🏗️ AssemLM: Spatial Reasoning Multimodal Large Language Models for Robotic Assembly

Zhi Jing^1,2, Jinbin Qiao^2,3, Ouyang Lu^2,4, Jicong Ao², Shuang Qiu⁵, Yu-Gang Jiang^1,*, Chenjia Bai^2,*

¹Fudan University^†, ²Institute of Artificial Intelligence (TeleAI), China Telecom^†,

³Tianjin University, ⁴Northwestern Polytechnical University, ⁵City University of Hong Kong

^* Equal advising | ^† Equally leading organizations

🚀 News

• [2026-04-16] 🗺️ Announce the open-source roadmap, including plans for releasing inference weights, code, datasets, and future improved versions.

• [2026-04-10] 📄 Upload the paper to arXiv: paper

• [2026-03-15] 🎉 Release the first version of the project page.

• [2026-03-05] 🏗️ Create the project page and code repository.

🗺️ Open-Source Roadmap

• [Coming within 1 week] 🔓 Release AssemLM-v1 inference weights, inference code, and a sample dataset.
• [Planned] 📦 Release the majority of the AssemBench dataset.
• [Planned] 📚 Release additional datasets and benchmark resources.
• [Planned] 🧠 Release the training code.
• [Planned] ⚙️ Release the data processing pipeline.
• [Planned] 🚀 Release updated and improved model weights.