Go to COLM 2025 Conference homepageCan Test-Time Scaling Improve World Foundation Model?
Keywords: world foundation model, test time scaling, autoregressive video generation, evaluation tookit
TL;DR: Test time scaling could work for world foundation models and shows a clear scaling law. Smaller model with test time scaling is even better than x2 larger pretrained model. A extensible tookit will be opensourced for evaluating performance of WFM.
Abstract: World foundation models, which simulate the physical world by predicting future states from current observations and inputs, have become central to many applications in physical intelligence, including autonomous driving and robotics. However, these models require substantial computational resources for pretraining and are further constrained by available data during post-training.
As such, scaling computation at test time emerges as both a critical and practical alternative to traditional model enlargement or re-training.
In this work, we introduce **SWIFT**, a test-time scaling framework tailored for WFMs. SWIFT integrates our extensible WFM evaluation toolkit with process-level inference strategies, including fast tokenization, probability-based Top-K pruning, and efficient beam search.
Empirical results on the COSMOS model demonstrate that test-time scaling exists even in a compute-optimal way. Our findings reveal that test-time scaling laws hold for WFMs and that SWIFT provides a scalable and effective pathway for improving WFM inference without retraining or increasing model size. Project page: [https://scalingwfm.github.io/](https://scalingwfm.github.io/).
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the COLM Code of Ethics on https://colmweb.org/CoE.html
Author Guide: I certify that this submission complies with the submission instructions as described on https://colmweb.org/AuthorGuide.html
Submission Number: 59
Loading