Tianlin Liu's Projects
Robust recipes for to align language models with human and AI preferences
Implementation of "Decoding-time Realignment of Language Models", ICML 2024.
A Python library that integrates the Curvelet transform into differentiable programming pipelines, such as PyTorch and JAX.
A collection of deep learning models written in JAX/Flax.
Code for reproducing figures in my master thesis
Implementation of "Learning Multiscale Convolutional Dictionaries for Image Reconstruction", IEEE Transaction On Computational Imaging, 2022.
This repository contains a benchmark of deep learning pickers
POT : Python Optimal Transport
Implementation of "Sparsity-Constrained Optimal Transport", ICLR 2023.
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Train transformer language models with reinforcement learning.