Havuz

My complete journey to becoming an Agentic AI Engineer through structured learning, projects, experiments, and production-ready implementati

Studio-quality voice enhancement that never uploads your voice. Local, open-source alternative to cloud podcast enhancers.

Compose neural architectures as typed, executable graph cards with two-way PyTorch sync, step-by-step local execution, and a constrained AI

Implementation of LatentMoE,Toward Optimal Accuracy per FLOP and Parameter in Mixture of Experts (Elango et al., NVIDIA 2026) — in Pytorch.

[Preprint] TBSM: Three-Body Scattering for Generative Modeling.

Tiny local text-to-24x24 pixel art model, trained on roughly 200K samples in 30 minutes on an RTX 5090.

Watch a real AI model think - live 3D visualization of a transformer's actual forward pass: tokens, embeddings, attention, neurons, sampling

A mental-model-first field guide to Audio AI — from raw waveforms to production voice systems. Covers ASR, TTS, audio classification, Transf

The htop for LLM inference see exactly where every GB of VRAM goes and get measured quantization savings.

Jacobian-Brainwash : A manual alignment tool for large language models built on Anthropic's Jacobian Lens. Results are exportable.

Production-ready batch inference for Cohere’s Arabic/English ASR model, with optimized Silero VAD, multi-file GPU batching, subtitles, and o

AI-powered deepfake detector that classifies uploaded face images and videos as Real or Fake with confidence scores. Full-stack app built wi

To know what models don't say out loud.

Learn Agentic AI, Deep Learning, Agentic Engineering, RAG and Multi-Agent Workflows.

A stateful AI Intrusion Prevention System (IPS) that reassembles TCP packet fragments in sequence order and uses PyTorch deep learning model

🔥 AI agent that ports CUDA code to AMD ROCm using local LLMs — FastAPI + React + Ollama | Live: rocmporter-agent.vercel.app

🧠 One LLM, split across a Mac (Apple MPS) + a Windows PC (NVIDIA CUDA) — heterogeneous pipeline inference over a framework-neutral wire, bit

One embedding space for text, image, video, audio, thermal, motion, and touch. Open weights, self-hostable.

Self-Tuning Multi-Agent AI Trading System 2026: 8-Source Signal Fusion & Kronos Model

WarMatrix 2026: Next-Gen Tactical Simulation & AI Command Console

从 MiniMind 源码读起,再延伸到现代大模型技术体系的中文学习笔记。主线逐行精读预训练 / SFT / DPO / PPO / GRPO 与训练机制;附录 17 篇进阶卷覆盖量化、投机解码、RLHF 全景、模型代际史等 MiniMind 没涉及、但进阶绕不开的主题。

Train linear embedding adapters with triplet loss to align retrieval embeddings with your queries (RAG).

OpenAI-compatible multilingual TTS server — Chatterbox on vLLM with real-time PCM audio streaming, low time-to-first-byte (~0.7 s), voice cl

GleamLM大语言模型全栈训练平台——核心代码用 PyTorch 从零实现，最低仅需 12GB 消费级显卡即可完整训练，另有一套工业代码与手写实现消费同一份数据逐层对照。模型训练支持CLI和可视化训练。

A complete, structured end-to-end roadmap to become a versatile Generalist AI Engineer from Python/math foundations through ML/DL, CV, NLP,

Ultralytics YOLO26 quickstart for detection, instance and semantic segmentation, depth estimation, classification, pose, OBB, and tracking.

Ultralytics YOLOv8 discovery and quickstart for detection, segmentation, classification, pose, OBB, and tracking.

Ultralytics YOLO11 discovery and quickstart for detection, segmentation, classification, pose, OBB, and tracking.

Full-featured DAW, DJ, and VJ app interoperable w/Ableton, Reaper, Resolume & more. Stable Audio 3, Magenta RT2, Suno API, Chimera track fus

Agentic AI platform transforming passive CCTV into proactive railway safety intelligence. Real-time behavioural detection (suicide risk, pic

A practical lab for exploring Apple's Core AI framework, model assets, specialization, and on-device inference.

Open benchmark for expert collapse and routing efficiency in sparse MoE LLMs

A comprehensive hands-on, AI-first Python curriculum with 80+ interactive Jupyter notebooks for AI Engineers from core basics to LLMs, RAG,

Production-grade Machine Learning, Data Science & MLOps skills for AI coding agents (Codex, Claude Code, Cursor, OpenCode). One npx command

From teacher to tiles — a from-scratch LLM distillation & serving engine: custom Triton/CUDA kernels, FSDP distillation, paged-KV continuous

AI Auto Annotation & YOLO Training Pipeline, End-to-end object detection auto-labeling and YOLO training platform. VLM-powered annotation wi

👻 MoEWatch: A lightweight diagnostic and audit library for Mixture-of-Experts (MoE) models in HuggingFace Transformers — the pytest for MoE

Open-source CLI, API, web UI, and reproducible benchmarks for probabilistic AI-generated image detection.

Official Implementation of LongLive-RAG: A general retrieval-augmented framework for long video generation.

Unofficial fairseq-free PyTorch implementation of UTMOS (v1, 2022), matching the original system.

Train decoder-only language models from scratch with PyTorch, featuring RoPE, RMSNorm, SwiGLU, and SDPA

[ICML 2026] NanoQuant: Efficient Sub-1-Bit Quantization of Large Language Models

让 MinerU 在 AMD 显卡上以 vLLM + hybrid-auto-engine 满血运行！ 本项目是对官方文档中 AMD/ROCm 生态支持的有效补充。针对 MinerU 3.x 提供了一套完整的 ROCm 7.x + PyTorch 2.11.0 + vLLM 源码

Building a small LLM in PyTorch from scratch - a step-by-step journey inspired by Stanford CS336.

FSQ K-line foundation model for China A-share stock selection, with a containerised multi-factor research platform: data governance, factor

Production-ready, bleeding-edge, upstream-first vLLM Docker image for the NVIDIA DGX Spark (GB10 / sm_121a), verified against real models on

Confucius4-TTS: a Multilingual and Cross-Lingual Zero-Shot TTS Engine

Bilingual (中文+EN) ML / LLM / diffusion / agent interview cheat sheets for AI 秋招 — generated by ARIS /interview-cheatsheet, rendered by /rend