Sublime

An inspiration engine for ideas

AllPeopleCollectionsArticlesAudioBooksFilesHighlightsImagesLinksNotesTextTweetsVideosSocial

Brax - A Differentiable Physics Engine for Large Scale Rigid Body Simulation pdf: https://t.co/QkVCDxi3ch github: https://t.co/kfteGt8VO4 an open source library for rigid body simulation with a focus on performance and parallelism on accelerators, written in JAX https://t.co/6s9F6Z8gig

AK x.com

🎊 New paper! We train loss-conditional diffusion models of *neural network checkpoints* that learn to optimize. w/ Radosavovic, Brooks, Efros, Malik proj: https://t.co/R58P8soLpy arxiv: https://t.co/9AzqV0koIz code:... See more

Bill Peebles x.com

Our new @iclr_conf '22 paper /How many degrees of freedom do we need to train deep networks: a loss landscape perspective/ is finally out! Led by @_BrettLarsen w @yisqe @SuryaGanguli. High-dim geometry+neural nets 📚Paper: https://t.co/zSHLl8sfP3 🖥️Code: https://t.co/bh19a9S7Jw https://t.co/DWRtd620Fj

Stanislav Fort x.com

Robust Dual Gaussian Splatting for Immersive Human-centric Volumetric Videos discuss: https://t.co/dTfd0enmg4 Volumetric video represents a transformative advancement in visual media, enabling users to freely navigate immersive virtual experiences and narrowing the gap between digital and... See more

AK x.com

SSS GS: Subsurface Scattering for Gaussian Splatting Real-time rendering, relighting and material editing of translucent objects. Learn more & explore our paper at 🌐 https://t.co/lQwZzswL6P 📷 https://t.co/cf4zFsWrgY Big thanks also... See more

Jan x.com

Reading the SmoothQuant paper (https://t.co/H2T9dCSf2e), which is quite ingenious and wanted to share. Since matmul, A*B=C, is linear, we can shift information in A or B around. As such, we can balance the quantization difficulty across both matrices leading to great performance! https://t.co/g1Ea1uSEa7

Tim Dettmers

x.com

time to go down the rabbit hole ig https://t.co/PUMGbMiRXp

samyak

x.com

3D Gaussian Editing with A Single Image discussion: https://t.co/W6DfSf8AMC The modeling and manipulation of 3D scenes captured from the real world are pivotal in various applications, attracting growing research interest. While previous works on editing have achieved interesting results... See more

x.com

Hash3D Training-free Acceleration for 3D Generation The evolution of 3D generative modeling has been notably propelled by the adoption of 2D diffusion models. Despite this progress, the cumbersome optimization process per se presents a critical hurdle to efficiency. In this... See more

x.com