mlsanityData to 14 Oct 2026

Generative World Modelling for Humanoids: 1X World Model Challenge Technical Report

arXiv 2510.07092 ↗First posted 8 Oct 2025cs.LG cs.AI cs.ROcited by 8

On the map: World models → Embodied and robot world models

Abstract (arXiv)

World models are a powerful paradigm in AI and robotics, enabling agents to reason about the future by predicting visual observations or compact latent states. The 1X World Model Challenge introduces an open-source benchmark of real-world humanoid interaction, with two complementary tracks: sampling, focused on forecasting future image frames, and compression, focused on predicting future discrete latent codes. For the sampling track, we adapt the video generation foundation model Wan-2.2 TI2V-5B to video-state-conditioned future frame prediction. We condition the video generation on robot states using AdaLN-Zero, and further post-train the model using LoRA. For the compression track, we train a Spatio-Temporal Transformer model from scratch. Our models achieve 23.0 dB PSNR in the sampling task and a Top-500 CE of 6.6386 in the compression task, securing 1st place in both challenges.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Placed in Embodied and robot world models, one of 11 directions in World models. Builds on 32 of its 40 references that are in the map. First posted on arXiv 8 Oct 2025.

Builds on

32 of 40 references.

References · 32

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  5. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  6. 2022Scalable Diffusion Models with Transformerscited by 6,054
  7. 2022Classifier-Free Diffusion Guidancecited by 5,847
  8. 2016Layer Normalizationcited by 5,669
  9. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformercited by 2,261
  10. 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,660
  11. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,264
  12. 2020Mastering Atari with Discrete World Modelscited by 1,007
20 more
  1. 2022CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformerscited by 985
  2. 2025Cosmos World Foundation Model Platform for Physical AIcited by 864
  3. 2015Scheduled Sampling for Sequence Prediction with Recurrent Neural Networkscited by 803
  4. 2018Recurrent World Models Facilitate Policy Evolutioncited by 785
  5. 2018Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Modelscited by 774
  6. 2024Genie: Generative Interactive Environmentscited by 747
  7. 2024LTX-Video: Realtime Video Latent Diffusioncited by 581
  8. 2023TD-MPC2: Scalable, Robust World Models for Continuous Controlcited by 512
  9. 2022Temporal Difference Learning for Model Predictive Controlcited by 397
  10. 2022Transformers are Sample-Efficient World Modelscited by 328
  11. 2024Diffusion for World Modeling: Visual Details Matter in Ataricited by 300
  12. 2020Query-Key Normalization for Transformerscited by 280
  13. 2016Using the Output Embedding to Improve Language Modelscited by 272
  14. 2024Navigation World Modelscited by 272
  15. 2020Spatial-Temporal Transformer Networks for Traffic Flow Forecastingcited by 180
  16. 2023Transformer-based World Models Are Happy With 100k Interactionscited by 139
  17. 2025MineWorld: a Real-Time and Open-Source Interactive World Model on Minecraftcited by 97
  18. 2023STORM: Efficient Stochastic Transformer based World Models for Reinforcement Learningcited by 89
  19. 2019Scheduled Sampling for Transformerscited by 48
  20. 2025Discrete Codebook World Models for Continuous Controlcited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 7.

8 papers.

  1. 2026Solaris: Building a Multiplayer Video World Model in Minecraftcited by 47
  2. 2025Dexterous World Modelscited by 18
  3. 2026Gamma-World: Generative Multi-Agent World Modeling Beyond Two Playerscited by 15
  4. 2026Lifting Embodied World Models for Planning and Controlcited by 2
  5. 2026Self-Evolving AI for Humanoids: Mechanisms, Safety, and Evaluation of Post-Deployment Self-Improvementcited by 1
  6. 2026From Generation to Simulation: How Far Are World Models from Being True Simulators?cited by 0
  7. 2026Hydra: A Navigation World Action Model with Discrete Latent Planning and Continuous Flow-Matching Executioncited by 0
  8. 2026HappyWorld-Benchcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Humanoid World Models: Open World Foundation Models for Humanoid Robotics
  2. 2025DreamGen: Unlocking Generalization in Robot Learning through Video World Models
  3. 2025X-Humanoid: Robotize Human Videos to Generate Humanoid Videos at Scale
  4. 2026Interactive World Simulator for Robot Policy Training and Evaluation
  5. 2026WALL-SS: Scaling Long-horizon World Models via Next-Scale Autoregression
  6. 2026One from Infinity: Actualizing Futures from Pretrained World Models into Robot Actions
  7. 2026Being-M0.7: A Latent World-Action Model for Humanoid Robots
  8. 2025GigaWorld-0: World Models as Data Engine to Empower Embodied AI