keyu-tian
Master's student @ pku, self-supervised learning & generative models & reinforcement learning
Peking UniversityLyoko
Pinned Repositories
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!
BUAA-datastructure-project-solution
[Ranked No. 1🥇] My solution for the course project of Datastructure 2019'Spring @ BUAA (北航数据结构). Plenty of C language tricks, hacks, and optimizations are used for extreme efficiency. *Ranked 1/800* in the efficiency test.
BUAA-parallel-computing-project-solution
[Ranked No. 1🥇] My solution for the course project of Parallel Computing 2021'Spring @ BUAA (北航并行程序设计). Plenty of C++ tricks, hacks, and optimizations are used for extreme efficiency. Ranked *1/100* in the efficiency test.
BUAA-SE-OS-summary
A simple summary of the OS course
Christmas-tree
Marry Xmas! (from http://www.codebaoku.com/it-python/it-python-232037.html)
Cpp-Gomoku-with-AI
C++ Gomoku with a strong AI based on minimax search and alpha-beta pruning with Qt5 GUI. *Dozens of C++ tricks & hacks are used to improve efficiency.* Come and try to see if you can beat the powerful AI!
dda
Dynamic Data Augmentation for Time Series
Gobang_AI_by_Kevin
纯C五子棋AI实现。当然也可双人对弈。
SparK
[ICLR'23 Spotlight🔥] The first successful BERT/MAE-style pretraining on any convolutional network; Pytorch impl. of "Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling"
Star-War
Multiplayer game with Java Swing framework, using MVVM design architecture and Dependency-Inversion principle.
keyu-tian's Repositories
keyu-tian/SparK
[ICLR'23 Spotlight🔥] The first successful BERT/MAE-style pretraining on any convolutional network; Pytorch impl. of "Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling"
keyu-tian/BUAA-datastructure-project-solution
[Ranked No. 1🥇] My solution for the course project of Datastructure 2019'Spring @ BUAA (北航数据结构). Plenty of C language tricks, hacks, and optimizations are used for extreme efficiency. *Ranked 1/800* in the efficiency test.
keyu-tian/BUAA-parallel-computing-project-solution
[Ranked No. 1🥇] My solution for the course project of Parallel Computing 2021'Spring @ BUAA (北航并行程序设计). Plenty of C++ tricks, hacks, and optimizations are used for extreme efficiency. Ranked *1/100* in the efficiency test.
keyu-tian/EVA-CLIP
EVA Series: Visual Representation Fantasies from BAAI
keyu-tian/nlp_prototype
keyu-tian/alphatensor
keyu-tian/biocatalysis-model
RXN for biochemical reactions
keyu-tian/ConvNeXt
Code release for ConvNeXt model
keyu-tian/DAB-DETR
[ICLR 2022] DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR
keyu-tian/DALLE2-pytorch
Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch
keyu-tian/deit
Official DeiT repository
keyu-tian/ESAN
Equivariant Subgraph Aggregation Networks (ICLR 2022 Spotlight)
keyu-tian/flash-attention
Fast and memory-efficient exact attention
keyu-tian/GNNAK
Source code for From Stars to Subgraphs (ICLR 2022)
keyu-tian/ibot
iBOT: Image BERT Pre-Training with Online Tokenizer
keyu-tian/image-gpt
keyu-tian/keyu-tian
keyu-tian/latent-diffusion
High-Resolution Image Synthesis with Latent Diffusion Models
keyu-tian/mae
PyTorch implementation of MAE https//arxiv.org/abs/2111.06377
keyu-tian/molecule_playground
keyu-tian/muse
Implementation of Muse: Text-to-Image Generation via Masked Generative Transformers, in Pytorch
keyu-tian/pdf-cut-white
自动裁剪PDF图表中的白边 / Cut white bound in PDF figures automatically.
keyu-tian/PixArt-alpha
Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis
keyu-tian/rq-vae
The official implementation of Autoregressive Image Generation using Residual Quantization (CVPR '22)
keyu-tian/stable-diffusion
A latent text-to-image diffusion model
keyu-tian/stable-diffusion-2
SD 2.0, High-Resolution Image Synthesis with Latent Diffusion Models
keyu-tian/stylegan-t
[ICML'23] StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis
keyu-tian/stylegan-xl
[SIGGRAPH'22] StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets
keyu-tian/Swin-Transformer-Semantic-Segmentation
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Semantic Segmentation.
keyu-tian/vqgan
Taming Transformers for High-Resolution Image Synthesis