A large-scale benchmark and learning environment.

A unified robotic manipulation learning framework

[CVPR 2025] Prompt Depth Anything

Stable-Sim2Real: Exploring Simulation of Real-Captured 3D Data with Two-Stage Depth Diffusion (ICCV 2025 Highlight)

The Power of the Senses: Generalizable Manipulation from Vision and Touch through Masked Multimodal Learning

Official repository for RSS 25 paper: ArticuBot. Project: https://articubot.github.io/

AcadHomepage: A Modern and Responsive Academic Personal Homepage

[ICLR 2025] Official implementation of 'Hidden in the Noise: Two-Stage Robust Watermarking for Images'

[ICLR 2025] An Undetectable Watermark for Generative Image Models

Official Implementation for: "RAW: A Robust and Agile Plug-and-Play Watermark Framework for AI-Generated Images (Videos) with Provable Guarantees"

source code for "ROBIN: Robust and Invisible Watermarks for Diffusion Models with Adversarial Optimization"

[NeurIPS 2024] Invisible Image Watermarks Are Provably Removable Using Generative AI

Code for our paper "Benchmarking the Robustness of Image Watermarks"

[ICLR 2025] VideoShield: Regulating Diffusion-based Video Generation Models via Watermarking (Official Implementation)

[ICLR 2025] "Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances" (Official Implementation)

Official implementation of the paper "Watermark Anything with Localized Messages"

CopyrightMeter: Revisiting Copyright Protection in Text-to-image Models

Processed / Cleaned Data for Paper Copilot

This is the official repository of the paper SimMark. SimMark is a sentence-level watermarking algorithm that achieves state-of-the-art detection performance and robustness against paraphrasing, wi…

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

This repository contains the implementation for the paper "AquaLoRA: Toward White-box Protection for Customized Stable Diffusion Models via Watermark LoRA", accepted by ICML 2024.

This is an unofficial implementation of the Paper by Kejiang Chen et.al. on Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Models

《动手学深度学习》的MindSpore实现。供MindSpore学习者配合李沐老师课程使用。

A toolbox of vision models and algorithms based on MindSpore

MindSpore is a new open source deep learning training/inference framework that could be used for mobile, edge and cloud scenarios.