Nanyang Technological University

HSImul3R, a human–scene interaction reconstruction framework from Daxiao Robotics, Nanyang Technological University S-Lab, and Shanghai AI Laboratory, targets uncalibrated sparse-view input and produces simulation-ready scenes. The paper, accepted at ECCV 2026, describes a closed-loop optimization combining reinforcement learning for the scene with direct simulation-reward optimization, then transfers the refined motion to a Unitree G1 humanoid. On HSIBench, interaction stability reaches 53.68%, 30.56%, and 13.92% across three task tiers, while interpenetration drops from 69.51% to 22.90%. Code and paper are public; license was not stated.

Westlake University AGI Lab and Nanyang Technological University have released Code World Model, a code-driven world model that uses a language model as the reasoning core and a video model for visual output. A coding agent maintains an executable world state and directs video generation. The research is published on arXiv with a project page and code repository; the prototype uses MiniMax-H3's Ref2VA backbone and GPT-5.6 Sol as the coding agent.