LLM-as-a-Verifier is a general-purpose framework that provides fine-grained feedback for any agent without requiring additional training. It achieves SOTA performance across coding, robotics, and medical agentic benchmarks.
Repository Index
142,273 visible repositories in the index
649–672 of 3,312 · Most stars
Official pytorch implementation of the paper: "SinGAN: Learning a Generative Model from a Single Natural Image"
- singan
- gan
- official
- single-image
An #OSINT Framework to perform various recon techniques on Companies, People, Phone Number, Bitcoin Addresses, etc., aggregate all the raw data, and give data in multiple formats.
The OCR approach is rephrased as Segmentation Transformer: https://arxiv.org/abs/1909.11065. This is an official implementation of semantic segmentation for HRNet. https://arxiv.org/abs/1908.07919
- segmentation
- semantic-segmentation
- cityscapes
- pascal-context
Platform Security Assessment Framework
Leaderboard Comparing LLM Performance at Producing Hallucinations when Summarizing Short Documents
- generative-ai
- hallucinations
- llm
A Markdown browser for your terminal
- markdown
- markdown-viewer
- python
- terminal-based
PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis
A Python command-line and library that draws basic graphs in the terminal
:musical_note: The original MusicBot for Discord (formerly SexualRhinoceros/MusicBot)
- discord
- python
- musicbot
- hacktoberfest
Implementation of MusicLM, Google's new SOTA model for music generation using attention networks, in Pytorch
- artificial-intelligence
- attention-mechanisms
- deep-learning
- music-synthesis
Archivy is a self-hostable knowledge repository that allows you to learn and retain information in your own personal and extensible wiki.
- elasticsearch
- knowledge
- productivity
- python
Barman - Backup and Recovery Manager for PostgreSQL
Python 3 API wrapper for Garmin Connect to get statistics and set activities
- fitness
- garmin
- garmin-connect
- garmin-sdk
Open-source companion agents, and the community that raises them: realtime voice & vision, long-term memory, Live2D / 3D avatars, game companions, social visits and a plugin market. 🐱开源的伙伴 Agent,和一个人与猫娘共同生活的社区。
- waifu
- own-your-data
- proactive-agent
- proactive-ai
Modding platform for GI, HSR, WW and ZZZ
基于深度强化学习的开源自动因子工厂。
[CVPR 2025] MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors
- computer-vision
- robotics
- slam
- cvpr2025
Pixel graphics in terminal with unicode braille characters
Curated tools, case studies and papers for reverse engineering websites, games, apps, binaries, firmware and protocols. Source-reviewed, English and Chinese.
- agent-skills
- ai-agents
- awesome-list
- ghidra
Cross-platform text editor, written in Free Pascal
- lazarus
- text-editor
- pascal
- cross-platform
This repository includes the official project of TransUNet, presented in our paper: TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation.
Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.
- deep-learning
- gpu
- python
- jittor
[IROS 2025 Best Paper Award Finalist & IEEE TRO 2026] The Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems
- robotic-manipulation
- vision-language-action-model
- pretraining-for-robotics
- robotic-foundation-model