Peter Zeng, Weiling Li, Amie J. Paige, Zhengxiang Wang, Panagiotis Kaliosis, Dimitris Samaras, Gregory J. Zelinsky, Susan Brennan, Owen Rambow. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

The paper explores the performance of LLMs in the context of multi-dimensional analytic writing assessments, i.e. their ability to provide both scores and comments based on multiple assessment criteria.Using a corpus of literature reviews written by L2 graduate students and assessed by human experts against 9 analytic criteria, we prompt several popular LLMs to perform the same task under various conditions.To evaluate the quality of feedback comments, we apply a novel feedback comment quality evaluation framework.This framework is interpretable, cost-efficient, scalable, and reproducible, compared to existing methods that rely on manual judgments.We find that LLMs can generate reasonably good and generally reliable multi-dimensional analytic assessments.We release our corpus and code 1 for reproducibility.

During conversation, speakers collaborate on spontaneous referring expressions, which they can then re-use in subsequent conversation with the same partner.Understanding such referring expressions is an important ability for an embodied agent so that it can carry out tasks in the real world.This requires integrating and understanding language, vision, and conversational interaction.We study the capabilities of seven state-of-the-art Large Vision Language Models (LVLMs) as overhearers to a corpus of spontaneous conversations between pairs of human discourse participants engaged in a collaborative object-matching task.We find that such a task remains challenging for current LVLMs, which fail to show a consistent performance improvement as they overhear more conversations from the same discourse participants repeating the same task for multiple rounds.We release our corpus and code 1 for reproducibility and to facilitate future research.

Automatic extraction of roads from remote sensing imagery has numerous applications, such as urban planning and navigation. However, the quality of images is limited, and most existing road extraction methods suffer from discontinuity. Additionally, there remains a gap between pixel-based road segmentation and road vectorization. To address these challenges, we introduce a method that utilizes a multistage feature fusion attention network (MFFANet) and regularization algorithm to extract road surfaces, centerlines, edges, and intersections. MFFANet comprises three components. The complementary feature embedding module (CFEM) adaptively encodes remote sensing images, vehicle trajectories, and OpenStreetMap (OSM) points to capture specific modal features. The multistage feature fusion module (MFFM) is proposed to improve the completeness and connectivity of road extraction by integrating multisource geospatial features. The multilevel mask generation module (MMGM) enhances road segmentation results through a weighting mechanism that can simultaneously predict local road segments, road sections, and road network masks. Additionally, a novel joint loss function is introduced to balance local and global optimization. In the regularization stage, fused hierarchical masks generate road segments, with a skeleton refinement for centerlines and widths, followed by smooth segment reconstruction and extraction of edges and intersections. Experiments on different datasets demonstrate that our designed fusion attention network outperforms the latest road segmentation models; our regularization algorithm shows strong robustness and the comprehensive metrics of vectorized road line extraction exceeds 70%.

The IEEE VIS Conference (VIS) recently rebranded itself as a unified conference and officially positioned itself within the discipline of Data Science. Driven by this movement, we investigated (1) who contributed to VIS, and (2) where VIS stands in the scientific world. We examined the authors and fields of study of 3,240 VIS publications in the past 32 years based on data collected from OpenAlex and IEEE Xplore, among other sources. We also examined the citation flows from referenced papers (i.e., those referenced in VIS) to VIS, and from VIS to citing papers (i.e., those citing VIS). We found that VIS has been becoming increasingly popular and collaborative. The number of publications, of unique authors, and of participating countries have been steadily growing. Both cross-country collaborations, and collaborations between educational and non-educational affiliations, namely "cross-type collaborations", are increasing. The dominance of the US is decreasing, and authors from China are now an important part of VIS. In terms of author affiliation types, VIS is increasingly dominated by authors from universities. We found that the topics, inspirations, and influences of VIS research is limited such that (1) VIS, and their referenced and citing papers largely fall into the Computer Science domain, and (2) citations flow mostly between the same set of subfields within Computer Science. Our citation analyses showed that award-winning VIS papers had higher citations. Interactive visualizations, replication data, source code and supplementary material are available at https://32vis.hongtaoh.com and https://osf.io/zkvjm.

