation!

Our new paper introduces a new tokenizer training paradigm that produces a semantically rich latent space, improving diffusion model performance🚀🚀.

[Hansheng Chen @HanshengCh]

New paper: AsymFlow🔥

JiT x0-prediction is not enough for pixel generation. Better keep velocity in a low-rank subspace:

- 1.57 FID on ImageNet (best pixel flow model)
- Finetunes FLUX.2 klein into pixel space, beats the original on HPSv3/DPG/GenEval (#1 overall on HPSv3)

1/7

[Bowei Chen @bowei_chen_19]

@vivjay30 @sesame Amazing!

[Bowei Chen @bowei_chen_19]

Nice blog, highly recommend!

[Kieran Didi @DidiKieran]

Too many REPA / RAE / representation alignment papers lately?
I was lost too, so I wrote a blog post that organizes the space into phases and zooms in on what actually matters for general/molecular ML.
Curious what folks think - link below!

🔗 Blog: https://t.co/6aJf8DCWTa

[Jingwei Ma @JingweiMa2]

Excited to present UltraZoom at SIGGRAPH Asia next Tuesday (Dec.16)!

UltraZoom converts sparse phone captures of an object into a single gigapixel-resolution image that you can seamlessly explore. Threads below.

Website: https://t.co/XinzBbkEXH
Paper: https://t.co/Ed26gMUaqZ

[Hansheng Chen @HanshengCh]

Excited to announce a new track of accelerating Generative AI:

pi-Flow: Policy-Based Few-Step Generation via Imitation Distillation
https://t.co/6ro55E1XGP

Distill 20B flow models now using just an L2 loss via imitation learning for SOTA diversity and teacher-aligned quality.

[Bowei Chen @bowei_chen_19]

The Representation Autoencoders (RAE) by @sainingxie's team is fascinating — a brilliant demonstration that high-dimensional diffusion is indeed feasible.

In our latest work on semantic encoders, we align a pretrained foundation encoder (e.g., DINOv2) as a visual tokenizer, achieving better reconstruction quality while preserving semantic consistency. Instead of freezing the encoder, we introduce a semantics-preserving fine-tuning strategy that significantly improves reconstruction quality.

I can see great potential in combining RAE with our approach to build semantically rich tokenizers with large channel dimension and strong reconstruction fidelity.

[Bowei Chen @bowei_chen_19]

We found that visual foundation encoder can be aligned to serve as tokenizers for latent diffusion models in image generation!

Our new paper introduces a new tokenizer training paradigm that produces a semantically rich latent space, improving diffusion model performance🚀🚀.

[Bowei Chen @bowei_chen_19]

@SwayStar123 @sainingxie Yes! I can see great potential in combining RAE with our approach to build semantically rich tokenizers with large channel dimension and strong reconstruction fidelity (we fine-tuned the encoder for better reconstruction).

[Bowei Chen @bowei_chen_19]

@Jacoed Yes, this is shown in both our work and previous work like VA-VAE.

[Bowei Chen @bowei_chen_19]

We found that visual foundation encoder can be aligned to serve as tokenizers for latent diffusion models in image generation!

Our new paper introduces a new tokenizer training paradigm that produces a semantically rich latent space, improving diffusion model performance🚀🚀.

[Bowei Chen @bowei_chen_19]

We hope our findings inspire a rethinking of tokenizer design in generative modeling.

🙏 Huge shoutout to my amazing co-authors and collaborators @KaiZhang9546,@Sai__Bi,@HaoTan5,@zhanghesprinter ,@tianyuanzhang99 ,@zhengqi_li, @bitxiong,@jianming_zhang_.

[9/N]

[Bowei Chen @bowei_chen_19]

On LAION 2B dataset, we train a text-to-image diffusion model on our tokenizer, which converges faster and surpasses the FLUX-VAE baseline.

Check out more details and results in our paper!

[8/N]

[Bowei Chen @bowei_chen_19]

@somebobcat8327 Thanks!

[Bowei Chen @bowei_chen_19]

#CVPR2024 Arm-captured selfies only capture your partial body. Instead, what if you could capture a full-body photo that someone else would take of you in the scene?

We present Total Selfie, which generates full-body selfies from photographs originally taken at arms length. 1/n