Lists (1)
Stars
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
Training-free framework for text watermarking that is scalable, robust to LLM attacks, and applicable to original text of multiple types
[ICML2024] Adaptive Text Watermark for Large Language Models
Computer Science fan's notes and blog, mostly about data structure and algorithm, also include other related topics: behavior question, object-oriented design, system design, database SQL and found…
机器学习工程师、算法工程师、软件工程师、数据科学家-面试指南 | Interview guide for MLE, SDE, DS
Watermark Stealing in Large Language Models (ICML '24)
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).
[ACL 2024] Can Watermarks Survive Translation? On the Cross-lingual Consistency of Text Watermark for Large Language Models
Compress your input to ChatGPT or other LLMs, to let them process 2x more content and save 40% memory and GPU time.
MarkLLM: An Open-Source Toolkit for LLM Watermarking.（EMNLP 2024 Demo）
《机器学习理论导引》（宝箱书）的证明、案例、概念补充与参考文献讲解。
Official PyTorch implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden States
[USENIX Security 2025] PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models
[EMNLP 2023] Poisoning Retrieval Corpora by Injecting Adversarial Passages https://arxiv.org/abs/2310.19156
Contriever: Unsupervised Dense Information Retrieval with Contrastive Learning
This repository provides a benchmark for prompt Injection attacks and defenses
EPFL Course - Optimization for Machine Learning - CS-439
A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.
PyTorch implementation of MAE https//arxiv.org/abs/2111.06377
[ICLR 2024 (Spotlight)] "Frozen Transformers in Language Models are Effective Visual Encoder Layers"
Official inference library for Mistral models
mistralai / FastChat-release
Forked from lm-sys/FastChatAn open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
Pytorch implementation of convolutional neural network visualization techniques