Stars
DeepEP: an efficient expert-parallel communication library
Production-Ready MCP Server Framework • Build, deploy & scale secure AI agent infrastructure • Includes Auth, Observability, Debugger, Telemetry & Runtime • Run real-world MCPs powering AI Agents
🎒 Token-Oriented Object Notation (TOON) – JSON for LLM prompts at half the tokens. Spec, benchmarks & TypeScript implementation.
[ICCV 2025] SCFlow: Implicitly Learning Style and Content Disentanglement with Flow Models
A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.
Collection of extracted System Prompts from popular chatbots like ChatGPT, Claude & Gemini
Scikit-learn compatible library for molecular fingerprints and chemoinformatics
The main repo for NLWeb, implemented in Python.
HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation
Oficjalne repozytorium drugiej edycji ogólnopolskiej Olimpiady Sztucznej Inteligencji
The collection of awesome papers on alignment of diffusion models.
Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference
The open-source CapCut alternative
Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.
Type-safe TypeScript SDK for docling-serve with first-class Bun support. The client is generated from the official OpenAPI schema and wraps every endpoint with a small, DX-focused API surface.
Evaluating text-to-image/video/3D models with VQAScore
[NeurIPS 2025] Hybrid Latent Reasoning via Reinforcement Learning
Hierarchical Reasoning Model Official Release
Official Repository of Absolute Zero Reasoner
A curated list of events, hackathons, and communities focused on AI and tech in Poland
Flash Attention from scratch in triton.