mlsanityData to 7 Oct 2026

MiMo-Embodied: X-Embodied Foundation Model Technical Report

arXiv 2511.16518 ↗First posted 20 Nov 2025cs.RO cs.CL cs.CVcited by 36

Not on the map. Why?

Abstract (arXiv)

We open-source MiMo-Embodied, the first cross-embodied foundation model to successfully integrate and achieve state-of-the-art performance in both Autonomous Driving and Embodied AI. MiMo-Embodied sets new records across 17 embodied AI benchmarks in Task Planning, Affordance Prediction and Spatial Understanding, while also excelling in 12 autonomous driving benchmarks across Environmental Perception, Status Prediction, and Driving Planning. Across these tasks, MiMo-Embodied significantly outperforms existing open-source, closed-source, and specialized baselines. Our results indicate that through multi-stage learning, curated data construction, and CoT/RL fine-tuning, these two domains exhibit strong positive transfer and mutually reinforce one another. We provide a detailed analysis of our model design and training methodologies to facilitate further research. Code and models are available at https://github.com/XiaomiMiMo/MiMo-Embodied.

Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Nov 2025.

Builds on

0 of 0 references.

No references here yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 34.

36 papers.

Sort:

By area:

  1. 2026DriveWorld-VLA: Unified Latent-Space World Modeling with Vision-Language-Action for Autonomous Drivingcited by 31
  2. 2026PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulationcited by 20
  3. 2026FASTER: Rethinking Real-Time Flow VLAscited by 20
  4. 2025Thinking in 360deg: Humanoid Visual Search in the Wildcited by 14
  5. 2026Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanationcited by 9
  6. 2026Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Drivingcited by 8
  7. 2026Done, But Not Sure: Disentangling World Completion from Self-Termination in Embodied Agentscited by 7
  8. 2026GEM: Generative Supervision Helps Embodied Intelligencecited by 6
  9. 2026Large Vision-Language Models Get Lost in Attentioncited by 5
  10. 2026Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Modelscited by 5
  11. 2026Vesta: A Generalist Embodied Reasoning Modelcited by 5
  12. 2026FutureNav: Unified World-Action Modeling for Vision-and-Language Navigationcited by 5
24 more
  1. 2026ACE-Brain-0.5: A Unified Embodied Foundational Model for Physical Agentic AIcited by 5
  2. 2026Planning Takes More Than Token Prediction: Causal Plan for Benchmarking and Building Physically Grounded Embodied Reasonerscited by 3
  3. 2026SEF-MAP: Subspace-Decomposed Expert Fusion for Robust Multimodal HD Map Predictioncited by 2
  4. 2026Weather-Conditioned Branch Routing for Robust LiDAR-Radar 3D Object Detectioncited by 1
  5. 2026RAG-KT: Cross-platform Explainable Knowledge Tracing with Multi-view Fusion Retrieval Generationcited by 1
  6. 2026Unmasking the Illusion of Embodied Reasoning in Vision-Language-Action Modelscited by 1
  7. 2026XEmbodied: A Foundation Model with Enhanced Geometric and Physical Cues for Large-Scale Embodied Environmentscited by 1
  8. 2026RoboEvolve: Co-Evolving Planner-Simulator for Robotic Manipulation with Limited Datacited by 1
  9. 2026EPIC-Bench: A Perception-Centric Benchmark for Fine-Grained Embodied Visual Grounding in Vision-Language Modelscited by 1
  10. 2026LayerRoute: Action-Conditioned Mixture-of-Layers Routing for Vision-Language-Action Policiescited by 1
  11. 2025Transforming Monolithic Foundation Models into Embodied Multi-Agent Architectures for Human-Robot Collaborationcited by 0
  12. 2026RoboPIN: Grounded Embodied Reasoning via Pinned Chain-of-Thoughtcited by 0
  13. 2026Robust 3D Alignment of Generative Reconstructions via Partial Monocular Observationscited by 0
  14. 2026Text-Driven 3D Indoor Scene Synthesis in Non-Manhattan Environmentscited by 0
  15. 2026UniETP: Unifying Environments for Generalizable Embodied Task Planningcited by 0
  16. 2026SpatioLM: Towards General Physical Spatial Intelligence in Vision-Language Modelscited by 0
  17. 2026Capek 0.5: An Execution-Centric Vision-Language Model for Embodied Intelligencecited by 0
  18. 2026Neurosymbolic Embodied Agentscited by 0
  19. 2026One Policy, Many Embodiments: Unified Camera-Centric Action Geometry Pre-training for Heterogeneous Embodied Manipulationcited by 0
  20. 2026Towards Generalizable Visually Grounded Exploration of Household Devicescited by 0
  21. 2026PhysBrain 1.5: From Vision-Language Models to Physical Foundation Modelscited by 0
  22. 2026Acting in Meters: Learning Metric Interactions for Precise Robotic Manipulationcited by 0
  23. 2026EmbodiedMind: Adaptive Data Curation and Prefix-Tree Reinforcement Learning for Efficient Embodied Intelligencecited by 0
  24. 2026ME-VLM: A Unified VLM for Embodied Cognition and Agent Coordinationcited by 0