🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

📢 We have a few poster places to grab at the Workshop on Uncertainty Quantification for Computer Vision #CVPR2025 If you have a cool recent work on uncertainty or reliability to talk about, just nominate yourself to join our poster session #cvpr2025 uncertainty-cv.github.io/2025/

When reviewer #2 asked for latent space interpolation 😂

Diffusion language models go multimodal! Particularly impressive to see the speed and quality results on visual reasoning benchmarks. Great work led by my students Shufan (Jack) Li, Hritik Bansal and amazing collaborators.

I'm hiring! Are you a technical, senior product leader passionate about driving the next generation of biomolecular simulation software? Then come and join our team! Apply here: bit.ly/pm-bionemo-sim…

🔥 How can we build hybrid auto-regressive & diffusion LLMs while keeping the best of both worlds?

🛟 Reliable & reliability researchers #CVPR2025! Join our workshop on Uncertainty Quantification for Computer Vision next week! We have a super lineup of speakers (from self-driving to LLMs) and cool posters. 🗓️ Day: Wed, Jun 11 📌Room: 102 B #CVPR2025 #UNCV2025

Join us for a full-day tutorial on Scalable Generative Models in Computer Vision at #CVPR2025 in Nashville, on Wednesday, June 11, from 9:00 AM to 5:00 PM in Room 202 B! 👉 We are honored to have Saining Xie, Deepti, Jiatao Gu, Kaiming He, Arash Vahdat, and Sherry Yang to

Refreshing and entertaining talk by Arash Vahdat ✈️ #CVPR2025 on Rare yet real: generative modeling beyond the modes, dealing with weather data. Former attendees of his great diffusion tutorial should know what I mean #uncv2025 #cvpr2025

And the #uncv2025 is now royally treated with a mini-tutorial on diffusion and flow matching by Arash Vahdat ✈️ #CVPR2025 himself #cvpr2025 Really, do check his great tutorials at past CVPR and NeurIPS editions

Arash Vahdat ✈️ #CVPR2025 Heavy-tailed diffusion models: lines of code to improve the ability of your diffusion model to handle extreme events in heavy-tailed distributions. ll;dr: replace you gaussian distribution with a tuned t-student one. Arash Vahdat ✈️ #CVPR2025 #uncv2025 #cvpr2025

For the generative modeling folks, check out this lineup 👀 Happening TODAY! #CVPR2025 Workshop on Visual Generative Modeling: What’s After Diffusion?

Loved the talk Arash Vahdat ✈️ #CVPR2025, slides too 😉

Vision or no vision great talk Ricky T. Q. Chen! 😉

🚨 “The Diffusion Duality” is out! International Conference on Minority Languages ⚡️ Few-step generation in discrete diffusion language models by exploiting the underlying Gaussian diffusion. 🦾Beats AR on 3/7 zero-shot likelihood benchmarks. 📄 Paper: arxiv.org/abs/2506.10892 💻 Code: github.com/s-sahoo/duo 🧠

This is 🔥🔥🔥 Subham and the company build a nice connection between Gaussian diffusion and discrete diffusion, enabling various capabilities like faster training and continuous relaxation of discrete variables.

The slides for my CVPR talks are now available at latentspace.cc