Pith

open record

sign in

arxiv: 2503.24320 · v2 · pith:NOVTFCGH · submitted 2025-03-31 · cs.CV

Can Test-Time Scaling Improve World Foundation Model?

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:NOVTFCGHrecord.jsonopen to challenge →

classification cs.CV
keywords scalingmodeltest-timeswiftworldfoundationincludinginference
0
0 comments X
read the original 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/.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. A Physics-Grounded Benchmark for Multi-Agent Dynamics in World Models

    cs.CV 2026-06 unverdicted novelty 6.0

    CrashTwin is a new benchmark framework that exposes physical violations in state-of-the-art world models during multi-agent collisions despite high visual quality.

  2. Test-Time Scaling in Multimodal Foundation Models: A Comprehensive Survey of Generation and Reasoning

    cs.CV 2026-06 unverdicted novelty 5.0

    A survey of test-time scaling for multimodal foundation models that introduces a three-way taxonomy of sampling, feedback, and search approaches along with applications and benchmarks.

  3. How Far Are We from Generating Missing Modalities with Foundation Models?

    cs.MM 2025-06 unverdicted novelty 5.0

    Evaluates 42 variants of foundation models across three formalized paradigms for missing modality reconstruction, identifies shortfalls in semantic extraction and validation, and introduces an agentic framework that r...

  4. Harnessing Photonics for Machine Intelligence

    physics.optics 2026-04 unverdicted novelty 4.0

    Photonic computing can reshape AI acceleration through optical bandwidth and parallelism, but requires cross-layer co-design and electronic-photonic design automation to move from prototypes to scalable systems.