paper-with-me

홈 › Papers

Towards Characterizing Scientific Image Utility and Upgradability

2026-06-02 · WenZhe Li, Qihang Yan, Liang Chen, Junying Wang, Farong Wen, Yijin Guo, Chunyi Li, Zicheng Zhang, Guangtao Zhai arxiv

Scientific images function as critical evidence in research communication, yet their integrity faces unprecedented threats from AI-generated content that introduces subtle but consequential errors. Existing evaluation paradigms prove inadequate: perceptual quality metrics poorly correlate with scientific validity, while language models lack domain-specific verification capabilities. To address this gap, we propose the \textbf{S}cientific \textbf{I}mage \textbf{U}tility and \textbf{U}pgradability \textbf{A}ssessment (\textbf{SIU$^2$A}) framework, which introduces two complementary dimensions for scientific image evaluation. \textbf{Utility} encompasses \textit{error detection} (identifying scientific inaccuracies) and \textit{correction feasibility} (assessing whether errors can be reliably repaired). \textbf{Upgradability} measures the quality of correction. We categorize scientific image corruption into four fundamental types: Detail Distortion, Incompleteness, False Content, and Entity Confusion. Based on this taxonomy, we construct SIU$^2$A-Benchmark, a dataset with expert annotations for error identification and repair. The framework implements a two-stage evaluation protocol: the \textit{Utility} stage evaluates error detection capability and repair instruction generation, while the \textit{Upgradability} stage assesses whether corrections faithfully restore scientific validity without compromising existing accurate information. Experiments reveal that current multimodal systems exhibit significant limitations in both scientific error assessment and faithful correction, exposing a fundamental gap between visual perception and scientific usability.

📄 PDF Abstract BibTeX arXiv:2606.03401

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Scientific Image Synthesis: Benchmarking, Methodologies, and Downstream Utility

2026-01-17 · Honglin Lin, Chonghan Qin, Zheng Liu, Qizhi Pei 외 arxiv

While synthetic data has proven effective for improving scientific reasoning in the text domain, multimodal reasoning remains constrained by the difficulty of synthesizing scientifically rigorous images. Existing Text-to…

Multimodal Reasoning

Interpretation of Crystal Energy Landscapes with Kolmogorov-Arnold Networks

2026-04-06 · Gen Zu, Ning Mao, Claudia Felser, Yang Zhang arxiv

Characterizing crystalline energy landscapes is essential to predicting thermodynamic stability, electronic structure, and functional behavior. While machine learning (ML) enables rapid property predictions, the "black-b…

Formation Energy

Equivariance Is Not All You Need: Characterizing the Utility of Equivariant Graph Neural Networks for Particle Physics Tasks

2023-11-06 · Savannah Thais, Daniel Murnane

Incorporating inductive biases into ML models is an active area of ML research, especially when ML models are applied to data about the physical world. Equivariant Graph Neural Networks (GNNs) have recently become a popu…

All

ROIAL: Region of Interest Active Learning for Characterizing Exoskeleton Gait Preference Landscapes

2020-11-09 · Kejun Li, Maegan Tucker, Erdem Biyik, Ellen Novoseller 외

Characterizing what types of exoskeleton gaits are comfortable for users, and understanding the science of walking more generally, require recovering a user's utility landscape. Learning these landscapes is challenging, …

Active Learning

Comparative Patience

2024-07-02 · Mark Whitmeyer

We begin by formulating and characterizing a dominance criterion for prize sequences: $x$ dominates $y$ if any impatient agent prefers $x$ to $y$. With this in hand, we define a notion of comparative patience. Alice is m…