jinghanjia
Ph.D. Student at Michigan State University. Scalable and Trustworthy AI. ❤️Optimization, AI for Programming language, AI health.
msu
jinghanjia's Stars
xialijun0801/qfin
Books for Quant Finance Interviews
anthropics/hh-rlhf
Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"
mtbench101/mt-bench-101
[ACL 2024] MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn Dialogues
chrisliu298/awesome-llm-unlearning
A resource repository for machine unlearning in large language models
eric-mitchell/direct-preference-optimization
Reference implementation for DPO (Direct Preference Optimization)
locuslab/tofu
Landing Page for TOFU
jinzhuoran/RWKU
RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models
PKU-Alignment/beavertails
BeaverTails is a collection of datasets designed to facilitate research on safety alignment in large language models (LLMs).
MinghuiChen43/awesome-trustworthy-deep-learning
A curated list of trustworthy deep learning papers. Daily updating...
xiaojunxu/learning-to-watermark-llm
OPTML-Group/AdvUnlearn
Official implementation of "Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models"
OPTML-Group/Unlearn-Saliency
[ICLR24 (Spotlight)] "SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation" by Chongyu Fan*, Jiancheng Liu*, Yihua Zhang, Eric Wong, Dennis Wei, Sijia Liu
hzy312/Awesome-LLM-Watermark
UP-TO-DATE LLM Watermark paper. 🔥🔥🔥
OPTML-Group/Unlearn-WorstCase
"Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning" by Chongyu Fan*, Jiancheng Liu*, Alfred Hero, Sijia Liu
cisco-open/modelsmith
A toolkit for optimizing machine learning models for practical applications
OPTML-Group/SOUL
Official repo for paper "SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning"
pprp/Awesome-LLM-Prune
Awesome list for LLM pruning.
meta-llama/llama3
The official Meta Llama 3 GitHub site
centerforaisafety/wmdp
WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning method which reduces LLM performance on WMDP while retaining general capabilities.
OPTML-Group/UnlearnCanvas
UnlearnCanvas: A Stylized Image Dataaset to Benchmark Machine Unlearning for Diffusion Models by Yihua Zhang, Chongyu Fan, Yimeng Zhang, Yuguang Yao, Jinghan Jia, Jiancheng Liu, Gaoyuan Zhang, Gaowen Liu, Ramana Kompella, Xiaoming Liu, Sijia Liu
LargeWorldModel/LWM
AI-secure/DecodingTrust
A Comprehensive Assessment of Trustworthiness in GPT Models
OPTML-Group/Unlearn-Sparse
[NeurIPS23 (Spotlight)] "Model Sparsity Can Simplify Machine Unlearning" by Jinghan Jia*, Jiancheng Liu*, Parikshit Ram, Yuguang Yao, Gaowen Liu, Yang Liu, Pranay Sharma, Sijia Liu
tamlhp/awesome-machine-unlearning
Awesome Machine Unlearning (A Survey of Machine Unlearning)
ShawnLJW/harry-GPTter
GPT2 clone that generates harry potter books.
voxel51/fiftyone
The open-source tool for building high-quality datasets and computer vision models
dhaitz/mplcyberpunk
"Cyberpunk style" for matplotlib plots
garrettj403/SciencePlots
Matplotlib styles for scientific plotting
ghzhang233/llama_paper_assistant
Llama based personalized ArXiv paper assistant bot
kevinyaobytedance/llm_unlearn
LLM Unlearning