Dynamic Token Expansion with Continual Transformers, accepted at CVPR 2022
APACHE-2.0 License
PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO
[CVPR 2021] Code for "Augmentation Strategies for Learning with Noisy Labels".
Embed arbitrary modalities (images, audio, documents, etc) into large language models.
Code release for the ICLR 2023 conference paper "DeFog: Decision Transformer under Random Frame D...
Generic image compressor for machine learning. Pytorch code for our paper "Lossy compression for ...
Continual Hyperparameter Selection Framework. Compares 11 state-of-the-art Lifelong Learning meth...
Pytorch implementation of our method for high-resolution (e.g. 2048x1024) photorealistic video-to...
Home of StarCoder: fine-tuning & inference!
[GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregress...
Official code of CVPR 2021's PLOP: Learning without Forgetting for Continual Semantic Segmentation
Semantic Image Synthesis with SPADE
GLM (General Language Model)
The PyTorch Implementation based on YOLOv4 of the paper: "Complex-YOLO: Real-time 3D Object Detec...
Hybrid Discriminative-Generative Training via Contrastive Learning