-
Virginia Tech
- Blacksburg
- http://sichen21.netlify.app
- @si_chen0921
Stars
Models and examples built with TensorFlow
The simplest, fastest repository for training/finetuning medium-sized GPTs.
PyTorch implementations of Generative Adversarial Networks.
Implementation of Denoising Diffusion Probabilistic Model in Pytorch
Simple Reinforcement learning tutorials, 莫烦Python 中文AI教学
arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv
Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams
Release for Improved Denoising Diffusion Probabilistic Models
🔥🔥High-Performance Face Recognition Library on PaddlePaddle & PyTorch🔥🔥
Code for reproducing results in "Glow: Generative Flow with Invertible 1x1 Convolutions"
Code for visualizing the loss landscape of neural nets
TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.
A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.
Code and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)
Generalist and Lightweight Model for Named Entity Recognition (Extract any entity types from texts) @ NAACL 2024
A modular active learning framework for Python
An optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks
A mix of GAN implementations including progressive growing
Official implementation of Cold-Diffusion for different transformations in pytorch.
Code relative to "Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks"
Locating and editing factual associations in GPT (NeurIPS 2022)
Code for "MixMatch - A Holistic Approach to Semi-Supervised Learning"
RewardBench: the first evaluation tool for reward models.
Making decision trees competitive with neural networks on CIFAR10, CIFAR100, TinyImagenet200, Imagenet
The open-sourced Python toolbox for backdoor attacks and defenses.
Mass-editing thousands of facts into a transformer memory (ICLR 2023)