PengfeiHePower

manifold-clustering

SC with angle-constrained annular proximity graph

100-Days-Of-ML-Code

100 Days of ML Coding

500lines

500 Lines or Less

agentscope

Start building LLM-empowered multi-agent applications in an easier way.

Awesome-Copyright-in-Generative-AI

boundary-backdoor

categorical-attack

Code for probabilistic categorical attack

Generalization-attack

ICLPoison

SAPA

PengfeiHePower/categorical-attack

Code for probabilistic categorical attack

PengfeiHePower/Awesome-Copyright-in-Generative-AI

PengfeiHePower/boundary-backdoor

PengfeiHePower/ICLPoison

PengfeiHePower/SAPA

PengfeiHePower/803

PengfeiHePower/842-proj

PengfeiHePower/agentscope

Start building LLM-empowered multi-agent applications in an easier way.

PengfeiHePower/awesome-computer-vision

A curated list of awesome computer vision resources

PengfeiHePower/Generalization-attack

PengfeiHePower/causal-mediation-case-study

PengfeiHePower/causal-mediation-data-splitting

PengfeiHePower/chain-of-knowledge

[ICLR2024] Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources

PengfeiHePower/ColossalAI

Making big AI models cheaper, easier, and more scalable

PengfeiHePower/concept-based-backdoor

Offical code of the paper Large Language Models Are Implicitly Topic Models: Explaining and Finding Good Demonstrations for In-Context Learning.

PengfeiHePower/hidden-repre-backdoor

PengfeiHePower/ICL-understanding-classification

PengfeiHePower/llama

Inference code for LLaMA models

PengfeiHePower/llm-security

Papers and resources related to the security and privacy of LLMs 🤖

PengfeiHePower/PengfeiHePower.github.io

A beautiful, simple, clean, and responsive Jekyll theme for academics

PengfeiHePower/Poisoning-Instruction-Tuned-Models

for testing

PengfeiHePower/ReAct

[ICLR 2023] ReAct: Synergizing Reasoning and Acting in Language Models

PengfeiHePower/SAM

SAM: Sharpness-Aware Minimization (PyTorch)

PengfeiHePower/Sharp-Agent

PengfeiHePower/sharp-auto-poison

Code for the paper "Autoregressive Perturbations for Data Poisoning" (NeurIPS 2022)

PengfeiHePower/sharp-gradient-matching

sharpness poisoning with gradient matching

PengfeiHePower/sharp-short

PengfeiHePower/sharp_adv_poison

PengfeiHePower/sharpness-unlearnable

[ICLR2021] Unlearnable Examples: Making Personal Data Unexploitable

PengfeiHePower/TRADES

TRADES (TRadeoff-inspired Adversarial DEfense via Surrogate-loss minimization)