A Keras implementation of CapsNet in NIPS2017 paper "Dynamic Routing Between Capsules". Now test error = 0.34%.
- keras
- capsnet
- capsule
- capsnet-keras
111,821 visible repositories in the index
2,065–2,088 of 7,326 · Most stars
A Keras implementation of CapsNet in NIPS2017 paper "Dynamic Routing Between Capsules". Now test error = 0.34%.
Next-Token Prediction is All You Need
Official PyTorch implementation of One-Minute Video Generation with Test-Time Training
Reproduce R1 Zero on Logic Puzzle
Less rage, more chill.
verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"
Battle-tested agent skills mapping the footguns of Kotlin, Compose Multiplatform and the desktop JVM — mined from a production music app, not from documentation.
[ICLR 2020] Contrastive Representation Distillation (CRD), and benchmark of recent knowledge distillation methods
ATLAS by General Intelligence Capital — Self-improving AI trading agents using Karpathy-style autoresearch
the terminal client for LLMs
Reconstruct and validate C/C++ code from compiled programs with AI.
Permanent memory for AI agents. A 426-token prompt, a script, plug and play.
SDG is a specialized framework designed to generate high-quality structured tabular data.
A lightweight suite of motion imitation methods for training controllers.
AssetOpsBench - Industry 4.0: A unified benchmark and framework for building, orchestrating, and evaluating domain-specific AI agents for Industry 4.0 asset operations and maintenance, with 460+ scenarios, 5 specialist agents (IoT, FMSR, TSFM, Work Order,...), and multi-agent orchestration blueprints (MetaAgent, AgentHive) over MCP.
A deep matching model library for recommendations & advertising. It's easy to train models and to export representation vectors which can be used for ANN search.
Generate generic activity streams from the actions on your site. Users can follow any actors' activities for personalized streams.
agentUniverse is a LLM multi-agent framework that allows developers to easily build multi-agent applications.
NeuroKit2: The Python Toolbox for Neurophysiological Signal Processing
Python & JS/TS SDK for running AI-generated code/code interpreting in your AI app
Seamlessly integrate LLMs as Python functions
The official CLI for Agentic Document Extraction (ADE) by LandingAI — parse documents and extract schema-shaped data from your terminal
AI agents running research on single-GPU nanochat training automatically adopted for MacOS
Stealing Signatures and Making One Invalid Signature at a Time