[ECCV2022] PETR: Position Embedding Transformation for Multi-View 3D Object Detection & [ICCV2023] PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images
- multi-camera
- multi-task-learning
- object-detection
- segmentation
103,113 visible repositories in the index
1,249–1,272 of 1,713 · Most stars
[ECCV2022] PETR: Position Embedding Transformation for Multi-View 3D Object Detection & [ICCV2023] PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images
PDFium - Project to compile PDFium library to multiple platforms.
A Framework for Speech, Language, Audio, Music Processing with Large Language Model
🐝 The First Self-Improving agents with RL / Prompting Optimization
660+ muapi-hosted generative-media models plus community-submitted third-party API tools (SEO, enrichment, social, scraping) — one YAML file per entry, browsable by capability.
GLM-TTS: Controllable & Emotion-Expressive Zero-shot TTS with Multi-Reward Reinforcement Learning
☕ BeatPrints, create eye-catching, Pinterest-style music posters effortlessly.
Efficient Multi-Scale 3D Convolutional Neural Network for Segmentation of 3D Medical Scans
QQ聊天记录备份导出,支持无密钥导出,图片导出。无需编译有GUI界面。Backup Chating History of Instant Messaging QQ.
[ECCV 2024 Best Paper Candidate & TPAMI 2025] PointLLM: Empowering Large Language Models to Understand Point Clouds
A Comparative Framework for Multimodal Recommender Systems
Manage AWS MFA Security Credentials
GigaModels: A Comprehensive Repository and Platform for Multi-modal, Generative, and Perceptual Models
[ICLR'24 spotlight] Chinese and English Multimodal Large Model Series (Chat and Paint) | 基于CPM基础模型的中英双语多模态大模型系列
Spotify to YT-Music Playlist Sync Tool
A general representation model across vision, audio, language modalities. Paper: ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities
Server for the ListenBrainz project, including the front-end (javascript/react) code that it serves and all of the data processing components that LB uses.
Layers Outputs and Gradients in Keras. Made easy.
A Python-first runtime layer for multi-agent systems, with persistent run state, streaming execution events, and a pluggable orchestration interface.
A pytorch quantization backend for optimum
A family of lightweight multimodal models.
Audio MODEM Communication Library in Python
Enterprise-ready MCP Gateway & Registry that centralizes AI development tools with secure OAuth authentication, dynamic tool discovery, and unified access for both autonomous AI agents and AI coding assistants. Transform scattered MCP server chaos into governed, auditable tool access with Keycloak/Entra integration.
Zero-attacker is an multipurpose hacking tool with over 15+ multifunction tools