Vision-to-code tasks require models to reconstruct structured visual inputs, such as charts, tables, and SVGs, into executable or structured representations with high visual fidelity. While recent Large Vision Language Models (LVLMs) achieve strong results via supervised fine-tuning, reinforcement learning remains challenging due to misaligned reward signals. Existing rewards either rely on textual rules or coarse visual embedding similarity, both of which fail to capture fine-grained visual discrepancies and are vulnerable to reward hacking. We propose Visual Equivalence Reward Model (Visual-ERM), a multimodal generative reward model that provides fine-grained, interpretable, and task-agnostic feedback to evaluate vision-to-code quality directly in the rendered visual space. Integrated into RL, Visual-ERM improves Qwen3-VL-8B-Instruct by +8.4 on chart-to-code and yields consistent gains on table and SVG parsing (+2.7, +4.1 on average), and further strengthens test-time scaling via reflection and revision. We also introduce VisualCritic-RewardBench (VC-RewardBench), a benchmark for judging fine-grained image-to-image discrepancies on structured visual data, where Visual-ERM at 8B d
Visual representation learning has been a cornerstone in computer vision, involving typical forms such as visual embeddings, structural symbols, and text-based representations. Despite the success of CLIP-type visual embeddings, they often lack access to world knowledge critical for visual reasoning. In this work, we propose Visual Table, a novel form of visual representation tailored for visual reasoning. Visual tables are constructed as hierarchical descriptions of visual scenes, featuring a scene description and multiple object-centric descriptions covering categories, attributes, and knowledge. Thanks to the structural and textual formats, visual tables offer unique advantages over mere visual embeddings, such as interpretability and controllable editing. Furthermore, they deliver instance-level world knowledge and detailed attributes that are essential for visual reasoning. To create visual tables, we develop a generator trained on the dataset with collected, small-scale annotations. Extensive results on 11 visual reasoning benchmarks demonstrate that the generated visual tables significantly outperform previous structural and text-based representations. Moreover, they consist
Collaboration between health science and visual analytics research is often hindered by different, sometimes incompatible approaches to research design. Health science often follows hypothesis-driven protocols, registered in advance, and focuses on reproducibility and risk mitigation. Visual analytics, in contrast, relies on iterative data exploration, prioritizing insight generation and analytic refinement through user interaction. These differences create challenges in interdisciplinary projects, including misaligned terminology, unrealistic expectations about data readiness, divergent validation norms, or conflicting explainability requirements. To address these persistent tensions, we identify seven research needs and actions: (1) guidelines for broader community adoption, (2) agreement on quality and validation benchmarks, (3) frameworks for aligning research tasks, (4) integrated workflows combining confirmatory and exploratory stages, (5) tools for harmonizing terminology across disciplines, (6) dedicated bridging roles for transdisciplinary work, and (7) cultural adaptation and mutual recognition. We organize these needs in a framework with three areas: culture, standards,
Precision medicine in ophthalmology requires accurate longitudinal predictions, but the fragmented nature of multimodal clinical data remains a barrier to forecasting. We introduce OphthaDT, an LLM-based digital twin for ophthalmology that serializes longitudinal patient histories from 3,220 patients across four Phase III clinical trials into structured narratives to forecast best corrected visual acuity (BCVA). In benchmarks spanning up to 100 weeks, OphthaDT demonstrated the lowest prediction error in neovascular age-related macular degeneration (nAMD), achieving an average mean absolute error (MAE) reduction of 6.0% compared to all baselines. In diabetic macular edema (DME), OphthaDT demonstrated competitive performance against all baselines while outperforming Random Forest and XGBoost by an average MAE reduction of 2.6% and 6.9%, respectively. Results reveal that OphthaDT's predictive advantage scales with trajectory complexity: whereas linear models remain effective for the more stable treatment responses of DME, OphthaDT's capacity is better suited for capturing the high longitudinal variability of nAMD. Finally, OphthaDT handles irregular sampling without imputation, positi
Vision impairment affects millions globally, and early detection is critical to preventing irreversible vision loss. Ophthalmology workflows require clinicians to integrate medical images, structured clinical data, and free-text notes to determine disease severity and management, which is time-consuming and burdensome. Recent multimodal large language models (MLLMs) show promise, but existing general and medical MLLMs perform poorly in ophthalmology, and few ophthalmology-specific MLLMs are openly available. We present VOLMO (Versatile and Open Large Models for Ophthalmology), a model-agnostic, data-open framework for developing ophthalmology-specific MLLMs. VOLMO includes three stages: ophthalmology knowledge pretraining on 86,965 image-text pairs from 26,569 articles across 82 journals; domain task fine-tuning on 26,929 annotated instances spanning 12 eye conditions for disease screening and severity classification; and multi-step clinical reasoning on 913 patient case reports for assessment, planning, and follow-up care. Using this framework, we trained a compact 2B-parameter MLLM and compared it with strong baselines, including InternVL-2B, LLaVA-Med-7B, MedGemma-4B, MedGemma-2
Although there are various ways to represent data patterns and models, visualization has been primarily taught in many data science courses for its efficiency. Such vision-dependent output may cause critical barriers against those who are blind and visually impaired and people with learning disabilities. We argue that instructors need to teach multiple data representation methods so that all students can produce data products that are more accessible. In this paper, we argue that accessibility should be taught as early as the introductory course as part of the data science curriculum so that regardless of whether learners major in data science or not, they can have foundational exposure to accessibility. As data science educators who teach accessibility as part of our lower-division courses in two different institutions, we share specific examples that can be utilized by other data science instructors.
