WeeLLM is a layer-streaming inference engine for large diffusion models (FLUX.2, Z-Image-Turbo, SDXL, SD1.5) that runs on under 4GB VRAM with zero quantization, streaming one trans...
Structured machine learning workflow for dataset preparation, model training, evaluation, and grid load forecasting, with organized notebooks and saved model artifacts to support r...
Python machine learning tool for forecasting game skin prices in 2026, combining gradient boosting, uncertainty measurements, and interpretable market insights in version 1.0.
Probability and statistics form the mathematical foundation of machine learning, helping quantify uncertainty in data and models. They support key tasks like inference, estimation,...
Browser-based AI security application using machine learning and behavioral analysis to detect, isolate, and mitigate ransomware, spyware, and emerging exploits in 2026.
Application Case Integrating Machine Learning and Deep Learning: Psychological Diagnosis Based on Text Analysis
Python machine learning project for unsupervised customer clustering, segment profiling, and affinity scoring, designed to support direct marketing analysis with configurable segme...
用 AI 大模型复刻聊天对象的本地对话 Agent：导入真实聊天记录，LLM 学习 TA 的语气、表情和回复节奏并以人物身份延续对话，支持语音、主动联系与长期记忆，数据全在本地。 | Clone anyone's texting style from real chat history: a local-first LLM agent that learns...
MCP server for Google Flow — image and video generation for Claude Code, Cursor and any MCP client. Runs on your own Google account: images free, video on your credits.
33 ways to spot AI-written text, right in your terminal. Before/after examples, draft checker, zero dependencies.
Camtasia 2026 is a professional screen recorder and video editor for tutorials, demos, and presentations. This repository includes a fully functional version with premium features ...
[NSDI' 27] Communication-Efficient Distributed Inference for Video Diffusion Models with Latent Parallelism
Evidence-aware on-prem LLM inference sizing and TCO calculator
让纯文本模型在 Codex 中无障碍调用内置看图工具（view_image）的方案，附为纯文本 LLM 设计的视觉工具包 ｜ Let text-only models call Codex's built-in view_image seamlessly, plus a vision toolkit designed for text-only LLMs.
给纯文本 LLM agent 装上眼睛：图片问答、OCR、截图分析、视觉定位、图转 SVG——一套视觉工具箱 + skill，并可无缝接入 Codex、Claude Code、OpenCode、Pi ｜ Give text-only LLM coding agents vision: image Q&A, OCR, screenshot understand...
一个可以让像deepseek-v4这样的纯文本模型, 在codex中无障碍调用内置看图工具(view_image)的方案，附为纯文本llm设计的视力工具包。
A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.
Official PyTorch implementation of lightweight speech enhancement with state-space modeling and depthwise separable convolution.
Labs, projects and verified credentials from the IBM Generative AI Engineering Professional Certificate
Desktop automation MCP server — computer use for any AI agent: control screen, windows, mouse/keyboard, and Chrome via Model Context Protocol (stdio)
A machine learning-based Credit Card Fraud Detection system that analyzes transaction data to identify fraudulent activities. Built with Python, Pandas, and Scikit-learn using a Ra...
Official implementation of AURORA-LM: Autoencoding Unified Representation for Continuous-Latent Diffusion Language Modeling.
Ноутбук для Гугл коллаба, в котором вы сможете к абсолютно любому медиа добавить субтитры и автоматически их первести на любой язык