This paper introduces to use semi-supervised learning for large scale image co segmentation. Different from traditional unsupervised cosegmentation that does not use any segmentation ground truth, semi-supervised cosegmentation exploits the similarity from both the very limited training image foregrounds, as well as the common object shared between the large number of unsegmented images. This would be a much practical way to effectively co segment a large number of related images simultaneously, where previous unsupervised co segmentation work poorly due to the large variances in appearance between different images and the lack of segmentation ground truth for guidance in co segmentation. For semi-supervised co segmentation in large scale, we propose an effective method by minimizing an energy function, which consists of the inter-image distance, the intra-image distance and the balance term. We also propose an iterative updating algorithm to efficiently solve this energy function, which decomposes the original energy minimization problem into sub-problems, and updates each image alternatively to reduce the number of variables in each sub-problem for computation efficiency. Experiment results on iCoseg and Pascal VOC datasets show that the proposed co segmentation method can effectively co segment hundreds of images in less than one minute. And our semi-supervised co segmentation is able to outperform both unsupervised co segmentation as well as fully supervised single image segmentation, especially when the training data is limited.

Image-To-Class (I2C) distance is a novel distance used for image classification and has successfully handled datasets with large intra-class variances. However, it uses Euclidean distance for measuring the distance between local features in different classes, which may not be the optimal distance metric in real image classification problems. In this article, we propose a distance metric learning method to improve the performance of I2C distance by learning per-class Mahalanobis metrics in a large margin framework. Our I2C distance is adaptive to different classes by combining with the learned metric for each class. These multiple per-class metrics are learned simultaneously by forming a convex optimization problem with the constraints that the I2C distance from each training image to its belonging class should be less than the distances to other classes by a large margin. A subgradient descent method is applied to efficiently solve this optimization problem. For efficiency and scalability to large-scale problems, we also show how to simplify the method to learn a diagonal matrix for each class. We show in experiments that our learned Mahalanobis I2C distance can significantly outperform the original Euclidean I2C distance as well as other distance metric learning methods in several prevalent image datasets, and our simplified diagonal matrices can preserve the performance but significantly speed up the metric learning procedure for large-scale datasets. We also show in experiment that our method is able to correct the class imbalance problem, which usually leads the NN-based methods toward classes containing more training images.

Image tagging is an important technique for the image content understanding and text based image processing. Given a selection of images, how to tag these images efficiently and effectively is an interesting problem. In this paper, a novel semi-auto image tagging technique is proposed: By assigning each image a category label first, our method can automatically recommend those promising tags to each image by utilizing existing vast web data. The main contributions of our paper can be highlighted as follows: (i) By assigning each image a category label, our method can automatically recommend other tags to the image, thus reducing the human annotation efforts. Meanwhile, our method guarantee tags' diversity due to abundant web data. (ii) We use sparse coding to automatically select those semantically related images for tag propagation. (iii) Local & global ranking agglomeration will make our method robust to noisy tags. We use Event dataset as the images to be tagged, and crawled Flickr images with their associated tags according to the category label in Event dataset as the auxiliary web data. Experimental results show that our method achieves promising performance for image tagging, which proves the effectiveness of our method.

BACKGROUND: Biochemical networks play an essential role in systems biology. Rapidly growing network data and versatile research activities call for convenient visualization tools to aid intuitively perceiving abstract structures of networks and gaining insights into the functional implications of networks. There are various kinds of network visualization software, but they are usually not adequate for visual analysis of complex biological networks mainly because of the two reasons: 1) most existing drawing methods suitable for biochemical networks have high computation loads and can hardly achieve near real-time visualization; 2) available network visualization tools are designed for working in certain network modeling platforms, so they are not convenient for general analyses due to lack of broader range of readily accessible numerical utilities. RESULTS: We present LucidDraw as a visual analysis tool, which features (a) speed: typical biological networks with several hundreds of nodes can be drawn in a few seconds through a new layout algorithm; (b) ease of use: working within MATLAB makes it convenient to manipulate and analyze the network data using a broad spectrum of sophisticated numerical functions; (c) flexibility: layout styles and incorporation of other available information about functional modules can be controlled by users with little effort, and the output drawings are interactively modifiable. CONCLUSIONS: Equipped with a new grid layout algorithm proposed here, LucidDraw serves as an auxiliary network analysis tool capable of visualizing complex biological networks in near real-time with controllable layout styles and drawing details. The framework of the algorithm enables easy incorporation of extra biological information, if available, to influence the output layouts with predefined node grouping features.

In this paper, we propose a large margin framework to learn the local instance-to-class distance function using local patch-based feature vectors, which satisfies the property that distance from instance to its own class should be less than the distance to other class. This instance-to-class distance is modeled as the weighted combination of the distance from every patch in test image to its nearest patch in training class, where the weight is learned through the above learning phase. We evaluate the proposed method on human action datasets and compare with related methods. It is shown that the proposed method achieves promising performance and improves the efficiency.