Pinned Repositories
fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
fyyfu.github.io
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
MAML-Pytorch
Reproduce MAML in Pytorch with omniglot dataset.
NMT
Neural Machine Translation
safety-defense
Code and data for paper: Cross-Task Defense: Instruction-Tuning LLMs for Content Safety (NNACL2024 TrustNLP Workshop)
SafetyAlignNLP
Code, Data and Demo for paper: Safety Alignment in NLP Tasks: Weakly Aligned Summarization as an In-Context Attack
semantic-watermark
Code for paper: Watermarking Conditional Text Generation for AI Detection: Unveiling Challenges and a Semantic-Aware Watermark Remedy
inseq
Interpretability for sequence generation models 🐛 🔍
llm-attacks
Universal and Transferable Attacks on Aligned Language Models
MusicFreePlugins
MusicFree播放插件
FYYFU's Repositories
FYYFU/semantic-watermark
Code for paper: Watermarking Conditional Text Generation for AI Detection: Unveiling Challenges and a Semantic-Aware Watermark Remedy
FYYFU/HeadKV
Code and data for paper: Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning
FYYFU/safety-defense
Code and data for paper: Cross-Task Defense: Instruction-Tuning LLMs for Content Safety (NNACL2024 TrustNLP Workshop)
FYYFU/fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
FYYFU/fyyfu.github.io
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
FYYFU/MAML-Pytorch
Reproduce MAML in Pytorch with omniglot dataset.
FYYFU/NMT
Neural Machine Translation
FYYFU/SafetyAlignNLP
Code, Data and Demo for paper: Safety Alignment in NLP Tasks: Weakly Aligned Summarization as an In-Context Attack