The analysis of spatiotemporal data is essential in domains such as epidemiology and environmental monitoring, where understanding the interplay between spatially distributed phenomena and their temporal evolution is critical. Dense pixel visualizations offer a compact, effective overview of spatiotemporal dynamics. However, the necessary linearization of 2D geographic space into a 1D ordering inevitably introduces structural distortions that manifest as visual artifacts. We propose a measure-driven visual analytics approach that captures visual artifacts through neighborhood preservation measures for 1D orderings and renders them using visual boosting techniques such as glyphs, halos, and hatching. We demonstrate our approach through a usage scenario analyzing COVID-19 incidence data across German districts, showing that interactive, measure-driven boosting enables analysts to reliably distinguish genuine spatial patterns from linearization artifacts.
Accurate diagnosis of ophthalmic diseases relies heavily on the interpretation of multimodal ophthalmic images, a process often time-consuming and expertise-dependent. Visual Question Answering (VQA) presents a potential interdisciplinary solution by merging computer vision and natural language processing to comprehend and respond to queries about medical images. This review article explores the recent advancements and future prospects of VQA in ophthalmology from both theoretical and practical perspectives, aiming to provide eye care professionals with a deeper understanding and tools for leveraging the underlying models. Additionally, we discuss the promising trend of large language models (LLM) in enhancing various components of the VQA framework to adapt to multimodal ophthalmic tasks. Despite the promising outlook, ophthalmic VQA still faces several challenges, including the scarcity of annotated multimodal image datasets, the necessity of comprehensive and unified evaluation methods, and the obstacles to achieving effective real-world applications. This article highlights these challenges and clarifies future directions for advancing ophthalmic VQA with LLMs. The development
Reinforcement Fine-Tuning (RFT) in Large Reasoning Models like OpenAI o1 learns from feedback on its answers, which is especially useful in applications when fine-tuning data is scarce. Recent open-source work like DeepSeek-R1 demonstrates that reinforcement learning with verifiable reward is one key direction in reproducing o1. While the R1-style model has demonstrated success in language models, its application in multi-modal domains remains under-explored. This work introduces Visual Reinforcement Fine-Tuning (Visual-RFT), which further extends the application areas of RFT on visual tasks. Specifically, Visual-RFT first uses Large Vision-Language Models (LVLMs) to generate multiple responses containing reasoning tokens and final answers for each input, and then uses our proposed visual perception verifiable reward functions to update the model via the policy optimization algorithm such as Group Relative Policy Optimization (GRPO). We design different verifiable reward functions for different perception tasks, such as the Intersection over Union (IoU) reward for object detection. Experimental results on fine-grained image classification, few-shot object detection, reasoning groun
Imagine observing someone scratching their arm; to understand why, additional context would be necessary. However, spotting a mosquito nearby would immediately offer a likely explanation for the person's discomfort, thereby alleviating the need for further information. This example illustrates how subtle visual cues can challenge our cognitive skills and demonstrates the complexity of interpreting visual scenarios. To study these skills, we present Visual Riddles, a benchmark aimed to test vision and language models on visual riddles requiring commonsense and world knowledge. The benchmark comprises 400 visual riddles, each featuring a unique image created by a variety of text-to-image models, question, ground-truth answer, textual hint, and attribution. Human evaluation reveals that existing models lag significantly behind human performance, which is at 82% accuracy, with Gemini-Pro-1.5 leading with 40% accuracy. Our benchmark comes with automatic evaluation tasks to make assessment scalable. These findings underscore the potential of Visual Riddles as a valuable resource for enhancing vision and language models' capabilities in interpreting complex visual scenarios.
