ECCV 2024 Best Paper Candidate & TPAMI 2025 PointLLM: Empowering Large Language Models to Understand Point Clouds
Emu Series: Generative Multimodal Models from BAAI
Jaaz is a self-hosted AI design suite and multimodal workspace used for generating and editing images and videos. It functions as a design workspace where users can produce visual content and assets through a combination of local and cloud-based AI models. The project features a hybrid model orchestrator that routes requests between local model runners and remote APIs to balance data privacy with processing performance. It utilizes an infinite canvas collaborative tool for organizing storyboards and assets, and includes an image prompt optimizer to translate rough ideas into detailed generati
This project is a computer control framework that uses multimodal vision models to simulate mouse and keyboard inputs for automating desktop tasks. It functions as an autonomous agent and vision-based orchestrator that interprets screen visuals to interact with user interfaces. The system employs vision language models and object detection to locate and click interface elements. It utilizes visual grounding to overlay numerical markers on UI components and uses optical character recognition to map on-screen text to precise pixel coordinates. The framework supports voice-controlled computing
[TMLR23] Official implementation of UnIVAL: Unified Model for Image, Video, Audio and Language Tasks.
Las características principales de mshukor/unival son: Foundation Models, Multimodal Agents.
Las alternativas de código abierto para mshukor/unival incluyen: openrobotlab/pointllm — [ECCV 2024 Best Paper Candidate & TPAMI 2025] PointLLM: Empowering Large Language Models to Understand Point Clouds. baaivision/emu — Emu Series: Generative Multimodal Models from BAAI. qwenlm/qwen3-omni — Qwen3-Omni is an omni-modal large language model designed to process and generate text, audio, images, and video… othersideai/self-operating-computer — This project is a computer control framework that uses multimodal vision models to simulate mouse and keyboard inputs… 11cafe/jaaz — Jaaz is a self-hosted AI design suite and multimodal workspace used for generating and editing images and videos. It… simular-ai/agent-s — Agent-S is a multimodal AI agent and LLM desktop automation framework designed to control operating systems through…