-
Tsinghua University
- Shenzhen & Beijing
- [email protected]
- https://scholar.google.com/citations?hl=en&user=dbCdFjoAAAAJ
Stars
verl: Volcano Engine Reinforcement Learning for LLMs
limenlp / verl
Forked from volcengine/verlAdaRFT: Efficient Reinforcement Finetuning via Adaptive Curriculum Learning
A unified framework for controllable caption generation across images, videos, and audio. Supports multi-modal inputs and customizable caption styles.
The official implementation for the paper "Invisible Entropy: A Safe and Efficient Paradigm for Low-entropy Watermarking".
MarkLLM: An Open-Source Toolkit for LLM Watermarking.(EMNLP 2024 System Demonstration)
This is a project that converts all types of LLM services (e.g. POST requests, local models) into the OpenAI API format. Ongoing updates...
A comprehensive benchmark of deepfake detection
A Fairness Benchmark for Face Forgery Detection
liudan193 / poison_froggo
Forked from LostOxygen/poison_froggofixed the memory leaks problem
A list of backdoor learning resources
No.3 solution of Tianchi ImageNet Adversarial Attack Challenge.
Convert tensorflow model to pytorch model via [MMdnn](https://github.com/microsoft/MMdnn) for adversarial attacks.
re-implementation of the poison frogs! paper in PyTorch