This Journal of Informetrics special issue aims to improve our understanding of the structure and dynamics of science by reviewing and advancing existing conceptualizations and models of scholarly activity. Several of these conceptualizations and models have visual manifestations supporting the combination and comparison of theories and approaches developed in different disciplines of science. Subsequently, we discuss challenges towards a theoretically grounded and practically useful science of science and provide a brief chronological review of relevant work. Then, we exemplarily present three conceptualizations of science that attempt to provide frameworks for the comparison and combination of existing approaches, theories, laws, and measurements. Finally, we discuss the contributions of and interlinkages among the eight papers included in this issue. Each paper makes a unique contribution towards conceptualizations and models of science and roots this contribution in a review and comparison with existing work.
A key trend in Large Reasoning Models (e.g., OpenAI's o3) is the native agentic ability to use external tools such as web browsers for searching and writing/executing code for image manipulation to think with images. In the open-source research community, while significant progress has been made in language-only agentic abilities such as function calling and tool integration, the development of multi-modal agentic capabilities that involve truly thinking with images, and their corresponding benchmarks, are still less explored. This work highlights the effectiveness of Visual Agentic Reinforcement Fine-Tuning (Visual-ARFT) for enabling flexible and adaptive reasoning abilities for Large Vision-Language Models (LVLMs). With Visual-ARFT, open-source LVLMs gain the ability to browse websites for real-time information updates and write code to manipulate and analyze input images through cropping, rotation, and other image processing techniques. We also present a Multi-modal Agentic Tool Bench (MAT) with two settings (MAT-Search and MAT-Coding) designed to evaluate LVLMs' agentic search and coding abilities. Our experimental results demonstrate that Visual-ARFT outperforms its baseline b
GREX-PLUS (Galaxy Reionization EXplorer and PLanetary Universe Spectrometer) is a mission candidate for a JAXA strategic L-class mission to be launched in the 2030s. Its primary science goals are two-fold: galaxy formation and evolution, and planetary system formation and evolution. The GREX-PLUS spacecraft will carry a telescope with a 1 m primary mirror aperture cooled down to 50 K. The two science instruments will be onboard: a wide-field camera in the 2--8 $μ$m wavelength band and a high-resolution spectrometer with a wavelength resolution of 30,000 in the 10--18 $μ$m band. The GREX-PLUS wide-field camera aims to detect the first generation of galaxies at redshift $z>15$. The GREX-PLUS high-resolution spectrometer aims to identify the location of the water ``snowline'' in protoplanetary disks. Both instruments will provide unique datasets for a broad range of scientific topics, including galaxy mass assembly, the origin of supermassive blackholes, infrared background radiation, molecular spectroscopy in the interstellar medium, transit spectroscopy of exoplanet atmospheres, planetary atmospheres in the Solar System, and so on. This document is the second version of a collect
The large instantaneous sensitivity, a wide frequency coverage and flexible observation modes with large number of beams in the sky are the main features of the SKA observatory's two telescopes, the SKA-Low and the SKA-Mid, which are located on two different continents. Owing to these capabilities, the SKAO telescopes are going to be a game-changer for radio astronomy in general and pulsar astronomy in particular. The eleven articles in this special issue on pulsar science with the SKA Observatory describe its impact on different areas of pulsar science. In this lead article, a brief description of the two telescopes highlighting the relevant features for pulsar science is presented followed by an overview of each accompanying article, exploring the inter-relationship between different pulsar science use cases.
Mauve is a low-cost small satellite developed and operated by Blue Skies Space Ltd. The payload features a 13 cm telescope connected with a fibre that feeds into a UV-Vis spectrometer. The detector covers the 200-700 nm range in a single shot, obtaining low resolution spectra at R~20-65. Mauve has launched on 28th November 2025, reaching a 510 km Low-Earth Sun-synchronous orbit. The satellite will enable UV and visible observations of a variety of stellar objects in our Galaxy, filling the gaps in the ultraviolet space-based data. The researchers that have already joined the mission have defined the science themes, observational strategy and targets that Mauve will observe in the first year of operations. To date 10 science themes have been developed by the Mauve science collaboration for year 1, with observational strategies that include both long duration monitoring and short cadence snapshots. Here, we describe these themes and the science that Mauve will undertake in its first year of operations.
