VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model
- embodied-ai
- robotics
- vision-language-action-model
89,572 visible repositories in the index
1,993–2,016 of 5,000 · Most stars
VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model
The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foundation Model..."
:boar: :bear: Deep Learning based Python Library for Stock Market Prediction and Modelling
[CVPR 2025 Highlight] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos
A Flow-based Generative Network for Speech Synthesis
An interactive, terminal-based markdown presenter
A large-scale face dataset for face parsing, recognition, generation and editing.
A very simple BiLSTM-CRF model for Chinese Named Entity Recognition 中文命名实体识别 (TensorFlow)
A Python library for audio data augmentation. Useful for making audio ML models work well in the real world, not just in the lab.
Refine and quantize messy AI pixel art into clean, perfect pixels.
A (PyTorch) imbalanced dataset sampler for oversampling low frequent classes and undersampling high frequent ones.
AALC,PC端Limbus Company小助手。AALC,Limbus Company Assistant on PC
Agent skill: design any process, idea, or problem into an ICM workspace (folder structure as agent architecture), or restructure an existing folder into one
Home Assistant integration framework for (garbage collection) schedules
🔮 Instill Core is a full-stack AI infrastructure tool for data, model and pipeline orchestration, designed to streamline every aspect of building versatile AI-first applications
Filters to block and remove copycat-websites from DuckDuckGo, Google and other search engines. Specific to dev websites like StackOverflow or GitHub.
DeepMind's Tacotron-2 Tensorflow implementation
Testcontainers is a Python library that providing a friendly API to run Docker container. It is designed to create runtime environment to use during your automatic tests.
【TMM 2025🔥】 Mixture-of-Experts for Large Vision-Language Models
[CVPR 2025] MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis
Let Claude (or any LLM) actually watch a video — scene-aware, deduplicated frames + transcript, from a URL or local file. Runs locally, MIT.
Tools & Interesting Things for RedTeam Ops
An agentic company research tool powered by LangGraph and Tavily that conducts deep diligence on companies using a multi-agent framework. It leverages OpenRouter on the backend for rapid inference with any leading model.
Steam 挂刀行情站 —— 24小时更新的 BUFF & IGXE & C5 & UUYP & ECO 挂刀比例数据 | Track cheap Steam Community Market items on buff.163.com, igxe.cn, c5game.com, youpin898.com and ecosteam.cn.