GitHub

Appa: Bending Weather Dynamics with Latent Diffusion Models for Global Data Assimilation

This repository contains the code and data for the paper Appa: Bending Weather Dynamics with Latent Diffusion Models for Global Data Assimilation by Gérôme Andry, Sacha Lewin, François Rozet, Omer ...
IEEE

Diffusion GAN-Based Oversampling for Imbalanced Tabular Data

Abstract: Imbalanced class distribution disrupts the training of a classifier, resulting in biases favoring majority classes. Data oversampling is a common strategy to tackle this issue. However, ...
The New York Times

How Johannes Høsflot Klæbo went from ‘average Joe’ to world’s best cross-country skier

With more than 100 World Cup wins, Johannes Høsflot Klaebo is the most decorated cross-country skier ever. All it took was some work and a little "friluftsliv." Federica Vanzetta / Nordic Focus / ...
CNBC

One year after DeepSeek, Chinese AI firms from Alibaba to Moonshot race to release new models

Chinese tech firms are releasing AI models at a faster pace as competition with U.S. rivals tightens. Open-source and low-cost strategies are driving the adoption of Chinese AI in emerging markets.
GitHub

Diffuse Everything: Multimodal Diffusion Models on Arbitrary State Spaces

Diffuse Everything is a general framework for building multimodal diffusion models for data of mixed modality, with a minimum need for tokenizers/VAEs/extra encoders. Diffuse Everything is built on ...
IEEE

Data-Free Knowledge Distillation with Diffusion Models

Abstract: Recently Data-Free Knowledge Distillation (DFKD) has garnered attention and can transfer knowledge from a teacher neural network to a student neural network without requiring any access to ...