mlsanityData to 7 Oct 2026

Jasmine: A Simple, Performant and Scalable JAX-based World Modeling Codebase

arXiv 2510.27002 ↗First posted 30 Oct 2025cs.LG cs.AIcited by 1

On the map: World models → World models for language agents

Abstract (arXiv)

While world models are increasingly positioned as a pathway to overcoming data scarcity in domains such as robotics, open training infrastructure for world modeling remains nascent. We introduce Jasmine, a performant JAX-based world modeling codebase that scales from single hosts to hundreds of accelerators with minimal code changes. Jasmine achieves an order-of-magnitude faster reproduction of the CoinRun case study compared to prior open implementations, enabled by performance optimizations across data loading, training and checkpointing. The codebase guarantees fully reproducible training and supports diverse sharding configurations. By pairing Jasmine with curated large-scale datasets, we establish infrastructure for rigorous benchmarking pipelines across model families and architectural ablations.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in World models for language agents, one of 11 directions in World models. Builds on 39 of its 50 references that are in the map. First posted on arXiv 30 Oct 2025.

Builds on

39 of 50 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025Cosmos World Foundation Model Platform for Physical AI7 Jan
  2. 2024Scaling Laws for Pre-training Agents and World Models7 Nov
  3. 2020Language Models are Few-Shot Learners28 May

Other references · 36

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  5. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  6. 2022Scalable Diffusion Models with Transformerscited by 5,931
  7. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  8. 2017Neural Discrete Representation Learningcited by 4,650
  9. 2017Deep reinforcement learning from human preferencescited by 3,846
  10. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,611
  11. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,014
  12. 2019Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelismcited by 1,829
24 more
  1. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,598
  2. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,221
  3. 2019Dota 2 with Large Scale Deep Reinforcement Learningcited by 1,084
  4. 2022MaskGIT: Masked Generative Image Transformercited by 1,082
  5. 2021Scaling Vision Transformerscited by 993
  6. 2020Mastering Atari with Discrete World Modelscited by 990
  7. 2018Recurrent World Models Facilitate Policy Evolutioncited by 761
  8. 2024Genie: Generative Interactive Environmentscited by 706
  9. 2024Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusioncited by 634
  10. 2023GAIA-1: A Generative World Model for Autonomous Drivingcited by 618
  11. 2018Exploring the Limits of Weakly Supervised Pretrainingcited by 604
  12. 2019Leveraging Procedural Generation to Benchmark Reinforcement Learningcited by 478
  13. 2024One Step Diffusion via Shortcut Modelscited by 373
  14. 2019Axial Attention in Multidimensional Transformerscited by 350
  15. 2024Diffusion for World Modeling: Visual Details Matter in Ataricited by 285
  16. 2024Diffusion Models Are Real-Time Game Enginescited by 282
  17. 2016Exploring the Limits of Language Modelingcited by 172
  18. 2022Evolving Curricula with Regret-Based Environment Designcited by 166
  19. 2025Training Agents Inside of Scalable World Modelscited by 122
  20. 2023Learning to Act without Actionscited by 116
  21. 2025MineWorld: a Real-Time and Open-Source Interactive World Model on Minecraftcited by 93
  22. 2025Hunyuan-GameCraft: High-dynamic Interactive Game Video Generation with Hybrid History Conditioncited by 92
  23. 2025Exploration-Driven Generative Interactive Environmentscited by 8
  24. 2024Penzai + Treescope: A Toolkit for Interpreting, Visualizing, and Editing Models As Datacited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Nano World Models: A Minimalist Implementation of Future Video Predictioncited by 4

Similar, not cited

Close in wording, no citation either way

  1. 2026WebWorld: A Large-Scale World Model for Web Agent Training
  2. 2025CWM: An Open-Weights LLM for Research on Code Generation with World Models
  3. 2026stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation
  4. 2026Simulate to Generalize: Scaling Stateful Supervision for API-calling Agents using LLM World Models
  5. 2025R2E-Gym: Procedural Environments and Hybrid Verifiers for Scaling Open-Weights SWE Agents
  6. 2025Web World Models
  7. 2026Looped World Models
  8. 2026WorldBench: Evaluating LLMs on Three.js Voxel World Generation