Tianci Liu's starred repositories
Anti-DreamBooth
Anti-DreamBooth: Protecting users from personalized text-to-image synthesis (ICCV 2023)
photoguard
Raising the Cost of Malicious AI-Powered Image Editing
academic-homepage
🏡 GitHub Pages template for personal academic homepage
ambient-diffusion-mri
Official Implementation: "Ambient Diffusion Posterior Sampling: Solving Inverse Problems with Diffusion Models trained on Corrupted Data"
improved-diffusion
Release for Improved Denoising Diffusion Probabilistic Models
lm-evaluation-harness
A framework for few-shot evaluation of language models.
Diff4RLSurvey
This repository contains a collection of resources and papers on Diffusion Models for RL, accompanying the paper "Diffusion Models for Reinforcement Learning: A Survey"
LLM-Adapters
Code for our EMNLP 2023 Paper: "LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models"
Watermark-Vaccine
The code for ECCV2022 (Watermark Vaccine: Adversarial Attacks to Prevent Watermark Removal)
pytorch-maml
PyTorch implementation of MAML: https://arxiv.org/abs/1703.03400
goodtriever
Code for "Goodtriever: Toxicity Mitigation with Retrieval-augmented Language Models"
Watermark-Removal-Pytorch
🔥 CNN for Watermark Removal using Deep Image Prior with Pytorch 🔥.
RippleEdits
Evaluating the Ripple Effects of Knowledge Editing in Language Models
DALLE2-pytorch
Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch
DALLE-pytorch
Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch
Multimodal-datasets
This repository is build in association with our position paper on "Multimodality for NLP-Centered Applications: Resources, Advances and Frontiers". As a part of this release we share the information about recent multimodal datasets which are available for research purposes. We found that although 100+ multimodal language resources are available in literature for various NLP tasks, still publicly available multimodal datasets are under-explored for its re-usage in subsequent problem domains.