Pith. sign in

REVIEW 2 cited by

Can Test-Time Scaling Improve World Foundation Model?

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

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

classification cs.CV
keywords scalingmodeltest-timeswiftworldfoundationincludinginference
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
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/.

Discussion (0). Sign in to comment.

Forward citations

Cited by 2 Pith papers

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

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

    cs.CV 2026-06 unverdicted novelty 6.5 of 10

    CrashTwin recovers metric-scale crash dynamics from monocular rollouts and shows that strong visual scores routinely mask large momentum, energy, and identity violations in world models.

  2. Interpretable Adaptive Sampling for LLM Test-Time Scaling

    cs.AI 2026-08 reject novelty 4.0 of 10

    A fuzzy controller that allocates a per-prompt sampling budget keeps LLM accuracy near a fixed full-budget baseline while reducing the average number of candidate answers on some datasets.

Pith tools