Related papers: SciFlow-Bench: Evaluating Structure-Aware Scientif…
Recent years have seen rapid advances in AI-driven image generation. Early diffusion models emphasized perceptual quality, while newer multimodal models like GPT-4o-image integrate high-level reasoning, improving semantic understanding and…
Creating high-quality figures and visualizations for scientific papers is a time-consuming task that requires both deep domain knowledge and professional design skills. Despite over 2.5 million scientific papers published annually, the…
Automating the creation of scientific diagrams from academic papers can significantly streamline the development of tutorials, presentations, and posters, thereby saving time and accelerating the process. Current text-to-image models…
Scientific papers use schematic diagrams to communicate methods, workflows, and system structure, yet existing scientific-figure corpora often mix them with plots, screenshots, and photographs and rarely preserve document context. We…
The prevalence of scientific workflows with high computational demands calls for their execution on various distributed computing platforms, including large-scale leadership-class high-performance computing (HPC) clusters. To handle the…
Scientific diagrams are essential for communicating complex methodologies in academic papers. A natural way for researchers to specify such diagrams is through rough sketches, where text labels, connectors, and spatial arrangements express…
The manual creation of system architecture diagrams for scientific papers is a time-consuming and subjective process, while existing generative models lack the necessary structural control and semantic understanding for this task. A primary…
While text-to-image generation has been extensively studied, generating images from scene graphs remains relatively underexplored, primarily due to challenges in accurately modeling spatial relationships and object interactions. To fill…
Learned representations of scientific documents can serve as valuable input features for downstream tasks without further fine-tuning. However, existing benchmarks for evaluating these representations fail to capture the diversity of…
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-Image (T2I) models…
Modern multimodal generators can now produce scientific figures at near-publishable quality, creating a new challenge for visual forensics and research integrity. Unlike conventional AI-generated natural images, scientific figures are…
Visual explanations are often plausible but not structurally faithful. We introduce CAMBench-QR, a structure-aware benchmark that leverages the canonical geometry of QR codes (finder patterns, timing lines, module grid) to test whether CAM…
Across the natural and life sciences, images have become a primary measurement modality, yet the dominant analytic paradigm remains semantics-first. Structure is recovered by predicting or enforcing domain-specific labels. This paradigm…
The rapid development of automated scientific survey generation technology has made it increasingly important to establish a comprehensive benchmark to evaluate the quality of generated surveys.Nearly all existing evaluation benchmarks rely…
We study technical image generation, where a model must synthesize information-dense, scientifically precise illustrations from detailed descriptions rather than merely produce visually plausible pictures. To quantify the progress, we…
Semantic segmentation and semantic image synthesis are two representative tasks in visual perception and generation. While existing methods consider them as two distinct tasks, we propose a unified framework (SemFlow) and model them as a…
While modern visual generation models excel at creating aesthetically pleasing natural images, they struggle with producing or editing structured visuals like charts, diagrams, and mathematical figures, which demand composition planning,…
While Vision Foundation Models (VFMs) excel at predictive tasks on satellite imagery, their performance can arise from visual correlations rather than underlying structural invariants, making even perception-based out-of-distribution…
Topological mapping offers a compact and robust representation for navigation, but progress in the field is hindered by the lack of standardized evaluation metrics, datasets, and protocols. Existing systems are assessed using different…
Existing rectified flow models are based on linear trajectories between data and noise distributions. This linearity enforces zero curvature, which can inadvertently force the image generation process through low-probability regions of the…