👁️ Om AI Lab

Open Multimodal AGI Research


*Pioneering the next generation of multimodal AI models for Spatial Intelligence and Embodied AI.*

---

🌌 About Us

At Om AI Lab, we believe the future of AI extends far beyond pure text. We are dedicated to building the "brains" for next-generation systems by focusing on the intersection of Spatial Intelligence, Visual Reasoning, and Embodied Agents.

Our research spans across open-vocabulary perception, reinforced vision-language models, and real-time inference. We aim to bridge the critical gap between high-level logical reasoning and fine-grained visual action—building models that don't just "see" the world, but intuitively understand and interact with it.

---

🚀 Core Research Tracks

🧠 Reinforced & Advanced VLMs

*Models that think, reason, and understand the visual world at a granular level.*

• 🌟 VLM-R1: Solving Visual Understanding with Reinforced VLMs. *(Highly active)*
• 🔍 VLM-FO1: Bridging the gap between high-level reasoning and fine-grained perception in Vision-Language Models.
• 🔎 ZoomEye: Enhancing Multimodal LLMs with human-like zooming capabilities through tree-based image exploration.

👁️ Real-Time Perception & Open-World Detection

*Foundational spatial understanding optimized for edge and on-premise speeds.*

• ⚡ OmDet: Real-time, highly accurate, open-vocabulary end-to-end object detection.
• 📐 GroundVLP: Harnessing Zero-shot Visual Grounding from Vision-Language Pre-training.
• 🌍 ImageRAG: Enhancing ultrahigh-resolution remote sensing imagery analysis.

🤖 Multimodal Agents & Embodied AI

*Action-oriented intelligence for physical and virtual environments.*

• 🛠️ OmAgent: A comprehensive framework to build multimodal language agents for fast prototyping and production.
• 🎯 OpenTrackVLA: Open and reproducible research for tracking Vision-Language-Action (VLA) models.

📊 Benchmarks & Evaluation

*Rigorous standards for the open-source multimodal community.*

• 📏 OVDEval: A comprehensive evaluation benchmark for Open-Vocabulary Detection.
• 📝 VL-CheckList: Evaluating Vision & Language Pretraining Models with Objects, Attributes, and Relations.

Building the foundational brains for the physical world.
Join us in exploring the spatial frontier.

Collapse