Repositories

adityaaryaman25/Hand_Cricket.ML: ML Hand Cricket is a computer vision game that reads webcam hand gestures as player moves. Using machine learning, it analyzes each player’s patterns to predict their next move. Unique player IDs and learning profiles let the AI adapt over time, with adjustable difficulty and an interactive interface.

ML Hand Cricket is a computer vision game that reads webcam hand gestures as player moves. Using machine learning, it analyzes each player’s patterns to predict their next move. Un...

hevnsnt/CVEngine: AI-first external attack surface assessment with continuous discovery, evidence-based vulnerability validation, and developer-agent MCP integration.

AI-first external attack surface assessment with continuous discovery, evidence-based vulnerability validation, and developer-agent MCP integration.

Xainner/media-lab: Media Lab — your own self-hosted AI media studio: image, video with audio, music, voice and an agent, on your GPUs

Media Lab — your own self-hosted AI media studio: image, video with audio, music, voice and an agent, on your GPUs

anonnerdfrenzy/survival-llm: A free AI assistant and survival library that runs on your own computer, with no internet needed. Shows the source of every answer.

A free AI assistant and survival library that runs on your own computer, with no internet needed. Shows the source of every answer.

routerhubSI/uncensored-ai-api: Uncensored AI API and models — one key for Claude, GPT, Gemini, Grok, DeepSeek, GLM and Qwen, with uncensored and abliterated variants where available. OpenAI- and Anthropic-compatible. Pay per token.

Uncensored AI API and models — one key for Claude, GPT, Gemini, Grok, DeepSeek, GLM and Qwen, with uncensored and abliterated variants where available. OpenAI- and Anthropic-compat...

xuanqi99/MUSE-Code: Official PyTorch implementation of "Revisiting Diffusion Fine-Tuning for Unsupervised Domain Adaptation" (NeurIPS 2026).

Official PyTorch implementation of "Revisiting Diffusion Fine-Tuning for Unsupervised Domain Adaptation" (NeurIPS 2026).

luo11creator/deepfake_fight: 近年来，以深度伪造（Deepfake）为代表的生成式人工智能技术进入爆发式增长阶段。在人脸方面，基于生成对抗网络（GAN）、自编码器与扩散模型（Diffusion）的换脸、人脸重建、人脸编辑技术已经能够生成肉眼难以分辨的伪造图像与视频。为此，我们自研了 GuardFusion 多模态融合检测模型， 在模型结构上，我们首先通过投影层将视觉 1280 维、音频 32 维、文本 512 维的差异化特征，统一映射至 256 维公共特征空间， 同时创新引入瓶颈融合 Transformer 机制，摒弃传统全量跨模态注意力的高开销结构，通过少量可学习瓶颈 Token 完成跨模态信息交互，将计算复杂度从 O(N²) 降至 O(3·N·B)。在保留多模态融合能力的同时，大幅轻量化模型。

近年来，以深度伪造（Deepfake）为代表的生成式人工智能技术进入爆发式增长阶段。在人脸方面，基于生成对抗网络（GAN）、自编码器与扩散模型（Diffusion）的换脸、人脸重建、人脸编辑技术已经能够生成肉眼难以分辨的伪造图像与视频。为此，我们自研了 GuardFusion 多模态融合检测模型， 在模型结构上，我们首先通过投影层将视觉 1280 维、音频 ...

Barry81-666/kaggle-portfolio: Curated Kaggle projects in computational biology, medical imaging, data science and machine learning.

Curated Kaggle projects in computational biology, medical imaging, data science and machine learning.

xuanqi99/VT-DUDA-Code: Official PyTorch implementation of "VT-DUDA: Visual Token Conditioning for Diffusion-guided Unsupervised Domain Adaptation" (TMLR 2026).

Official PyTorch implementation of "VT-DUDA: Visual Token Conditioning for Diffusion-guided Unsupervised Domain Adaptation" (TMLR 2026).

google-deepmind/detectorscope: Build AI text detectors whose decisions are mechanistically grounded and human-auditable (EMNLP 2026)

Build AI text detectors whose decisions are mechanistically grounded and human-auditable (EMNLP 2026)

Rageshwaran13/precision-cardiology-digital-twin: Cardiac digital twin combining synthetic EHR data, wearable signals, machine learning and an interactive 3D heart dashboard.

