Salvato in:
Dettagli Bibliografici
Autori principali: Lan, Jian, Liu, Zhicheng, Wang, Xinpeng, Zhou, Yuhao, Chen, Haokun, Lv, Jiancheng, Plank, Barbara, Seidl, Thomas
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2605.08452
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910203240251392
author Lan, Jian
Liu, Zhicheng
Wang, Xinpeng
Zhou, Yuhao
Chen, Haokun
Lv, Jiancheng
Plank, Barbara
Seidl, Thomas
author_facet Lan, Jian
Liu, Zhicheng
Wang, Xinpeng
Zhou, Yuhao
Chen, Haokun
Lv, Jiancheng
Plank, Barbara
Seidl, Thomas
contents The ability to derive precise spatial and physical insights is a cornerstone of vision-language models (VLMs), yet their poor performances in related spatial intelligence tasks such as physical reasoning remain a fundamental barrier. The community critically lacks a scientific analysis revealing whether VLMs faithfully reach answers or plausibly make guesses. This work aims to provide a fundamental understanding of how VLMs perceive the physical world, and utilize physical laws, while assessing the reliability of model confidence. We propose NICE and FACT, a dual-diagnostic paradigm that explicitly decomposes quantitative reasoning for kinematic physics: FACT diagnoses visual fidelity, physical law comprehension, and temporal grounding. NICE studies our novel neighborhood-informed calibration method and novel metrics to evaluate and calibrate confidence reliability. Evaluated across 6 latest state-of-the-art VLMs, we uncover that models fail to identify visual preconditions or utilize necessary physical laws to reach answers. This work highlights and establishes a standardized diagnostic paradigm to guide the development of faithful, physically-grounded VLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2605_08452
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle NICE FACT: Diagnosing and Calibrating VLMs in Quantitative Reasoning for Kinematic Physics
Lan, Jian
Liu, Zhicheng
Wang, Xinpeng
Zhou, Yuhao
Chen, Haokun
Lv, Jiancheng
Plank, Barbara
Seidl, Thomas
Computer Vision and Pattern Recognition
The ability to derive precise spatial and physical insights is a cornerstone of vision-language models (VLMs), yet their poor performances in related spatial intelligence tasks such as physical reasoning remain a fundamental barrier. The community critically lacks a scientific analysis revealing whether VLMs faithfully reach answers or plausibly make guesses. This work aims to provide a fundamental understanding of how VLMs perceive the physical world, and utilize physical laws, while assessing the reliability of model confidence. We propose NICE and FACT, a dual-diagnostic paradigm that explicitly decomposes quantitative reasoning for kinematic physics: FACT diagnoses visual fidelity, physical law comprehension, and temporal grounding. NICE studies our novel neighborhood-informed calibration method and novel metrics to evaluate and calibrate confidence reliability. Evaluated across 6 latest state-of-the-art VLMs, we uncover that models fail to identify visual preconditions or utilize necessary physical laws to reach answers. This work highlights and establishes a standardized diagnostic paradigm to guide the development of faithful, physically-grounded VLMs.
title NICE FACT: Diagnosing and Calibrating VLMs in Quantitative Reasoning for Kinematic Physics
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.08452