#
wenqsun
Follow
Lists (13)
3⃣️ 3D generation&reconstruction
78 repositories
🚀Adversarial Attack
Adversarial attack resources20 repositories
🧗 Embodied AI
A list for Embodied AI.3 repositories
🌟Federated Learning
This a repository list for federated learning algorithms.31 repositories
👀General deep learning
A general deep learning list includes GAN, knowledge distillation, computer vision, NLP, etc.82 repositories
🧐🧐🧐General research and writing
This is a list of general research methods, writing skills, and information helpers!24 repositories
🤩Interesting computer works
A repository for some interesting computer works, such as obtaining information from websites, API usage(ChatGPT, etc.), and secrete computer technique.12 repositories
💥💥💥LLMs
54 repositories
🔥🔥🔥Multi modal and diffusion
A repository for Multi-modal and diffusion model174 repositories
🌛Privacy attack and defense
Learning resources for privacy attack and defense, such as MIA and gradient inversion .etc.20 repositories
🤔Reinforcement learning
This is a list of reinforcement learning resources.12 repositories
🧠Thinking and working
This is a list about some findings in computer science, math, reading, work, .etc.17 repositories
🛸🛸🛸 World Model
3 repositories
Starred repositories
ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion Transformer
DINO-X: The World's Top-Performing Vision Model for Open-World Object Detection and Understanding
DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos
[ARXIV'24] SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints
A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.
(NeurIPS 2024 Oral 🔥) Improved Distribution Matching Distillation for Fast Image Synthesis
Depth Any Video with Scalable Synthetic Data
A linear estimator on top of clip to predict the aesthetic quality of pictures
An open-source lightweight game generation paradigm. It includes everything from data processing to model architecture design and playability-based evaluation methods. The game runs at 20 FPS on a …
High-resolution models for human tasks.
HunyuanVideo: A Systematic Framework For Large Video Generation Model
Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation".
code for "Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion"
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
[SIGGRAPH Asia 2024 (Journal Track)] StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal
The paper collections for the autoregressive models in vision.
EdgeRunner: Auto-regressive Auto-encoder for Efficient Mesh Generation
Official repository of In-Context LoRA for Diffusion Transformers
Official Implementations for Paper - MagicQuill: An Intelligent Interactive Image Editing System
Unifying 3D Mesh Generation with Language Models
DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion
A suite of image and video neural tokenizers
No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images
Pytorch implementation of Transfusion, "Predict the Next Token and Diffuse Images with One Multi-Modal Model", from MetaAI