Xianghao Kong

On the Job Market📍Santa Clara | PhDone @UCR_CSE | interpretability, alignment, compositionality of diffusion models | EX - @AdobeFirefly, @SonyAI_global

[Xianghao Kong @xk_theo7]

Most diffusion research today asks: How can we sample faster?

But I think another question is equally important: Are we training diffusion models in the right way?

https://t.co/WYHNXJamhi

[Xianghao Kong @xk_theo7]

@mo_norouzi physically grounded image model🤣🤣

[Xianghao Kong @xk_theo7]

This is my first time turning some of my research thoughts into a blog post, so it may contain errors or unclear arguments. Any suggestions, comments, or feedback would be greatly appreciated🙌

[Xianghao Kong @xk_theo7]

Most diffusion research today asks: How can we sample faster?

But I think another question is equally important: Are we training diffusion models in the right way?

https://t.co/WYHNXJamhi

[Xianghao Kong @xk_theo7]

This may matter even more for recurrent diffusion and interactive generative models, where small errors can accumulate over long-term rollouts.

[Zyphra @ZyphraAI]

Today we're releasing ZAYA1-74B-Preview, a major milestone in scaling pretraining on @AMD.

ZAYA1-74B-Preview is a 4B active / 74B total MoE.

This preview model is a strong pre-RL base checkpoint. The final post-trained reasoning model is coming soon. 🧵

[Yunong Liu@CVPR @yunongliu1]

Really excited to see Uni-1 out in the world 🔥Our first unified model.

The range of things this model can do is wild: image-to-~100 styles, manga generation, multi-ref with strong identity preservation, temporal storytelling, sketch-to-image, spatial reasoning, multilingual infographics, layering… the capability range is honestly unreal. this is just the start 🫡 check out the blog to learn more https://t.co/B8Nedl86Dk

Proud of the team and what we’re building at @LumaLabsAI 🚀

[Xianghao Kong @xk_theo7]

@hudsonyeoce Cool cool! We’ve mastered alignment for nouns in image/video models, but verbs (or more abstract terms) are the real challenge in video. Seeing this kind of motion control proves Runway’s cracking the code on abstract concepts🔥

[Xianghao Kong @xk_theo7]

🤯💥

[karim_yourself @karim_yourself]

Jujutsu Kaisen Live Action.

[Xianghao Kong @xk_theo7]

I’m currently in transit to San Diego for NeurIPS. If you’re also killing time, feel free to check out a 2-minute-30-second horror sci-fi short film Michael and I recently created. We’d love any comments or likes:
https://t.co/MW9h7PIHah

Looking forward to catching up at the venue! 🎥

[Xianghao Kong @xk_theo7]

Why must robots be human-shaped? Bringing impossible creatures into the real world can create just as beautiful an emotional bond ❤️

[Disneyland Paris EN @DisneyParis_EN]

It's official! From 29 March 2026 you'll be able to discover World of Frozen and lots of other experiences at Disney Adventure World! 🤩

[Xianghao Kong @xk_theo7]

I feel the debate shouldn’t only be about whether DiT is effective, but also about how information preservation is the key to accelerating diffusion training. Our MicroDiT (https://t.co/uRWJRzAJRp) paper showed this: by letting masked token info mix into unmasked ones, we can cut down a lot of tokens with only minor performance loss.

Interestingly, two months ago, when I caught up with @StefanABaumann at #CVPR, we discussed how TREAD and MicroDiT are conceptually similar from info perspective. Maybe it’s time to look at diffusion through an information-theoretic lens: from post-training (for the better alignment) to latent space curation, I believe this could lead to some really exciting discoveries!

[サメQCU @sameQCU]

bros, DiT is wrong.
it's mathematically wrong.
it's formally wrong. there is something wrong with it

[Xianghao Kong @xk_theo7]

Shout out for Doji!

[Doji @doji_com]

Introducing Look Studio.

Style looks from scratch with 1M+ products from designer brands - including shoes, multiple layers and more.

Reply for an invite.

[Xianghao Kong @xk_theo7]

@jfischoff Yura Borisov?😂

[Xianghao Kong @xk_theo7]

@sleenyre Loving the post-training insights 👏

[Reka @RekaAILabs]

Excited to introduce Reka Vision, an agentic visual understanding and search platform. Transform your unstructured multimodal data into insights and actions.

[Midjourney @midjourney]

Introducing our V1 Video Model. It's fun, easy, and beautiful. Available at 10$/month, it's the first video model for *everyone* and it's available now.

[Özgür Kara @ozgurkara99]

+ @cveu_workshop starting at 1:00 PM, 207 A-D.

[Xianghao Kong @xk_theo7]

Heading to Nashville 🎸 for @CVPR (06/11 - 06/16)!

Always excited to catch up with old friends and make new connections. Let’s grab a coffee ☕️ or chat about diffusion models, post-training, or just life!

#CVPR2025 #Diffusion #GenerativeAI #Nashville