CHENGY12

Tree-Transformer

Implementation of the paper Tree Transformer

dowhy

DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions. DoWhy is based on a unified language for causal inference, combining causal graphical models and potential outcomes frameworks.

CogVideo

Text-to-video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

LaVIT

LaVIT: Empower the Large Language Model to Understand and Generate Visual Content

Structured-Diffusion-Guidance

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

awesome-english-ebooks

经济学人(含音频)、纽约客、卫报、连线、大西洋月刊等英语杂志免费下载,支持epub、mobi、pdf格式, 每周更新

LaVi-Bridge

[ECCV 2024] Bridging Different Language Models and Generative Vision Models for Text-to-Image Generation

AlphaCLIP

[CVPR 2024] Alpha-CLIP: A CLIP Model Focusing on Wherever You Want

DeCLIP

Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm

datacomp

DataComp: In search of the next generation of multimodal datasets

InternVL

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

ELLA

ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment

ALIP

[ICCV 2023] ALIP: Adaptive Language-Image Pre-training with Synthetic Caption

Pandora

Pandora: Towards General World Model with Natural Language Actions and Video States

MambaOut

MambaOut: Do We Really Need Mamba for Vision?

LLaVA-NeXT

i-stylegan

Multi-domain image generation and translation with identifiability guarantees

MGM

Official repo for "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models"

sglang

SGLang is a fast serving framework for large language models and vision language models.

Chain-of-Spot

Chain-of-Spot: Interactive Reasoning Improves Large Vision-language Models

VAR

[GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly yet state-of-the-art* codebase for autoregressive image generation!

tapnet

Tracking Any Point (TAP)

Open-Sora

Open-Sora: Democratizing Efficient Video Production for All

Mora

Mora: More like Sora for Generalist Video Generation

SoraReview

The official GitHub page for the review paper "Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models".

honeybee

Official implementation of project Honeybee (CVPR 2024)

howto100m

Code for the HowTo100M paper

unmasked_teacher

[ICCV2023 Oral] Unmasked Teacher: Towards Training-Efficient Video Foundation Models

Revisiting-Contrastive-SSL

Revisiting Contrastive Methods for Unsupervised Learning of Visual Representations. [NeurIPS 2021]

VILA

VILA - a multi-image visual language model with training, inference and evaluation recipe, deployable from cloud to edge (Jetson Orin and laptops)