Multi-engine long-term memory for game AI agents. Deep Godot 4.7+ (99 skills, 27 genre blueprints) + Bevy docs-first parity — audited patterns, persona orchestration (Analyst · Auditor · Builder), production-grade engineering.
Repository Index
132,218 visible repositories in the index
2,209–2,232 of 3,447 · Most stars
3D mesh stylization driven by a text input in PyTorch
An Automatic Prompt Optimization Framework for Large Language Models
A production-oriented AI workflow runtime for building, validating, recovering, and shipping complex AI workflows as dependable services. 面向生产的 AI 工作流运行时:快速开发、验证和恢复复杂 AI 工作流,并将其稳定交付为服务。
(Linear-chain) Conditional random field in PyTorch.
- pytorch
- neural-networks
- conditional-random-fields
This repository implements a demo of the networks described in "How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)" paper.
- face-alignment
- torch7
- 3d-face-alignment
- deeplearning
The most robust observability solution for Salesforce experts. Built 100% natively on the platform, and designed to work seamlessly with Apex, Lightning Components, Flow, OmniStudio, and integrations.
- salesforce
- salesforce-developers
- salesforce-admins
- apex
OmniXAI: A Library for eXplainable AI
- explainable-ai
- explainable-ml
- interpretable-machine-learning
- machine-learning
An Intelligent wordlist generator based on user profiling, permutations, and statistics. (Named after the same tool in Mr.Robot series S01E01)
- elliot
- cupp
- passwords
- hacking-tool
An AI-powered personal productivity system where knowledge management and daily task planning are intelligently orchestrated by your AI assistant.
NequIP is a code for building E(3)-equivariant interatomic potentials
- machine-learning
- atomistic-simulations
- molecular-dynamics
- computational-chemistry
The complete post-training stack for LLMs, plus RL for any problem. SFT, DPO and multi-turn agentic RL, with evolutionary hyperparameter optimization built in.
- reinforcement-learning
- deep-reinforcement-learning
- deep-learning
- machine-learning
Tutorial for video classification/ action recognition using 3D CNN/ CNN+RNN on UCF101
- action-recognition
- video-classification
- pytorch-tutorial
- cnn
Code for paper " AdderNet: Do We Really Need Multiplications in Deep Learning?"
- pytorch
- imagenet
- convolutional-neural-networks
- cvpr2020
PyTorch code for EMNLP 2019 paper "LXMERT: Learning Cross-Modality Encoder Representations from Transformers".
Extremely fast file change detector and task orchestrator for Node.js.
- file
- watch
Pytorch implementation of Feature Pyramid Network (FPN) for Object Detection
[NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning; [NeurIPS 2022] MCUNetV3: On-Device Training Under 256KB Memory
- c
- codegenerator
- cpp
- deep-learning
PINNs-Torch, Physics-informed Neural Networks (PINNs) implemented in PyTorch.
- cuda-graph
- jit-compiler
- physics-informed-neural-networks
- pinns
PyGCL: A PyTorch Library for Graph Contrastive Learning
- contrastive-learning
- graph-representation-learning
- machine-learning
- graph-contrastive-learning
Official implementation of HARL algorithms based on PyTorch.
Termcolor is a header-only C++ library for printing colored messages to the terminal. Written just for fun with a help of the Force.
Deep Reinforcement Learning toolkit: record and replay cryptocurrency limit order book data & train a DDQN agent
- bitfinex
- multiprocessing
- mongodb
- orderbook
天池中药说明书实体识别挑战冠军方案;中文命名实体识别;NER; BERT-CRF & BERT-SPAN & BERT-MRC;Pytorch