- Shanghai
Highlights
- Pro
Stars
xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism
Recipes to train the self-rewarding reasoning LLMs.
The HiPIMS-FLAMEGPU Coupled Model Framework integrates the high-performance hydrodynamic modeling capabilities of HiPIMS with the flexible agent-based modeling environment of FLAMEGPU. This combine…
MMDepth: Comprehensive MMEngine-based Framework for Monocular, Stereo & Multi-view Depth Estimation
[Web demo version] Learn photography through AI-powered guidance, tutorials, and community feedback.
We introduce temporal working memory (TWM), which aims to enhance the temporal modeling capabilities of Multimodal foundation models (MFMs). This plug-and-play module can be easily integrated into …
Official implementation for "JL1-CD: A New Benchmark for Remote Sensing Change Detection and a Robust Multi-Teacher Knowledge Distillation Framework"
GENERator: A Long-Context Generative Genomic Foundation Model
【 ICLR 2025 】I2VControl-Camera: Precise Video Camera Control with Adjustable Motion Strength
[TPAMI2024] NCMNet: Neighbor Consistency Mining Network for Two-View Correspondence Pruning [CVPR2023] Progressive Neighbor Consistency Mining for Correspondence Pruning
Official Code of "GeReA: Question-Aware Prompt Captions for Knowledge-based Visual Question Answering"
A GPU-accelerated library for Tree-based Genetic Programming, leveraging PyTorch and custom CUDA kernels for high-performance evolutionary computation. It supports symbolic regression, classificati…
An intelligent development and testing platform designed to empower small and medium-sized enterprises to build their own R&D systems, streamline workflows, and enhance operational efficiency.
【NeurIPS 2022 Spotlight】Neural Surface Reconstruction of Dynamic Scenes with Monocular RGB-D Camera
一个超超超好用的 uniapp 开发框架:uni-plus 是由 Uniapp + Vue3 + TS + Vite + Pinia + Unocss + WotUi 驱动的跨端快速启动模板,使用 VS Code 开发,具有丰富的代码提示、错误校验、类型提醒、预先插件安装、代码片段等功能,而且拥有丰富的案例 echarts 图表,表单分页,权限控制、接口请求优化等等(配备搭建教程)
SVG Differentiable Rendering: Generating vector graphics using neural networks. Support: text-to-SVG, Image-to-SVG, SVG Editing.
Official code of the paper "Relational Representation Learning Network for Cross-Spectral Image Patch Matching"
"AutoAgent: Fully-Automated and Zero-Code LLM Agent Framework"
Dataset approched by A Benchmark and Frequency Compression Method for Infrared Few-Shot Object Detection
[ECCV 2024] Tuning-Free Image Customization with Image and Text Guidance
Simple & Efficient Desktop QR/Bar Code Scanner