Jay Whang

Happy to have been part of the effort that ultimately led to Nano Banana Pro🍌 It's a SOTA image generator, go give it a try (in your native language)!

Oh to be a duck sipping on boba on a cozy day...

More fun with multi-turn image editing! Fixing my failed attempt at latte art with Gemini 2.0 ☕️

Happy to share what's been keeping me busy this year! With native multimodal output, I interactively turned my duck crochet into a mallard using Gemini 2.0 🦆

Researchers from our NSF Institute on the Foundations of Machine Learning (IFML) win 2 outstanding paper awards at NeurIPS 2022 (after winning 2/5 awards in NeurIPS 2021 also)! Congratulations @jaywhang_ @lschmidt3 (1/n) The first...

Two important breakthroughs from @GoogleAI this week - Imagen Video, a new text-conditioned video diffusion model that generates 1280x768 24fps HD video. And Phenaki, a model which generates long coherent videos for a sequence of text prompts. imagen.research.google/video/

Really excited to release our latest work, Imagen Video! Happy to see the explosive growth of generative models. #imagenvideo imagen.research.google/video

Check our new CVPR paper: Blind image deblurring that can produce diverse samples. Obtained by the combination of a deterministic and a stochastic model.

"Deblurring via Stochastic Refinement" to appear in CVPR 2022 Decouples a conditional diffusion model into deterministic+stochastic parts, that are then trained jointly & comprise a single stochastic deblurring model w/ @jaywhang_,@2ptmvd,@AlexGDimakis arxiv.org/abs/2112.02475

Congratulations to our remarkable students Jay Whang @jaywhang_ and Erik Lindgren for the best paper award in the TPM UAI workshop for 'Composing Normalizing Flows for Inverse problems' !

Time for best paper awards! The first goes to Jay Wang, Erik Lindgren and @AlexGDimakis for "Composing Normalizing Flows for Inverse Problems"