[T-PAMI 2025] EMOv2: Pushing 5M Vision Model Frontier

[CADL'22, ECCVW] Official repository of paper titled "EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications".

A simple cross attention that updates both the source and target in one step

A practical implementation of GradNorm, Gradient Normalization for Adaptive Loss Balancing, in Pytorch

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

Implementation of MeshGPT, SOTA Mesh generation using Attention, in Pytorch

A concise but complete full-attention transformer with a set of promising experimental features from various papers

Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI

Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorch