Project Page For "Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement"
- reasoning-language-models
- reinforcement-learning
- segmentation
- multimodel-large-language-model
131,939 visible repositories in the index
60,289–60,312 of 81,218 · Most stars
Project Page For "Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement"
[Windows Anti-Rootkit] KSword 5.1 is an source-available Windows toolkit for ARK, kernel debugging, and system forensics. KSword 5.1 是面向 Windows 的源码可见 ARK、内核调试与系统取证工具集。
A sd-webui extension for utilizing DanTagGen to "upsample prompts".
A SwiftUI library for presenting views as popups, much like the Apple Music and Podcasts apps.
grass-mining
小红书无压缩无水印原图下载器
The repository host gives no description.
Agentic CAD for 3D printing
Steeltoe samples and reference application collection
Books and other resources
Checks if a Minecraft player has a valid paid account. If so, they can skip offline authentication automatically. (premium auto login)
This library augments road images to introduce various real world scenarios that pose challenges for training neural networks of Autonomous vehicles. Automold is created to train CNNs in specific weather and road conditions.
A Telegram bot with a silky smooth AI experience. UI enabled.
The repository host gives no description.
📊 Circular and Rectangular Manhattan Plot
苹方字体(经转换可在Windows系统安装使用)| PingFang extracted in OTF for Windows
React component for building interactive diagrams.
Powerful multi-threaded coroutine dispatcher and parallel execution engine
Example of using micro-frontends in a React Native mobile app with Re.Pack to create a Super App.
An introduction to Active Directory security
Monitor ESXi, Synology, Docker, PiHole and Raspberry Pi and Windows using Grafana, InfluxDB and Telegraf
A curated list of .NET Compiler Platform ("Roslyn") diagnostic analyzers and code fixes. Everyone can contribute here!
Web framework for Zig that leverages dependency injection for clean, modular application development.
VITS2: Improving Quality and Efficiency of Single-Stage Text-to-Speech with Adversarial Learning and Architecture Design