The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement …

用于贝叶斯神经网络的不确定性量化方法合集

四种强化学习算法在“CartPole-v1”游戏中的表现，包括DQN/DDQN/PolicyGradient/ActorCritic。

Qwen Code is a coding agent that lives in the digital world.

Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.

A lightweight, portable pure C99 onnx inference engine for embedded devices with hardware acceleration support.

HAZARD challenge

An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

Awesome machine learning for combinatorial optimization papers.

True Detective: Challenging Benchmark for Deep Abductive Reasoning in Foundation Models

The Birth of the Modern Detective Story (BMDS) Dataset

[NeurIPS 2024] Official pytorch implementation of SPLAT

A MIT-licensed, deployable starter kit for building and customizing your own version of AI town - a virtual town where AI characters live, chat and socialize.

Open-source search and retrieval database for AI applications.

TurtleBench: Evaluating Top Language Models via Real-World Yes/No Puzzles.

Code and documentation to train Stanford's Alpaca models, and generate the data.

Source code for "Packed Levitated Marker for Entity and Relation Extraction"

Situational Awareness Dataset

Python wrapper for Stanford CoreNLP.

High-resolution models for human tasks.

基于 TensorRT 的 C++ 高性能单目标跟踪推理，支持算法OSTrack、LightTrack。

small c++ library to quickly deploy models using onnxruntime

CMake Cookbook recipes.

High-performance Inference and Deployment Toolkit for LLMs and VLMs based on PaddlePaddle

Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark (CVPR 2021)

OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.

VMamba: Visual State Space Models，code is based on mamba

[ICML 2024] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

Mamba SSM architecture