Iterative Learning for Joint Image Denoising and Motion Artifact Correction of 3D Brain MRI

Kavli Affiliate: Lihong Wang | First 5 Authors: Lintao Zhang, Mengqi Wu, Lihong Wang, David C. Steffens, Guy G. Potter | Summary: Image noise and motion artifacts greatly affect the quality of brain MRI and negatively influence downstream medical image analysis. Previous studies often focus on 2D methods that process each volumetric MR image slice-by-slice, […]


Continue.. Iterative Learning for Joint Image Denoising and Motion Artifact Correction of 3D Brain MRI

Automated discovery of reprogrammable nonlinear dynamic metamaterials

Kavli Affiliate: Katia Bertoldi | First 5 Authors: Giovanni Bordiga, Eder Medina, Sina Jafarzadeh, Cyrill Boesch, Ryan P. Adams | Summary: Harnessing the rich nonlinear dynamics of highly-deformable materials has the potential to unlock the next generation of functional smart materials and devices. However, unlocking such potential requires effective strategies to spatially design optimal material […]


Continue.. Automated discovery of reprogrammable nonlinear dynamic metamaterials

Bayesian Diffusion Models for 3D Shape Reconstruction

Kavli Affiliate: Xiang Zhang | First 5 Authors: Haiyang Xu, Yu Lei, Zeyuan Chen, Xiang Zhang, Yue Zhao | Summary: We present Bayesian Diffusion Models (BDM), a prediction algorithm that performs effective Bayesian inference by tightly coupling the top-down (prior) information with the bottom-up (data-driven) procedure via joint diffusion processes. We show the effectiveness of […]


Continue.. Bayesian Diffusion Models for 3D Shape Reconstruction

Bayesian Diffusion Models for 3D Shape Reconstruction

Kavli Affiliate: Xiang Zhang | First 5 Authors: Haiyang Xu, Yu Lei, Zeyuan Chen, Xiang Zhang, Yue Zhao | Summary: We present Bayesian Diffusion Models (BDM), a prediction algorithm that performs effective Bayesian inference by tightly coupling the top-down (prior) information with the bottom-up (data-driven) procedure via joint diffusion processes. We show the effectiveness of […]


Continue.. Bayesian Diffusion Models for 3D Shape Reconstruction

V3D: Video Diffusion Models are Effective 3D Generators

Kavli Affiliate: Feng Wang | First 5 Authors: Zilong Chen, Yikai Wang, Feng Wang, Zhengyi Wang, Huaping Liu | Summary: Automatic 3D generation has recently attracted widespread attention. Recent methods have greatly accelerated the generation speed, but usually produce less-detailed objects due to limited model capacity or 3D data. Motivated by recent advancements in video […]


Continue.. V3D: Video Diffusion Models are Effective 3D Generators

Control of flow behavior in complex fluids using automatic differentiation

Kavli Affiliate: Michael Brenner | First 5 Authors: Mohammed Alhashim, Kaylie Hausknecht, Michael Brenner, , | Summary: Inverse design of complex flows is notoriously challenging because of the high cost of high dimensional optimization. Usually, optimization problems are either restricted to few control parameters, or adjoint-based approaches are used to convert the optimization problem into […]


Continue.. Control of flow behavior in complex fluids using automatic differentiation

Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Kavli Affiliate: Felix Fischer | First 5 Authors: Gemini Team, Petko Georgiev, Ving Ian Lei, Ryan Burnell, Libin Bai | Summary: In this report, we introduce the Gemini 1.5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over fine-grained information from millions of tokens of context, […]


Continue.. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Kavli Affiliate: Felix Fischer | First 5 Authors: Gemini Team, Petko Georgiev, Ving Ian Lei, Ryan Burnell, Libin Bai | Summary: In this report, we introduce the Gemini 1.5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over fine-grained information from millions of tokens of context, […]


Continue.. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Kavli Affiliate: Felix Fischer | First 5 Authors: Gemini Team, Petko Georgiev, Ving Ian Lei, Ryan Burnell, Libin Bai | Summary: In this report, we introduce the Gemini 1.5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over fine-grained information from millions of tokens of context, […]


Continue.. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

A Magnetic Millirobot Walks on Slippery Biological Surfaces for Targeted Cargo Delivery

Kavli Affiliate: Felix Fischer | First 5 Authors: Moonkwang Jeong, Xiangzhou Tan, Felix Fischer, Tian Qiu, | Summary: Small-scale robots hold great potential for targeted cargo delivery in minimally-inv asive medicine. However, current robots often face challenges to locomote efficiently on slip pery biological tissue surfaces, especially when loaded with heavy cargos. Here, we report […]


Continue.. A Magnetic Millirobot Walks on Slippery Biological Surfaces for Targeted Cargo Delivery