-
Chinese Academy of Sciences
- Beijing
-
15:25
(UTC +08:00) - https://robin-wzq.github.io/
Lists (9)
Sort Name ascending (A-Z)
Stars
[ECCV24] T2IShield: Defending Against Backdoors on Text-to-Image Diffusion Models
⚡️HivisionIDPhotos: a lightweight and efficient AI ID photos tools. 一个轻量级的AI证件照制作算法。
Repository for Show-o, One Single Transformer to Unify Multimodal Understanding and Generation.
real time face swap and one-click video deepfake with only a single image
Implementation of Generative Moment Matching Networks in pytorch
MMD-GAN: Towards Deeper Understanding of Moment Matching Network
EraseDiff: Erasing Data Influence in Diffusion Models
The official implementation of ECCV'24 paper "To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Now". This work introduces one fast and e…
MiniCPM-V 2.6: A GPT-4V Level MLLM for Single Image, Multi Image and Video on Your Phone
A continually updated list of literature on Reinforcement Learning from AI Feedback (RLAIF)
Source code for the Energy-Latency Attacks via Sponge Poisoning paper.
Cambrian-1 is a family of multimodal LLMs with a vision-centric design.
[CVPR 2024] "MACE: Mass Concept Erasure in Diffusion Models" (Official Implementation)
"From Trojan Horses to Castle Walls: Unveiling Bilateral Backdoor Effects in Diffusion Models" by Zhuoshi Pan*, Yuguang Yao*, Gaowen Liu, Bingquan Shen, H. Vicky Zhao, Ramana Rao Kompella, Sijia Liu
Six-CD: Benchmarking Concept Removals for Benign Text-to-image Diffusion Models
Everything you want about DP-Based Federated Learning, including Papers and Code. (Mechanism: Laplace or Gaussian, Dataset: femnist, shakespeare, mnist, cifar-10 and fashion-mnist. )
[ICML2024] Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast
Chinese safety prompts for evaluating and improving the safety of LLMs. 中文安全prompts,用于评估和提升大模型的安全性。
A curated list of Diffusion Model in RL resources (continually updated)
A PyTorch implementation of the paper "All are Worth Words: A ViT Backbone for Diffusion Models".
Open-Sora: Democratizing Efficient Video Production for All