paper-with-me

Papers

Looped World Models

2026-06-16 · Hongyuan Adam Lu, Z. L. Victor Wei, Qun Zhang, Jinrui Zeng, Bowen Cao, Lingwei Meng, Mocheng Li, Zezhong Wang, Haonan Yin, Naifu Xue, Minyu Chen, Cenyuan Zhang, Zefan Zhang, Hao Wei, Jiawei Zhou, Haoran Xu, Hao Yang, Ronglai Zuo, Tongda Xu, Yonghao Li, Jian Chen, Hebin Wang, Zeyu Gao, Yang Li, Wei Zhao, Qimin Zhong, Siqi Liu, Yumeng Zhang, Leyan Cui, Zhangyu Wang, Wai Lam arxiv

Current world models face a fundamental tension: faithful long-horizon simulation demands deep computation, but deeper models are expensive to deploy and prone to compounding errors. We resolve this by introducing Looped World Models (LoopWM), which are the first looped architectures for world modelling. Our method iteratively refines latent environment states through a parameter-shared transformer block. This yield up to 100x parameter efficiency over conventional approaches with adaptive computation that automatically scales depth to match the complexity of each prediction step. Orthogonal to scaling model size and training data, LoopWM establishes iterative latent depth as a new scaling axis for world simulation, which might significantly push the community forward.

📄 PDF Abstract BibTeX arXiv:2606.18208

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Slots, Transitions, Loops: Learning Composable World Models for ARC

2026-06-10 · Gege Gao, Bernhard Schölkopf, Andreas Geiger arxiv

ARC tests in-context rule induction: given a few input-output demonstrations, a model must infer the hidden rule and apply it to a new query. While many approaches express ARC rules through language, code, or symbolic pr…

Sparse Layers are Critical to Scaling Looped Language Models

2026-05-09 · Ryan Lee, Jacob Biloki, Edward J. Hu, Jonathan May arxiv

Looped language models repeat a set of transformer layers through depth, reducing memory costs and providing natural early-exit points at loop boundaries. However, looped models do not scale as favorably as standard tran…

Simply Stabilizing the Loop via Fully Looped Transformer

2026-05-11 · Rao Fu, Zixuan Yang, Jiankun Zhang, Jing Ma 외 arxiv

Scaling model performance typically requires increasing model size. Looped Transformer offers a compelling alternative by iteratively reusing the same Transformer blocks, trading additional computation for improved perfo…

Looped State-Space Language Models with Adaptive Exit-State Selection

2026-07-11 · Zhenxuan Yu, Takeshi Kojima, Yutaka Matsuo, Yusuke Iwasawa arxiv

Recent work on looped language models suggests that many reasoning problems benefit from greater computational depth rather than from additional independent parameters. Existing studies, however, focus almost exclusively…

Reasoning with Latent Thoughts: On the Power of Looped Transformers

2025-02-24 · Nikunj Saunshi, Nishanth Dikkala, Zhiyuan Li, Sanjiv Kumar 외

Large language models have shown remarkable reasoning abilities and scaling laws suggest that large parameter count, especially along the depth axis, is the primary driver. In this work, we make a stronger claim -- many …

Language ModelingLanguage ModellingMathMemorization