ddikong
Follow
Stars
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Inference-Time Alignment in Protein Diffusion Models
Awesome lists about framework figures in papers
Development of a GAN for image denoising in photoacoustic imaging
Implementation of various image-to-image translation models for photoacoustic imaging reconstruction.
[NeurIPS'22] PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies
[NeurIPS 2024 Best Paper][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ult…
A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.
A Modular Framework for 3D Gaussian Splatting and Beyond
Official code for NeRF-US: Removing Ultrasound Imaging Artifacts from Neural Radiance Fields in the Wild
[ICLR24] Official implementation of the paper “MagicDrive: Street View Generation with Diverse 3D Geometry Control”
AIInfra（AI 基础设施）指AI系统从底层芯片等硬件，到上层软件栈支持AI大模型训练和推理。
AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术
Photoacoustic (PA) imaging can revolutionize medical ultrasound by augmenting it with molecular information. However, clinical translation of PA imaging remains a challenge due to the limited viewi…
Python Package for Reflection Ultrasound Computed Tomography (RUCT) Delay And Sum (DAS) Algorithm
No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images
[SIGGRAPH Asia 2024 (Journal Track)] StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal
[NeurIPS 2024 Spotlight]"LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS", Zhiwen Fan, Kevin Wang, Kairun Wen, Zehao Zhu, Dejia Xu, Zhangyang Wang
Gensis is a lightweight deep learning framework written from scratch in Python, with Triton as its backend for high-performance computing.
This is a collective repository for all 3DGS related progresses in research and industry world
[CVPR'24 Oral] Official repository of Point Transformer V3 (PTv3)
Official repository of MICCAI 2023 TDSC-ABUS challenge
[NeurIPS 2024] Learning from Pattern Completion: Self-supervised Controllable Generation
This method, named the sliding Gaussian ball adaptive growth (SlingBAG) algorithm, enables high-quality 3D large-scale PA reconstruction with fast iteration and extremely less memory usage.