[ECCV2024] Video Foundation Models & Data for Multimodal Understanding
- foundation-models
- video-understanding
- vision-transformer
- action-recognition
105,102 visible repositories in the index
601–624 of 1,760 · Most stars
[ECCV2024] Video Foundation Models & Data for Multimodal Understanding
🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
pytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding are performed with the kaldi toolkit.
E-Commerce Platform
[ICML 2026] Video generation via code
GLM-4.6V/4.5V/4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding
Intelligent Music & Video Automation Platform
Memory that AI Agents Love!
Deep Eye orchestrates multiple AI providers (OpenAI, Claude, Grok, Gemini, OLLAMA, Groq, Mistral, OpenRouter, LiteLLM, LM Studio) for intelligent payload generation, scans targets for 45+ vulnerability types, and produces professional reports with compliance mapping.
A framework for large scale recommendation algorithms.
Multilingual text (NLP) processing toolkit
Cast macOS and Linux Audio/Video to your Google Cast and Sonos Devices
Genymotion ARM translation packages: legacy Android 4.3–9.0 and experimental Android 11–14 x86_64 ARM64 bundles, with offline configuration tools and checksums.
PyTorch implementation of SENet
A deliberately vulnerable CI/CD environment. Learn CI/CD security through multiple challenges.
Refine and quantize messy AI pixel art into clean, perfect pixels.
A Python library for audio data augmentation. Useful for making audio ML models work well in the real world, not just in the lab.
Home Assistant integration framework for (garbage collection) schedules
Let Claude (or any LLM) actually watch a video — scene-aware, deduplicated frames + transcript, from a URL or local file. Runs locally, MIT.
[CVPR 2025] MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis
The first fruit of the Nüwa tree — an autonomous AI pentest legion (634-team champion, 8h unattended, 1B tokens beat 4.5B). Not just a tool: evolvable by design. Grow your own fruit on the Nüwa Foundation (Create/Language/History).
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.
【TMM 2025🔥】 Mixture-of-Experts for Large Vision-Language Models