Training data extraction on GPT-2

Convert Compute And Books Into Instruct-Tuning Datasets! Makes: QA, RP, Classifiers.

Is ChatGPT Good at Search? LLMs as Re-Ranking Agent [EMNLP 2023 Outstanding Paper Award]

Privacy backdoors

A survey and reflection on the latest research breakthroughs in LLM-generated Text detection, including data, detectors, metrics, current issues and future directions.

We jailbreak GPT-3.5 Turbo’s safety guardrails by fine-tuning it on only 10 adversarially designed examples, at a cost of less than $0.20 via OpenAI’s APIs.

Official repository for our NeurIPS 2023 paper "Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense" (https://arxiv.org/abs/2303.13408).

Using Low-rank adaptation to quickly fine-tune diffusion models.

A collection of libraries to optimise AI model performances

A lightweight library designed to accelerate the process of training PyTorch models by providing a minimal, but extensible training loop which is flexible enough to handle the majority of use cases…

BackPACK - a backpropagation package built on top of PyTorch which efficiently computes quantities other than the gradient.

Breaching privacy in federated learning scenarios for vision and text

A refreshed version of Hyde for Jekyll 3.x and 4.x

A brazen two-column theme for Jekyll.

Official implementation of "Provable Defense against Privacy Leakage in Federated Learning from Representation Perspective"

An API standard for multi-agent reinforcement learning environments, with popular reference environments and related utilities

Python client library for Diem

Diem’s mission is to build a trusted and innovative financial network that empowers people and businesses around the world.

Chia blockchain python implementation (full node, farmer, harvester, timelord, and wallet)

A simple Blockchain in Python

🔧 .files, including ~/.macos — sensible hacker defaults for macOS

Code for the paper "Quantifying Transfer in Reinforcement Learning"

PyTorch implementation of Soft Actor-Critic (SAC), Twin Delayed DDPG (TD3), Actor-Critic (AC/A2C), Proximal Policy Optimization (PPO), QT-Opt, PointNet..

Code for book Python Playground by Mahesh Venkitachalam (No Starch Press, USA)

Advice for writing LaTeX documents

刷算法全靠套路，认准 labuladong 就够了！English version supported! Crack LeetCode, not only how, but also why.

DeepQoE: A unified framework for learning to predict video QoE (ICME2018 oral)