Poy's repositories
active-learning-benchmark
Active learning benchmark for classification
tensorflow-sequences-time-series-and-prediction-PyTorch
Sequences, Time Series and Prediction by deeplearning.ai
html.2023.bonusfinal-public
The repository serves as the tutorial for the bonus track of the final project of [CSIE 5043] Machine Learning during the Spring semester of 2023 at National Taiwan University.
alignment-handbook
Robust recipes for to align language models with human and AI preferences
ALiPy
ALiPy: Active Learning in Python is an active learning python toolbox, which allows users to conveniently evaluate, compare and analyze the performance of active learning methods.
ariapoy.github.io
To my aquamarine.
byol-pytorch
Usable Implementation of "Bootstrap Your Own Latent" self-supervised learning, from Deepmind, in Pytorch
chjhs_2020
靜心中學高中資訊社課程 Chingshin Academy
d2l-en
Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 300 universities from 55 countries including Stanford, MIT, Harvard, and Cambridge.
ddpo-pytorch
DDPO for finetuning diffusion models, implemented in PyTorch with LoRA support
deep-active-learning
Deep Active Learning
DiffusionDPO
Code for "Diffusion Model Alignment Using Direct Preference Optimization"
dockerfile_collection
Collection of my docker environments.
DRLX
Diffusion Reinforcement Learning Library
ImageReward
[NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation
libact
Pool-based active learning in Python
NTU-Spring2021-DIP
NTU Sprint 2021 DIP
PaLM-rlhf-pytorch
Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM
photoguard
Raising the Cost of Malicious AI-Powered Image Editing
ShadeSketch
Implementation of "Learning to Shadow Hand-drawn Sketches" CVPR 2020 (Oral)
simsiam
PyTorch implementation of SimSiam https//arxiv.org/abs/2011.10566
skills-code-with-codespaces
My clone repository
trl
Train transformer language models with reinforcement learning.
vaal
Variational Adversarial Active Learning (ICCV 2019)
ZOOM
code for Zero-shot-model-diagnosis (CVPR 2023)