Video Face Manipulation Detection Through Ensemble of CNNs

[CVPR] MARLIN: Masked Autoencoder for facial video Representation LearnINg

一个本地的基于内容的图像检索系统，实现了包括颜色特征提取（颜色直方图，HSV中心距），纹理特征（灰度共生矩阵，LBP算子），边缘特征（边缘直方图），哈希感知算法（aHash,pHash,dHash算法等），SIFT特征提取。以及基于VGG-16提取特征等功能

IFAKE is an application for detecting image and video forgery, designed to help users verify the authenticity of digital media. This repository also contains the AI model and dataset that we develo…

[CVPR 2023 (Highlight)] Self-Supervised Video Forensics by Audio-Visual Anomaly Detection

[Official] Exploring Temporal Coherence for More General Video Face Forgery Detection(ICCV 2021)

This projects aims in detection of video deepfakes using deep learning techniques like RestNext and LSTM. We have achived deepfake detection by using transfer learning where the pretrained RestNext…

A prize winning solution for DFDC challenge

This project is a real-time deepfake detection system implemented in PyTorch.

A comprehensive benchmark of deepfake detection

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, GLM4.5, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, Llava, GLM4v, Ph…

EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

Making large AI models cheaper, faster and more accessible

This is the official code of the publised paper 'A Multi-action Deep Reinforcement Learning Framework for Flexible Job-shop Scheduling Problem'

This repository is the official implementation of the paper “Flexible Job Shop Scheduling via Dual Attention Network Based Reinforcement Learning”. IEEE Transactions on Neural Networks and Learning…

收集各大AndroidTV的apk应用，可免费看vip和国外电影电视。如大家有也可以贡献一下。

LLM101n: Let's build a Storyteller

Production-ready platform for agentic workflow development.

ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括303个大模型，覆盖chatgpt、gpt-5、o4-mini、谷歌gemini-2.5、Claude4.5、智谱GLM-Z1、文心一言、qwen3-max、百川、讯飞星火、商汤senseChat、minimax等商用模型， 以及kimi-k2、ernie4.5、minimax-M1、DeepSeek-R1-0528、deepsee…

Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型

LLMX: 大语言模型微调工具，支持ChatGLM、Baichuan、LLama、Qwen、Yi等模型的预训练（PT）、微调（SFT）和偏好对齐（DPO）。

Firefly中文LLaMA-2大模型，支持增量预训练Baichuan2、Llama2、Llama、Falcon、Qwen、Baichuan、InternLM、Bloom等大模型

用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.

Inference code for Llama models

📢编译原理，java实现的词法分析器&语法分析器，有运行窗口💻，附带使用说明📗

规则引擎drools集成springboot