Overcoming a barrier to projecting near-term climate evolution and risk

The Earth is warming more rapidly than before, and extreme weather events are becoming more frequent and more intense. While ...

Scientists thought they understood global warming. Then the past three years happened.

The fastest warming period since 1880 occurred in the past 30 years, according to a Washington Post analysis of NASA data.

When heat flows backwards: A neat solution for hydrodynamic heat transport

When we think about heat traveling through a material, we typically picture diffusive transport, a process that transfers ...
GitHub

MoDiff - Graph Generation with Motif-Aware Diffusion Model

The subgraphs for training are preprocessed with motif detection and stored in different files in this code. We provide StackOverflow as an example. The 1h scale can be used directly, while the 5h and ...
IEEE

A Flexible Diffusion Convolution for Graph Neural Networks

Abstract: Graph Neural Networks (GNNs) have been gaining more attention due to their excellent performance in modeling various graph-structured data. However, most of the current GNNs only consider ...
IEEE

Learning Joint 2-D and 3-D Graph Diffusion Models for Complete Molecule Generation

Abstract: Designing new molecules is essential for drug discovery and material science. Recently, deep generative models that aim to model molecule distribution have made promising progress in ...
GitHub

RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation

RDT-1B is a 1B-parameter (largest to date) imitation learning Diffusion Transformer pre-trained on 1M+ (largest to date) multi-robot episodes. Given language instruction and RGB images of up to three ...