AI agents running research on single-GPU nanochat training automatically

TurboDiffusion: 100–200× Acceleration for Video Diffusion Models

Official JAX implementation of MAGVIT: Masked Generative Video Transformer

Scenic: A Jax Library for Computer Vision Research and Beyond

Pre-trained models, data, code & materials from the paper "ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness" (ICLR 2019 Oral)

Regularizing Generative Adversarial Networks under Limited Data (CVPR 2021)

Collect some papers about transformer with vision. Awesome Transformer with Computer Vision (CV)

Top ML papers published daily in arXiv

pytorch implementation for Contrastive Adaptation Network

Code and model for "Peeking into the Future: Predicting Future Person Activities and Locations in Videos", Liang et al, CVPR 2019

e3d-lstm; Eidetic 3D LSTM A Model for Video Prediction and Beyond

deep learning, image retrieval, vision and language

Graph Distillation for Action Detection

MemexQA Dataset

Real-world photo sequence question answering system

Code for MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks

Code for "Image Generation from Scene Graphs", Johnson et al, CVPR 2018

Real-world photo sequence question answering system (MemexQA). CVPR'18 and TPAMI'19