Privacy and security enhanced releases of Chromium for GrapheneOS. Vanadium provides the WebView and standard user-facing browser on GrapheneOS. It depends on hardening in other GrapheneOS repositories and doesn't include patches not relevant to the build targets used on GrapheneOS.
Repository Index
132,241 visible repositories in the index
73–96 of 292 · Most stars
"FastCode: Accelerating and Streamlining Your Code Understanding"
Official SGLang x Datawhale course on LLM inference: understand inference, build a mini-sglang from scratch, then read the real SGLang source and land your first PR. Available in English and Chinese.
AI code-writing assistant that understands data content
The implementation of DeBERTa
- bert
- deeplearning
- representation-learning
- roberta
Multi-Task Deep Neural Networks for Natural Language Understanding
- multi-task-learning
- natural-language-understanding
- deep-learning
- microsoft
JoyAI-Image is the unified multimodal foundation model for image understanding, text-to-image generation, and instruction-guided image editing.
[ICCV 2019] TSM: Temporal Shift Module for Efficient Video Understanding
- acceleration
- low-latency
- temporal-modeling
- video-understanding
Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding
Open Source AI Accelerator Research Platform Standard / 开源推理研究平台
A collection of extensions and data-loaders for few-shot learning & meta-learning in PyTorch
- pytorch
- meta-learning
- few-shot-learning
[EMNLP2026] "VideoAgent: All-in-One Agentic Framework for Video Understanding and Editing, and Remaking"
- agents
- llm-agents
- video-editing
- video-understanding
ARA Records Ansible and makes it easier to understand and troubleshoot.
PerfKit Benchmarker (PKB) contains a set of benchmarks to measure and compare cloud offerings. The benchmarks use default settings to reflect what most users will see. PerfKit Benchmarker is licensed under the Apache 2 license terms. Please make sure to read, understand and agree to the terms of the LICENSE and CONTRIBUTING files before proceeding.
Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR benchmarks, while also offering outstanding singing lyrics recognition capability.
- asr
- industrial-grade
- llm
- multimodal-llm
NVIDIA AI Blueprint for video search and summarization (VSS) is a GPU-accelerated reference architecture for building video analytics agents with real-time verified alerts, visual Q&A, and automated reporting. The VSS Blueprint uses vision language models (VLMs) such as NVIDIA Cosmos, LLMs such as NVIDIA Nemotron, RAG, and NVIDIA NIMs.
[ICLR & NeurIPS 2025] Repository for Show-o series, One Single Transformer to Unify Multimodal Understanding and Generation.
- diffusion-models
- large-language-models
- multimodal
An end-to-end growth tool that understands the product, fetch the data it needs, researches the market, executes campaigns, and reviews results to improve the next round of growth. 从代码到市场的开源端到端增长工具。理解产品、接入信息渠道、研究市场、执行增长行动,并基于真实数据自我改进。
- agentic-marketing
- ai-agent
- claude-code
- codex
Guardian is a production-ready AI-powered penetration testing automation CLI tool that leverages Google Gemini and LangChain to orchestrate intelligent, step-by-step penetration testing workflows while maintaining ethical hacking standards.
- automation
- gemini-ai
- generative-ai
- pentest-tool
Complex code hides connections, workflows, and business risks.Unvibe complex code. Trace business workflows.
- business-logic
- code-analysis
- code-understanding
- codebase-analysis
An open-source toolbox for action understanding based on PyTorch
- action-recognition
- action-detection
- video-understanding
- pytorch
[ACL 2026] Open-source framework for holistic, structured repository-level documentation across multilingual codebases
- automated-documentation
- code-documentation
- code-understanding
- documentation-generator
WeMM-Embedding is a family of universal multimodal embedding models by the WeChat Vision Team at Tencent, supporting multimodal understanding and retrieval.
- embedding-models
- multimodal
- multimodal-llm
[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
- self-supervised-learning
- action-recognition
- video-understanding
- masked-autoencoder