[SIGGRAPH 2026] Pixal3D: Pixel-Aligned 3D Generation from Images

A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎，预测万物

Open-source, low-cost 10.5 GHz PLFM phased array RADAR system

Kolmogorov Arnold Networks

Python Gaze Estimation application and Computer Pointer Controller created using Intel's OpenVINO Machine Learning toolkit

Java interface for fastText

Voice activity detection (VAD) library, based on WebRTC's VAD engine

Voice activity detection (VAD) toolkit including DNN, bDNN, LSTM and ACAM based VAD. We also provide our directly recorded dataset.

💰 A Mina Protocol Desktop Wallet

A SOTA Industrial-Grade Voice Activity Detection & Audio Event Detection, supporting 100+ languages, outperforming Silero-VAD, TEN-VAD, FunASR-VAD and WebRTC-VAD

Official implementation of Kimodo, a kinematic motion diffusion model for high-quality human(oid) motion generation.

Open-Source Frontier Voice AI

provides Rust interface of fetching youtube live chat comments

Transformer related optimization, including BERT, GPT

Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

Scalable, reliable, distributed storage system optimized for data analytics and object store workloads.

Java library used to generate Java source files.

termai: Rust terminal AI assistant using OpenAI APIs for intelligent CLI interactions.

Official front-end implementation of ComfyUI

Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.

LLM inference in C/C++

Fast, flexible LLM inference

Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

The Modular Platform (includes MAX & Mojo)

3D Reconstruction of Indoor Scenes with a Generative Framework

The repository provides code for running inference with the Meta Segment Anything Audio Model (SAM-Audio), links for downloading the trained model checkpoints, and example notebooks that show how t…

Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"

A distribution of Linux Virtual Server with some advanced features. It introduces a new packet forwarding method - FULLNAT other than NAT/Tunneling/DirectRouting, and defense mechanism against synf…

For Polllen detect