David Fleet

Google Research, Brain Team; and University of Toronto.

[Shayan Shekarforoush @s_shekarforoush]

We compare our method with the state-of-the-art on both synthetic and experimental benchmarks. Empirically, cryoSPIN outperforms in reconstruction quality and FSC.
[6/7]

[Shayan Shekarforoush @s_shekarforoush]

🎉🎉Excited to share that “CryoSPIN” has been accepted to #NeurIPS2024!
Special thanks to my amazing collaborators and supervisors @DaveLindell, @marcusabrubaker, and @fleet_dj

Paper: https://t.co/D63rG6SWFr
Webpage: https://t.co/jcFbHoYXQm
Code is also released!

🧵[1/7]

[Daniel Watson @watson_nn]

Why use RLHF when u can backprop through the sampler with any differentiable reward🥹🥹🥹

[Kevin Clark @clark_kev]

DRaFT backpropagates the reward directly into LoRA parameters – we don’t need to use RL because diffusion sampling is differentiable. We improve efficiency by truncating the BPTT; even truncating to one step still works! (2/5)

[Kevin Clark @clark_kev]

Our best variant, DRaFT-LV, learns 2x faster than ReFL (https://t.co/n5Dx2IBigZ) and 100x faster than RL. (3/5)

[Priyank Jaini @priyankjaini]

.@clark_kev & I are excited to share our new work on studying Imagen by evaluating it as a zero-shot classifier! Highlights include Imagen achieving SoTA on Stylized Imagenet and being able to perform attribute binding in certain settings unlike CLIP
https://t.co/rGiN03qred
🧵👇

[Kevin Clark @clark_kev]

We can reduce the effect of the fine-tuning or mix different reward functions post-training simply by scaling down or mixing LoRAs. (4/5)

[Structura Biotechnology @structurabio]

📄 An updated paper describing 3D Flexible Refinement is now out in @naturemethods!
Paper: https://t.co/sCn0nVmcEx

It describes further experimental #cryoEM results and the improved 3DFlex method that was released in #CryoSPARC v4.1 ❄️⚡
Tutorial: https://t.co/ct3QT93W2m

[AK @_akhaliq]

Monocular Depth Estimation using Diffusion Models

abs: https://t.co/p3O3L6huBf
project page: https://t.co/mzNIKRDt1K

[Chitwan Saharia @Chitwan_Saharia]

Awesome work by Hshmat. The work showcases yet another evidence of how effective noise conditioning augmentation can be.

[Hshmat Sahak @HshmatSahak]

Thrilled to announce SR3+, our new model that establishes a new state-of-the-art on diffusion-based super-resolution for images in the wild!

https://t.co/n6KZAODjhN

Joint work w/ @watson_nn @Chitwan_Saharia @fleet_dj

[George E. Dahl @GeorgeEDahl]

We've just released the first version of our Deep Learning Tuning Playbook! This is our attempt to distill our process for actually getting good results with deep learning. We emphasize hyperparameter tuning since it has been a large pain point. https://t.co/PjeJVWeOzS

[Daniel Watson @watson_nn]

Excited to announce our work on novel view synthesis with diffusion models! Our model can lift a single 2d image into 3d.

https://t.co/z1ynTchHvE

Joint work w/ @wchan212 @rmbrualla @hojonathanho @taiyasaki @mo_norouzi

[Jonathan Ho @hojonathanho]

Excited to announce Imagen Video, our new text-conditioned video diffusion model that generates 1280x768 24fps HD videos! #ImagenVideo
https://t.co/JWj3L7MpBU
Work w/ @wchan212 @Chitwan_Saharia @jaywhang_ @RuiqiGao @agritsenko @dpkingma @poolio @mo_norouzi @fleet_dj @TimSalimans

[Ben Poole @poolio]

Happy to announce DreamFusion, our new method for Text-to-3D!

https://t.co/4xI2VHcoQW

We optimize a NeRF from scratch using a pretrained text-to-image diffusion model. No 3D data needed!

Joint work w/ the incredible team of @BenMildenhall @ajayj_ @jon_barron

#dreamfusion

[Brad Neuberg @bradneuberg]

If you don’t think DallE-2 and Imagen are an Alexnet level moment in the machine learning world you aren’t paying attention enough. Very impressive visual results coming out of these. Getting similar chills to when I saw first web browser, iPhone, etc.

[Chitwan Saharia @Chitwan_Saharia]

Daniel has created some of the most amazing #Imagen images so far. Keep an eye out.

[Mohammad Norouzi @CVPR @mo_norouzi]

If you have any kind of feedback for the #imagen team, we'd love to hear it! https://t.co/uuusDOJwTc

@Chitwan_Saharia, @wchan212, @srbhsxn, Lala Li, @jaywhang_, @cephaloponderer, @coolboi95, Burcu Karagol Ayan, Sara Mahdavi, @iraphas13, @TimSalimans, @hojonathanho, @fleet_dj.

[Durk Kingma @dpkingma]

It was 16 years ago, in 2006, that @geoffreyhinton et al released their demo of deep belief nets. Undergrad me was highly impressed, and helped convince me that deep learning was the way to go. I refreshed Geoff's website almost every day checking for new papers... (1/n)

[Chitwan Saharia @Chitwan_Saharia]

@RolandMemisevic @mo_norouzi @wellingmax a blue elephant riding a unicycle on the moon #imagen