AI 开源项目榜。

Official code for CVPR2022 paper: Depth-Aware Generative Adversarial Network for Talking Head Video Generation

RetinaNet in PyTorch

日本語UIをAIエージェントに正しくつくらせるためのDESIGN.md集。Japanese DESIGN.md collection for AI agents — extending Google Stitch format with CJK typography.

:art: A CNN visualizer

Working, locally-running, low-cost implementation of Generative Agents: Interactive Simulacra of Human Behavior.

Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models

A CPU+GPU Profiling library that provides access to timeline traces and hardware performance counters.

[ACL2023] We introduce LLM-Blender, an innovative ensembling framework to attain consistently superior performance by leveraging the diverse strengths of multiple open-source LLMs. LLM-Blender cut the weaknesses through ranking and integrate the strengths through fusing generation to enhance the capability of LLMs.

Academic Survey Paper Generation.

Framework-agnostic implementation for state-of-the-art saliency methods (XRAI, BlurIG, SmoothGrad, and more).

Perception toolkit for sim2real training and validation in Unity

Visualization framework for autonomy and robotics data encoded in XVIZ

Pretrained model hub for Keras 3.

A cool, modern and responsive django admin application based on bootstrap 5 that brings AI to the Django admin - https://baton.sqrt64.it/

An AI-powered smart vocabulary tool with features like One-click vocabulary building and story-based memorization.

Fetch X/Twitter tweets, replies, timelines, and articles without login or API keys — field tool for AI agents.

This app can now use Android, just like a human.

llama3.np is a pure NumPy implementation for Llama 3 model.

Texture synthesis from examples

PyTorch Library for Active Learning to accompany Human-in-the-Loop Machine Learning book

Offical PyTorch implementation of "BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework"

A codebase wiki for AI coding agents. Captures what the code can't say: decisions, flows, invariants, gotchas.

A self-supervised learning framework for audio-visual speech

High level network definitions with pre-trained weights in TensorFlow

The Electricity Transformer dataset is collected to support the further investigation on the long sequence forecasting problem.

Agentic Hours-Long Video Editing via Music Synchronization

提供产品级IOCR自定义模板识别，以图搜图，人像搜索等，免费，可商用，Java AI 人工智能一站式解决方案，为工作减负，为产品研发加速。项目类别包括：以及AI SDK，web应用等。

Code for "TD-MPC2: Scalable, Robust World Models for Continuous Control"

A simple Langchain RAG application.