spatial-vqa-bench

Spatial-VQA-Bench: a focused benchmark of spatial visual reasoning for multimodal LLMs.

speech-tokenizer-arena

A side-by-side benchmarking playground for discrete speech tokenizers (EnCodec, HuBERT-units, SpeechTokenizer, etc.).

PhenoPixel

An OpenCV based image analysis web application (Deployed at Hiroshima University)

PilotDeck

Task-oriented AI Agent productivity platform — redefining operational boundaries and memory evolution, one WorkSpace at a time.     English | 简体中文 Website · Live Demo · Tutorial · Quick Start · Highlights · Use Cases · Community --- **Ne

audio-vis-align

Training and evaluation toolkit for audio-visual contrastive representation alignment (CLIP-style, but for audio + video).

tts-prosody-probe

Probe and compare the prosody (pitch / energy / duration) of TTS outputs.

uni-mm-trainer

A small library for training multimodal LLMs combining text, vision, and audio

SAM3DBody-cpp

Real-time 3D full-body reconstruction from a single camera, Multiperson BVH output, Pure C++ runtime, ONNX + ggml, 70-joint skeleton with hands.

make-x-great-again

Make X Great Again 少看垃圾，多看人话。 你照常刷 X，AI 在后台把广告号和色情 bot 挑出来 · Chrome 扩展 · AGPL-3.0 开源 🟦 从 Chrome 商店安装 · 🌐 官网门户 · 📋 公共名单 · 📦 GitHub Release --- 这个项目要解决什么 X 现在的问题，大家都知道： - 评论区一半是广告号和色情 bot，正常讨论被刷到底 - 想关注一个新人，分不清是真号还是水军 - 算法决定你看到谁，而不是你决定 - 看一个人聊过什么、最热几条是什么——只能

Genspark-AI

Genspark AI open-source, self-hosted Super Agent. Free alternative to Genspark.ai with multi-agent orchestration, deep research, Sparkpages, AI slides & sheets, image generation and 80+ tools. One-command Windows install. Run locally with any LLM (OpenAI, Anthropic, Gemini, Ollama)

linux-devmgmt

A faithful recreation of the Windows Device Manager built with Qt6 and real hardware backends via sysfs/procfs. Best enjoyed with AeroThemePlasma, but looks great on regular KDE as well.

flashlib

Fast and memory-efficient classical machine learning operators