Cardiac digital twin combining synthetic EHR data, wearable signals, machine learning and an interactive 3D heart dashboard.

PRITHIVSAKTHIUR/flux-3-image-klein-loras-fast: flux-3-image-klein-loras-fast is an interactive image editing, text-to-image synthesis, and dynamic LoRA execution studio powered by the black-forest-labs/flux-3-image-klein Distilled architecture (ModularPipeline).

flux-3-image-klein-loras-fast is an interactive image editing, text-to-image synthesis, and dynamic LoRA execution studio powered by the black-forest-labs/flux-3-image-klein Distil...

tony2marseille-droid/N-o: Neo - assistant IA 100 % local : chat multi-agents, generation d'images 4K (FLUX), 3D imprimable, RAG documents, voix francaise, Telegram. Rust + React + Ollama, aucun cloud, aucune donnee envoyee.

Neo - assistant IA 100 % local : chat multi-agents, generation d'images 4K (FLUX), 3D imprimable, RAG documents, voix francaise, Telegram. Rust + React + Ollama, aucun cloud, aucun...

Nikita-Sherstnev/Visage-Image: A small text-to-image diffusion model focused on realistic face generation.

A small text-to-image diffusion model focused on realistic face generation.

xiaozhangup/Oh-My-McDonald: 基于麦当劳官方 MCP 的对话式 AI Skill，支持餐品推荐、门店比价、优惠查询、营养计算和探索记录，并通过 Python 生成体素风格分享图片。

基于麦当劳官方 MCP 的对话式 AI Skill，支持餐品推荐、门店比价、优惠查询、营养计算和探索记录，并通过 Python 生成体素风格分享图片。

hitgalani/EV_Battery_Health_Prediction: ML project that predicts EV battery State of Health (SoH, %) using Simple and Multiple Linear Regression in Python (pandas, numpy, matplotlib, seaborn, scikit-learn). Follows the ML life cycle. Uses a synthetic Kaggle dataset.

ML project that predicts EV battery State of Health (SoH, %) using Simple and Multiple Linear Regression in Python (pandas, numpy, matplotlib, seaborn, scikit-learn). Follows the M...

DavidDingXu/hello-llm: 《手写小模型，看懂大模型》：原创语言模型入门课程，20 讲图解与代码、23 支配套视频、浏览器训练实验和离线电子书。

《手写小模型，看懂大模型》：原创语言模型入门课程，20 讲图解与代码、23 支配套视频、浏览器训练实验和离线电子书。

rddmwmddr/android-ad-cleaner: 关掉国产安卓手机系统里的广告、热搜、资讯推荐和营销推送。不 root，可还原，支持 AI 智能体一键执行。

关掉国产安卓手机系统里的广告、热搜、资讯推荐和营销推送。不 root，可还原，支持 AI 智能体一键执行。

maggujyoti/Python-Machine-Learning-Deep-Learning-YT-Tutorials: Google Colab notebooks and practical coding examples for Machine Learning and Deep Learning tutorials by Learn with Dr. Jyoti YouTube Channel

Google Colab notebooks and practical coding examples for Machine Learning and Deep Learning tutorials by Learn with Dr. Jyoti YouTube Channel

zgx949/ai-pojia: 用 AI 搞定麻烦事。面向小白的实用 Skills 与插件，附完整教程和示例。

用 AI 搞定麻烦事。面向小白的实用 Skills 与插件，附完整教程和示例。

wlnhnoqefoxt/adult-ai-video: AI adult video generator: text-to-clip diffusion, image-to-video motion, 4K NSFW output, uncensored model presets

AI adult video generator: text-to-clip diffusion, image-to-video motion, 4K NSFW output, uncensored model presets

Rex-YinRX/machine-learning-in-c: No description

YiFeng-lab/ai-ethics-debate-coach: A Socratic AI ethics debate coach for generative AI literacy — conversation design, knowledge grounding and reflection.

A Socratic AI ethics debate coach for generative AI literacy — conversation design, knowledge grounding and reflection.

Cattmonkey/ChaosIntelligence: 把智能体当函数，把想法写成程序。Agent-native functional language with a CLI, Web IDE, goal-driven bots and live UI. Source-available; no AI training.

把智能体当函数，把想法写成程序。Agent-native functional language with a CLI, Web IDE, goal-driven bots and live UI. Source-available; no AI training.