📢🔥My team at NVIDIA Research is looking for Summer 2024 interns. Topics of interest are: 1⃣ Fundamental generative learning (diffusion, etc) 2⃣Gen AI for science (climate, biology, chemistry) 3⃣Image/Video/3D (generate, edit, manipulate) Apply via nvidia.wd5.myworkdayjobs.com/en-US/NVIDIAEx…

📢📢📢 thrilled to announce "𝟒𝐃-𝐟𝐲: 𝐓𝐞𝐱𝐭-𝐭𝐨-𝟒𝐃 𝐆𝐞𝐧𝐞𝐫𝐚𝐭𝐢𝐨𝐧 𝐔𝐬𝐢𝐧𝐠 𝐇𝐲𝐛𝐫𝐢𝐝 𝐒𝐜𝐨𝐫𝐞 𝐃𝐢𝐬𝐭𝐢𝐥𝐥𝐚𝐭𝐢𝐨𝐧 𝐒𝐚𝐦𝐩𝐥𝐢𝐧𝐠" sherwinbahmani.github.io/4dfy Way to start @sherwinbahmani 🎉 PhD co-advised with @DaveLindell at #UofT.

Super excited for the launch of Pika 1.0! I am extremely grateful to be working with such an amazing and talented team on this journey! ❤️ I am also very thankful for the support from our incredible investors, advisors, friends, and community members. We couldn't have achieved… twitter.com/i/web/status/1…

Excited to share WildFusion! WildFusion requires *only* unposed, single-view images for training but can generate novel instances from varying viewpoints. Project Page: katjaschwarz.github.io/wildfusion/ @seungkim0123 @JunGao33210520 @FidlerSanja @AutoVisionGroup @karsten_kreis

The Chosen One: Consistent Characters in Text-to-Image Diffusion Models Distills a representation that enables consistent depiction of the same character in novel contexts proj: omriavrahami.com/the-chosen-one/ abs: arxiv.org/abs/2311.10093

@CSProfKGD There should be a warning saying "don't try this at home"!

#ICLR2024 I am looking for emergency reviewers for a submission on neural network training dynamics and analysing feature learning patterns. Ping me by Nov 7 if you can and are willing to help🙏🙏🙏 (Yes this conference still has some theory submissions even given other hypes 😅

📢 Introducing Genie, a generative 3D foundation model that gives you 4x 3D models in 10 seconds! Try 🧞 on discord with: lumalabs.ai/genie #MadeWithGenie twitter.com/LumaLabsAI/sta…

@baaadas Congrats! This is amazing.

The cat 🐱 Peanut will be more famous lol twitter.com/karsten_kreis/…

📢 Booking your NeurIPS trip? Wondering the advancement of latent diffusion models, and how they have been applied to various domains? @karsten_kreis, @ArashVahdat and I will present the #NeurIPS2023 tutorial on "Latent Diffusion Models" on Mon, Dec 11. neurips2023-ldm-tutorial.github.io

@ajaydiv @RuiqiGao @karsten_kreis Thanks! Hopefully, we will deliver even better content at NeurIPS this year.

The diffusion tutorial dream team is back. Don't miss it. twitter.com/karsten_kreis/…

📢 Planning your NeurIPS'23 trip? Interested in *Latent* Diffusion Models? @RuiqiGao, @ArashVahdat and I will present the tutorial "Latent Diffusion Models: Is the Generative AI Revolution Happening in Latent Space?" Monday, Dec 11, New Orleans. neurips2023-ldm-tutorial.github.io (1/n)

📢 Would you like to build latent diffusion models for new problem domains? Wondering about theoretical and practical considerations! @RuiqiGao, @karsten_kreis and I will present the #NeurIPS2023 tutorial on "Latent Diffusion Models" on Monday, Dec 11. neurips2023-ldm-tutorial.github.io

@Azaliamirh Congratulations!

@MillionInt Lord of the models?

non-IID sampling can promote diversity / mitigate memorization in diffusion models! twitter.com/GabriCorso/sta…

Had a great TED AI Panel yesterday! My main point: LLMs need embodiment to unlock higher levels of intelligence. The stream of experience data through exploration & experiments will provide infinite tokens. Our current LLMs are the "pre-training checkpoints" for an embodied… twitter.com/i/web/status/1…

Today was my first day as a Research Scientist Intern at NVIDIA 🥳 Will be working with @ArashVahdat and the team on some pretty exciting research directions around generative models in the coming months 👌 Looking forward to it!

@giannis_daras Thrilled to have you with us and to work with you!

@alexjc @jm_alexia Wait! Don't you hold your mug that way?!

Generative AI + biomolecular structure is gaining traction again! It's been a year since we introduced NeuralPLexer arxiv.org/abs/2209.15171 to jointly predict and dynamically sample diverse compound(s)-protein complex structures. Glad to see works adopting relevant strategies🧵:

@tungnd_13 Not yet. We will know about our summer headcount in a couple of months.

@wandedob Thanks for letting me know. I'll ask the team to take a close look into your application.

📢🔥 My team at NVIDIA research is looking for candidates with a fundamental generative learning background (ideally) in one of these domains: - Gen AI for science (climate, chemistry, biology) - Gen AI for 3D data Apply via: bit.ly/3P9yxMC bit.ly/43ZgpZW

@fastml_extra But these are not the same: landing on the moon is orders of magnitude more expensive than running AI algorithms in production.

Our #CVPR2023 tutorial on diffusion models is now available publicly (with much better audio quality 🤣) Website: …3-tutorial-diffusion-models.github.io With: @chenlin_meng and @baaadas @CVPR

Honored to receive the PAMI Mark Everingham Prize with the COCO team at #ICCV2023. Mark Everingham's legacy with PASCAL dataset is a major inspiration for COCO. Grateful to work with brilliant minds early in my career. pc @chriswolfvision

🌉#Schrödinger #bridge is nice. It finds nonlinear diffusion w/ least kinetic energy, has strong theory, and recent works make it scalable. But does kinetic optimality suit all tasks? 📢 Introducing #GSBM, a new matching algo for generalized optimality! arxiv.org/abs/2310.02233