This work presents Uranus, a data-driven robot simulator built around a joint-trajectory-conditioned autoregressive diffusion model, providing a unified interface for synchronized multi-view generation across diverse robot embodiments and camera configurations.
Abstract
Scalable simulation is essential for robot data generation, policy training, evaluation, and safe iteration, yet real-world interaction is costly and conventional simulators require labor-intensive construction. We present Uranus, a data-driven robot simulator built around a joint-trajectory-conditioned autoregressive diffusion model. Uranus offers three key capabilities: (1) streaming, open-ended rollout, which receives future joint-position trajectories online and autoregressively generates one latent frame per step, corresponding to four RGB frames, without a fixed horizon; (2) low-latency generation, achieving 24 FPS after inference optimization; and (3) scalable, extensible robot control, providing a unified interface for synchronized multi-view generation across diverse robot embodiments and camera configurations. We conduct comprehensive quantitative and qualitative evaluations on both in-distribution and out-of-distribution data, providing an objective assessment of Uranus and clearly identifying its current limitations. We release the code and model weights to empower the community with practical tools and insights.
Adapting robot manipulation policies to new tasks and environments remains highly data-intensive, while the data needed for further improvement depends on the policy's current capabilities and failure modes. We introduce EmbodiRSI, an agentic system for recursive self-improvement (RSI) in a real-to-sim-to-real setting,...
Hao-Ran Lang, Hao-Tao Lu, Shi-Yu Sang et al.· arXiv.org· 9 citations
This work proposes a synthetic-to-real framework coupling physically validated data generation with a hierarchical, diffusion-based controller that outperforms state-of-the-art manipulation policies in transport smoothness and dynamic stability.
Ying-Yue Li, Chenyangguang Zhang, Rui-Da Zhang et al.· IEEE Robotics and Automation...· 0 citations
FluxVLA Engine is presented, an open, configuration-driven platform that turns heterogeneous embodied-policy components into a reproducible data-to-deployment workflow and targets the engineering bottlenecks separating promising embodied-learning algorithms from reproducible evaluation and dependable deployment.
Yin-Hao Li, Wei-Xin Mao, Zi-Han Lan et al.· arXiv.org· 4 citations
DynaForge combines low-frequency global planning with high-frequency object-centric inverse kinematics across task phases, and applies a residual policy to correct actions during dynamic interaction, showing the ability of DynaForge for sim-to-real transfer.
Yi-Yang Jin, Yu Zheng, Xiao He et al.· 0 citations
MILER, an end-to-end policy framework with zero-shot sim-to-real transfer of both perception and control, is presented and extensively evaluated on a diverse test track comprising numerous challenges.
Thomas Steinecker, Denis Trescher, Alexander Bienemann et al.· 0 citations
This work presents AeroManip-VLA, a scalable benchmark for aerial VLA data generation and policy evaluation, and evaluates a range of imitation learning and VLA baselines across different task settings, revealing their performance characteristics and failure modes.
Rui Huang, Yan-Lin Mu, Li-Dong Li et al.· arXiv.org· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduJul 30, 2026
From feet to fingertips — we are teaching robots intelligent whole-body control, fine dexterity, and teamwork to complete a broad range of complex tasks.