#
Starred repositories
Tensorflow implementation of DeepFM for CTR prediction.
一些经典的CTR算法的复现; LR, FM, FFM, AFM, DeepFM, xDeepFM, PNN, DCN, DCNv2, DIFM, AutoInt, FiBiNet,AFN,ONN,DIN, DIEN ... （pytorch, tf2.0）
原理解析及代码实战，推荐算法也可以很简单 🔥 想要系统的学习推荐算法的小伙伴，欢迎 Star 或者 Fork 到自己仓库进行学习🚀 有任何疑问欢迎提 Issues，也可加文末的联系方式向我询问！
Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷
Official code for "Improving 3D Imaging with Pre-Trained Perpendicular 2D Diffusion Models" (TPDM)
Segment Anything in Medical Images
Making large AI models cheaper, faster and more accessible
A very simple GRPO implement for reproducing r1-like LLM thinking.
🔥LeetCode solutions in any programming language | 多种编程语言实现 LeetCode、《剑指 Offer（第 2 版）》、《程序员面试金典（第 6 版）》题解
LeetCode Solutions: A Record of My Problem Solving Journey.( leetcode题解，记录自己的leetcode解题之路。)
A high-throughput and memory-efficient inference and serving engine for LLMs
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
Janus-Series: Unified Multimodal Understanding and Generation Models
《动手学大模型Dive into LLMs》系列编程实践教程
本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）
DiffBoost: Enhancing Medical Image Segmentation via Text-Guided Diffusion Model
A generative world for general-purpose robotics & embodied AI learning.
[ECCV2024] I-MedSAM: Implicit Medical Image Segmentation with Segment Anything
2025年全网最全即插即用模块，免费分享！CVPR2025，AAAI2025，ICLR2025，TNNLS2025，arXiv2025......包含人工智能全领域（机器学习、深度学习等），适用于图像分类、目标检测、实例分割、语义分割、全景分割、姿态识别、医学图像分割、视频目标分割、图像抠图、图像编辑、单目标跟踪、多目标跟踪、行人重识别、RGBT、图像去噪、去雨、去雾、去阴影、去模糊、超分辨…
WWW2025 Multimodal Intent Recognition for Dialogue Systems Challenge
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (Qwen2.5-VL, Qwen2.5-Omni, Qwen2-Audio, Ovis2, InternVL3, Llava, GLM4…
Qwen2.5-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
Causal Discovery in Python. It also includes (conditional) independence tests and score functions.
整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。
[TPAMI 2024] Measurement Guidance in Difffusion Models: Insight from Medical Image Synthesis
[MICCAI 24] The official code repository for paper "FairDiff: Fair Segmentation with Point-Image Diffusion".