Introducing REPA! We show that learning high-quality representations in diffusion transformers is crucial for boosting generation performance. With REPA, we speed up SiT training by 17.5x (without CFG) and achieve state-of-the-art FID = 1.42 using CFG with the guidance interval.

Introducing Representation Autoencoders (RAE)! We revisit the latent space of Diffusion Transformers, replacing VAE with RAE: pretrained representation encoders (DINOv2, SigLIP2) paired with trained ViT decoders. (1/n)

three years ago, DiT replaced the legacy unet with a transformer-based denoising backbone. we knew the bulky VAEs would be the next to go -- we just waited until we could do it right. today, we introduce Representation Autoencoders (RAE). >> Retire VAEs. Use RAEs. 👇(1/n)

Excited to introduce DiffuseNNX, a comprehensive JAX/Flax NNX-based library for diffusion and flow matching! It supports multiple diffusion / flow-matching frameworks, Autoencoders, DiT variants, and sampling algorithms. Repo: https://t.co/zOcA6nyrcM Delve into details below!

I spent the past month reimplementing DeepMind’s Genie 3 world model from scratch Ended up making TinyWorlds, a 3M parameter world model capable of generating playable game environments demo below + everything I learned in thread (full repo at the end)👇🏼

I know op is click-baiting, but let me bite... fwiw every researcher’s DREAM is to find out their architecture is wrong. If it’s never wrong, that’s a bigger problem. we try to break DiT every day w/ SiT, REPA, REPA-E etc. but you gotta form hypotheses, run experiments, test, not

Anyone knows adam?

Enhancing Motion Dynamics of Image-to-Video Models via Adaptive Low-Pass Guidance

🚀 Come check our poster at ICML @genbio_workshop! We show that pretrained MLIPs can accelerate training of Boltzmann emulators — by aligning their internal representations. Coauthors @LucasPinede, @junonam_, @RGBLabMIT (1/n)

I’ve wondered why I2V models tend to generate more static videos compared to their T2V counterparts. This project, led by @june_suk_choi, provides an analysis of this phenomenon and introduces a very simple (yet effective) fix to address it! Excited to have been part of this

@joserf28323 @CVPR @ICCVConference @nyuniversity Thanks for bringing this to my attention. I honestly wasn’t aware of the situation until the recent posts started going viral. I would never encourage my students to do anything like this—if I were serving as an Area Chair, any paper with this kind of prompt would be

Excited to share MDMs for molecule generation led by @bellaseo72 and @taewonKKK!

now the code is up here:

We introduce LiveCodeBench Pro. Models like o3-high, o4-mini, and Gemini 2.5 Pro score 0% on hard competitive programming problems.

The slides for my CVPR talks are now available at

#CVPR2025 PAMI-TC awards

Padding in our non-AR sequence models? Yuck. 🙅 👉 Instead of unmasking, our new work *Edit Flows* perform iterative refinements via position-relative inserts and deletes, operations naturally suited for variable-length sequence generation. Easily better than using mask tokens.

Had a great time at this CVPR community-building workshop---lots of fun discussions and some really important insights for early-career researchers. I also gave a talk on "Research as an Infinite Game." Here are the slides: https://t.co/T5FZS1A3CT

Join us for a full-day tutorial on Scalable Generative Models in Computer Vision at @CVPR in Nashville, on Wednesday, June 11, from 9:00 AM to 5:00 PM in Room 202 B! 👉 We are honored to have @sainingxie, @deeptigp, @thoma_gu, Kaiming He, @ArashVahdat, and @sherryyangML to

Excited to present FastTD3: a simple, fast, and capable off-policy RL algorithm for humanoid control -- with an open-source code to run your own humanoid RL experiments in no time! Thread below 🧵

Indeed. For text-to-image, @xichen_pan had a great summary supporting this decoupled design philosophy: "Render unto diffusion what is generative, and unto LLMs what is understanding." We've repeatedly observed that diffusion gradients can negatively impact the backbone repr.