Large multimodal models such as Stable Diffusion can generate, detect, and classify new visual concepts after fine-tuning just a single word embedding. Do models learn similar words for the same concepts (i.e. <orange-cat> = orange + cat)? We conduct a large-scale analysis on three state-of-the-art models in text-to-image generation, open-set object detection, and zero-shot classification, and find that new word embeddings are model-specific and non-transferable. Across 4,800 new embeddings trained for 40 diverse visual concepts on four standard datasets, we find perturbations within an $ε$-ball to any prior embedding that generate, detect, and classify an arbitrary concept. When these new embeddings are spliced into new models, fine-tuning that targets the original model is lost. We show popular soft prompt-tuning approaches find these perturbative solutions when applied to visual concept learning tasks, and embeddings for visual concepts are not transferable. Code for reproducing our work is available at: https://visual-words.github.io.
Recently, natural language has been the primary medium for human-robot interaction. However, its inherent lack of spatial precision introduces challenges for robotic task definition such as ambiguity and verbosity. Moreover, in some public settings where quiet is required, such as libraries or hospitals, verbal communication with robots is inappropriate. To address these limitations, we introduce the Robotic Visual Instruction (RoVI), a novel paradigm to guide robotic tasks through an object-centric, hand-drawn symbolic representation. RoVI effectively encodes spatial-temporal information into human-interpretable visual instructions through 2D sketches, utilizing arrows, circles, colors, and numbers to direct 3D robotic manipulation. To enable robots to understand RoVI better and generate precise actions based on RoVI, we present Visual Instruction Embodied Workflow (VIEW), a pipeline formulated for RoVI-conditioned policies. This approach leverages Vision-Language Models (VLMs) to interpret RoVI inputs, decode spatial and temporal constraints from 2D pixel space via keypoint extraction, and then transform them into executable 3D action sequences. We additionally curate a specializ
The basic objective of data visualization is to provide an efficient graphical display for summarizing and reasoning about quantitative information. During the last decades, political science has accumulated a large corpus of various kinds of data such as comprehensive factbooks and atlases, characterizing all or most of existing states by multiple and objectively assessed numerical indicators within certain time lapse. As a consequence, there exists a continuous trend for political science to gradually become a more quantitative scientific field and to use quantitative information in the analysis and reasoning. It is believed that any objective analysis in political science must be multidimensional and combine various sources of quantitative information; however, human capabilities for perception of large massifs of numerical information are limited. Hence, methods and approaches for visualization of quantitative and qualitative data (and, especially multivariate data) is an extremely important topic. Data visualization approaches can be classified into several groups, starting from creating informative charts and diagrams (statistical graphics and infographics) and ending with ad
Recent studies have indicated that foundation models, such as BERT and GPT, excel in adapting to a variety of downstream tasks. This adaptability has established them as the dominant force in building artificial intelligence (AI) systems. As visualization techniques intersect with these models, a new research paradigm emerges. This paper divides these intersections into two main areas: visualizations for foundation models (VIS4FM) and foundation models for visualizations (FM4VIS). In VIS4FM, we explore the primary role of visualizations in understanding, refining, and evaluating these intricate models. This addresses the pressing need for transparency, explainability, fairness, and robustness. Conversely, within FM4VIS, we highlight how foundation models can be utilized to advance the visualization field itself. The confluence of foundation models and visualizations holds great promise, but it also comes with its own set of challenges. By highlighting these challenges and the growing opportunities, this paper seeks to provide a starting point for continued exploration in this promising avenue.
Data science and technology offer transformative tools and methods to science. This review article highlights latest development and progress in the interdisciplinary field of data-driven plasma science (DDPS). A large amount of data and machine learning algorithms go hand in hand. Most plasma data, whether experimental, observational or computational, are generated or collected by machines today. It is now becoming impractical for humans to analyze all the data manually. Therefore, it is imperative to train machines to analyze and interpret (eventually) such data as intelligently as humans but far more efficiently in quantity. Despite the recent impressive progress in applications of data science to plasma science and technology, the emerging field of DDPS is still in its infancy. Fueled by some of the most challenging problems such as fusion energy, plasma processing of materials, and fundamental understanding of the universe through observable plasma phenomena, it is expected that DDPS continues to benefit significantly from the interdisciplinary marriage between plasma science and data science into the foreseeable future.