frank-xwang

bsq-vit

[BSQ-ViT] Image and Video Tokenization with Binary Spherical Quantization

cambrian

Cambrian-1 is a family of multimodal LLMs with a vision-centric design.

DeepSeek-VL

DeepSeek-VL: Towards Real-World Vision-Language Understanding

ml-4m

4M: Massively Multimodal Masked Modeling

CRATE-alpha

This repository includes the official implementation our paper "Scaling White-Box Transformers for Vision"

Awesome-Unsupervised-Object-Localization

Curated list of awesome works on unsupervised object localization in 2D images.

LLaVA-NeXT

scaling_on_scales

When do we not need larger vision models?

UnScene3D

Unsupervised 3D Instance Segmentation

xformers

Hackable and optimized Transformers building blocks, supporting a composable construction.

BrainDecodesDeepNets

PyTorch implementation of "Brain Decodes Deep Nets"

annotated_deep_learning_paper_implementations

🧑‍🏫 60 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

zest_code

This is the official implementation of ZeST

FreeU

FreeU: Free Lunch in Diffusion U-Net (CVPR2024 Oral)

CuVLER

Enhanced Unsupervised Object Discoveries through Exhaustive Self-Supervised Transformers

garfield

[CVPR'24] Group Anything with Radiance Fields

FeatUp

Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024

grok-1

Grok open release

faster-rcnn.pytorch

A faster pytorch implementation of faster r-cnn

FreeSOLO

FreeSOLO for unsupervised instance segmentation, CVPR 2022

DetectAndTrack

The implementation of an algorithm presented in the CVPR18 paper: "Detect-and-Track: Efficient Pose Estimation in Videos"

PixArt-alpha

PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis

dust3r

DUSt3R: Geometric 3D Vision Made Easy

Open-Sora-Plan

This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

LayoutGPT

Official repo for LayoutGPT

Structured-Diffusion-Guidance

Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis

MaskTrackRCNN

MaskTrackRCNN for video instance segmentation based on mmdetection

RADIO

Official repository for "AM-RADIO: Reduce All Domains Into One"

EMO

Emote Portrait Alive: Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions

ComfyUI-InstanceDiffusion