kpsss34/Walkyrie-1.3B: Walkyrie is a Text-to-Image diffusion model
Walkyrie is a Text-to-Image diffusion model
Walkyrie is a Text-to-Image diffusion model
Autonomous self-evolving agents. Vision-grounded layered memory and self-written skills for LLM agents that operate your computer.
My implementations and Turkish notes from Andrej Karpathy's Neural Networks: Zero to Hero series.
AI Agent skills for a structured catalog of 100k+ US professional-services firms
Kalshi prediction markets trading bot algorithmic automated trading TypeScript Node.js Kalshi REST API RSA signing OpenRouter LLM CLI npm quant fintech event contracts market makin...
From-scratch, paper-faithful PyTorch implementation of DeepSeek-V4 core architecture for transparent study, testing, ablation, and mini-scale training.
This project focuses on predicting the future spread of COVID-19 using data analysis and machine learning techniques
A curated, public-facing list of Python audio science, scientific audio research, music information retrieval, DSP, machine learning audio, datasets, notebooks, and creator-audio t...
A structured audit framework for ML pipelines. 14 stages, 100+ checks, and every leakage pattern that silent model failures are made of.
[CVPR2026] LeapAlign: Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories
Multi-role chain-of-thought LLM pipeline for Solidity security auditing, layered on top of Slither output.
A benchmark for evaluating LLM reasoning on Ethereum and DeFi tasks
True AI-Native Browser — a VLM reads the HTML and hallucinates the page.
AI-driven user testing for iOS Simulator, macOS apps, and web apps. Write a goal in plain language; an LLM agent drives the UI and reports friction. macOS 14+, Swift 6.
Use the GPU's idle NVENC silicon to multiply the effective bandwidth of every PCIe wire on the board
Build a modern LLM from scratch. Every line commented. Explained like we are five.
Hands-on demos for the Pluralsight course: Generative AI Data Privacy and Safe Use for Developers. Covers PII masking, prompt injection attacks and defenses, five guardrail rail ty...
Snoolink Lens is an Electron desktop app that scans media folders, indexes image and video metadata, and enables fast semantic search with practical filters. It also helps you gene...
A Claude skill for slides that don't look like AI made them. Brand DNA × 20 codified design principles.
Two-stage semantic language modeling with DIL surface-to-meaning encoding and NAZ meaning-to-meaning generation.
A lightweight local tool for GPT-Image-2 generation and image-to-image workflows.
Red-Teaming Text-to-Image Models via In-Context Experience Replay and Semantic-Preserving Prompt Rewriting
Dataset preprocessing tool for diffusion model training