Can Test-Time Scaling Improve World Foundation Model?

• URL: http://arxiv.org/abs/2503.24320v1
• Date: Mon, 31 Mar 2025 17:07:37 GMT
• Title: Can Test-Time Scaling Improve World Foundation Model?
• Authors: Wenyan Cong, Hanqing Zhu, Peihao Wang, Bangya Liu, Dejia Xu, Kevin Wang, David Z. Pan, Yan Wang, Zhiwen Fan, Zhangyang Wang,
• Abstract summary: We introduce SWIFT, a test-time scaling framework tailored for world foundation models (WFMs)<n> Empirical results on the COSMOS model demonstrate that test-time scaling exists even in a compute-optimal way.<n>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.
• Score: 67.82670175383761
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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. The code is available at https://github.com/Mia-Cong/SWIFT.git.

Related papers

• LoTUS: Large-Scale Machine Unlearning with a Taste of Uncertainty [31.008361777309638]
  We present LoTUS, a novel Machine Unlearning (MU) method that eliminates the influence of training samples from pre-trained models.<n>LoTUS smooths the prediction probabilities of the model up to an information-theoretic bound, mitigating its over-confidence stemming from data memorization.<n>We evaluate LoTUS on Transformer and ResNet18 models against eight baselines across five public datasets.
  arXiv  Detail & Related papers  (2025-03-24T03:34:23Z)
• Benchmarking Time Series Forecasting Models: From Statistical Techniques to Foundation Models in Real-World Applications [0.0]
  Time series forecasting is essential for operational intelligence in the hospitality industry.<n>This study evaluates the performance of statistical, machine learning (ML), deep learning, and foundation models in forecasting hourly sales over a 14-day horizon.
  arXiv  Detail & Related papers  (2025-02-05T17:30:31Z)
• Unlock the Correlation between Supervised Fine-Tuning and Reinforcement Learning in Training Code Large Language Models [12.656574142412484]
  We make an attempt to understand the correlation between supervised fine-tuning and reinforcement learning.<n>We find that both atomic and synthetic functions are indispensable for SFT's generalization.
  arXiv  Detail & Related papers  (2024-06-14T03:39:01Z)
• A Dynamical Model of Neural Scaling Laws [79.59705237659547]
  We analyze a random feature model trained with gradient descent as a solvable model of network training and generalization. Our theory shows how the gap between training and test loss can gradually build up over time due to repeated reuse of data.
  arXiv  Detail & Related papers  (2024-02-02T01:41:38Z)
• Towards Flexible Time-to-event Modeling: Optimizing Neural Networks via Rank Regression [17.684526928033065]
  We introduce the Deep AFT Rank-regression model for Time-to-event prediction (DART) This model uses an objective function based on Gehan's rank statistic, which is efficient and reliable for representation learning. The proposed method is a semiparametric approach to AFT modeling that does not impose any distributional assumptions on the survival time distribution.
  arXiv  Detail & Related papers  (2023-07-16T13:58:28Z)
• FlexMoE: Scaling Large-scale Sparse Pre-trained Model Training via Dynamic Device Placement [19.639936387834677]
  Mixture-of-Experts (MoEs) are becoming more popular and have demonstrated impressive pretraining scalability in various downstream tasks. MoEs are becoming a new data analytics paradigm in the data life cycle and suffering from unique challenges at scales, complexities, and granularities never before possible. In this paper, we propose a novel DNN training framework, FlexMoE, which systematically and transparently address the inefficiency caused by dynamic dataflow.
  arXiv  Detail & Related papers  (2023-04-08T07:34:26Z)
• SOLIS -- The MLOps journey from data acquisition to actionable insights [62.997667081978825]
  In this paper we present a unified deployment pipeline and freedom-to-operate approach that supports all requirements while using basic cross-platform tensor framework and script language engines. This approach however does not supply the needed procedures and pipelines for the actual deployment of machine learning capabilities in real production grade systems.
  arXiv  Detail & Related papers  (2021-12-22T14:45:37Z)
• ForceNet: A Graph Neural Network for Large-Scale Quantum Calculations [86.41674945012369]
  We develop a scalable and expressive Graph Neural Networks model, ForceNet, to approximate atomic forces. Our proposed ForceNet is able to predict atomic forces more accurately than state-of-the-art physics-based GNNs.
  arXiv  Detail & Related papers  (2021-03-02T03:09:06Z)
• Fast-Convergent Federated Learning [82.32029953209542]
  Federated learning is a promising solution for distributing machine learning tasks through modern networks of mobile devices. We propose a fast-convergent federated learning algorithm, called FOLB, which performs intelligent sampling of devices in each round of model training.
  arXiv  Detail & Related papers  (2020-07-26T14:37:51Z)
• Ensemble Distillation for Robust Model Fusion in Federated Learning [72.61259487233214]
  Federated Learning (FL) is a machine learning setting where many devices collaboratively train a machine learning model. In most of the current training schemes the central model is refined by averaging the parameters of the server model and the updated parameters from the client side. We propose ensemble distillation for model fusion, i.e. training the central classifier through unlabeled data on the outputs of the models from the clients.
  arXiv  Detail & Related papers  (2020-06-12T14:49:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.