Junke Wang

SimpleAR. Pytorch implementation for the paper titled "SimpleAR: Pushing the Frontier of Autoregressive Visual Generation"

M2TR-Multi-modal-Multi-scale-Transformers-for-Deepfake-Detection. Python

PyDeepFakeDet. PyDeepFakeDet is an integrated and scalable tool for Deepfake detection.

RepWAM. Code for RepWAM: World Action Modeling with Representation Visual-Action Tokenizers

OmniVid. Python

STTS. Official PyTorch implementation of the ECCV 2022 paper: Efficient Video Transformers with Spatial-Temporal Token Selection.

ARM. ARM: An AutoRegressive Large Multimodal Model with Discrete Representations

Objectformer. Jupyter Notebook

OpenTokenizer. Python

vllm. Python

Video-Swin-Transformer. This is an official implementation for "Video Swin Transformers".