Pedro Ortiz Suarez, Laurie Burchell, Catherine Arnett, Rafael Mosquera, Sara Hincapié Monsalve, Thom Vaughan, Damian Stewart, Malte Ostendorff, Idris Abdulmumin, Vukosi Marivate, Shamsuddeen Hassan Muhammad, Atnafu Lambebo Tonja, Hend Al-Khalifa, Nadia Ghezaiel Hammouda, Verrah Akinyi Otiende, Tack Hwa Wong, Jakhongir Saydaliev, Melika Nobakhtian, Muhammad Ravi Shulthan Habibi, Chalamalasetti Kranti, Carol Muchemi, Khang Nguyen, Faisal Muhammad Adam, Luis Frentzen Salim, Reem Alqifari, Cynthia Jayne Amol, Joseph Marvin Imperial, Ilker Kesen, Ahmad Mustafid, Pavel Stepachev, Leshem Choshen, David Anugraha, Hamada Nayel, Seid Muhie Yimam, Vallerie Alexandra Putra, My Chiffon Nguyen, Azmine Toushik Wasi, Gouthami Vadithya, Rob Van Der Goot, Lanwenn ar C’horr, Karan Dua, Andrew Yates, Mithil Bangera, Yeshil Bangera, Hitesh Laxmichand Patel, Shu Okabe, Fenal Ashokbhai Ilasariya, Dmitry Gaynullin, Genta Indra Winata, Yiyuan Li, Juan Pablo Martínez, Amit Agarwal, Ikhlasul Akmal Hanif, Raia Abu Ahmad, Esther Adenuga, Filbert Aurelian Tjiaranata, Weerayut Buaphet, Michael Anugraha, Sowmya Vajjala, Benjamin L Rice, Azril Hafizi Amirudin, Jesujoba Oluwadara Alabi, Srikant Panda, Yassine Toughrai, Bruhan Kyomuhendo, Daniel Ruffinelli, Akshata, Manuel Goulão, Ej Zhou, Ingrid Gabriela Franco Ramirez, Cristina Aggazzotti, Konstantin Dobler, Jun Kevin, Quentin Pagès, Nicholas Andrews, Nuhu Ibrahim, Mattes Ruckdeschel, Amr Keleg, Mike Zhang, Casper Rufaro Muziri, Saron Samuel, Sotaro Takeshita, Kun Kerdthaisong, Luca Foppiano, Rasul Dent, Tommaso Green, Ahmad Mustapha Wali, Kamohelo Makaaka, Vicky Feliren, Inshirah Idris, Hande Celikkanat, Abdulhamid Abubakar, Jean Maillard, Benoît Sagot, Thibault Clérice, Kenton Murray, Sarah K. K. Luger. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

As a core component of the maritime Internet of Things (IoT), the Automatic Identification System (AIS) continuously collects dynamic vessel navigation data, providing a solid foundation for addressing complex maritime traffic prediction tasks that support intelligent Vessel Traffic Services (VTS), such as vessel trajectory prediction and vessel arrival time (VAT) estimation. However, existing methods typically focus on single prediction objectives, falling short of meeting practical multi-task requirements. To address this gap, this study proposes a geospatial grid-constrained deep learning framework based on AIS data to simultaneously handle three key prediction tasks: vessel trajectory prediction, whether the vessel arrives within the specified time, and VAT. The framework incorporates a dynamic patch construction method and a Graph Soft Evolution (GSE) module to capture temporal correlations among observations under spatial grid constraints. An encoder-decoder architecture is introduced, where the encoder employs a Squeeze-and-Excitation (SE) block to adaptively select feature channels, and the decoder models dependencies across both variable and temporal dimensions. In a case study of New York Harbor, the model achieved an R² of 0.8386 and RMSE of 0.0329 for latitude increment prediction, and an R² of 0.8432 with RMSE of 0.0322 for longitude increment prediction. It also attained 99.83% accuracy in arrival status prediction and an R² of 0.9350 with RMSE of 0.0701 for VAT prediction. The framework demonstrated effectiveness in port scheduling and robust generalizability in cross-validation experiments at the Port of Los Angeles, thereby demonstrating its substantial potential to enhance the operational efficiency of VTS within maritime IoT systems.

Unmanned Aerial Vehicle (UAV) search has been widely applied in critical mission scenarios such as battlefield reconnaissance and disaster response. Due to uncertainties caused by target maneuverability and environmental threats, the development of multi-UAV distributed cooperative search methods to overcome the limitations of single-UAV perception has become imperative. This study addresses the decision optimization problem for multi-UAV cooperative dynamic target search in complex adversarial environments and proposes a systematic decision optimization framework. Firstly, an environmental perception system model is constructed by integrating a multiple distribution hypothesis target motion prediction model with a multi-dimensional search map model, which incorporates target existence probability, environmental uncertainty, and pheromone-inspired coordination signals, and achieves situational updates through dynamic Bayesian inference. Secondly, a distributed model predictive control (DMPC) architecture with motion encoding mechanisms and a lightweight communication protocol is designed to effectively alleviate communication resource dependence. Furthermore, Genetic Programming (GP) algorithm is combined with DMPC to autonomously generate cooperative search strategies that satisfy multiple conditional constraints. Simulation results demonstrate that the proposed method significantly outperforms traditional search methods in terms of dynamic target search timeliness and adaptability to complex environments, particularly exhibiting stronger robustness in adversarial scenarios.

Fuzzy reasoning is vital due to the frequent use of imprecise information in daily contexts.However, the ability of current large language models (LLMs) to handle such reasoning remains largely uncharted.In this paper, we introduce a new benchmark, FROG, for fuzzy reasoning, featuring real-world mathematical word problems that incorporate generalized quantifiers.Our experimental findings reveal that fuzzy reasoning continues to pose significant challenges for LLMs.Moreover, we find that existing methods designed to enhance reasoning do not consistently improve performance in tasks involving fuzzy logic.Additionally, our results show an inverse scaling effect in the performance of LLMs on FROG.Interestingly, we also demonstrate that strong mathematical reasoning skills are not necessarily indicative of success on our benchmark 1 .

The evolution of Artificial Intelligence (AI) has been significantly accelerated by advancements in Large Language Models (LLMs) and Large Multimodal Models (LMMs), gradually showcasing potential cognitive reasoning abilities in problem-solving and scientific discovery (i.e., AI4Science) once exclusive to human intellect. To comprehensively evaluate current models' performance in cognitive reasoning abilities, we introduce OlympicArena, which includes 11,163 bilingual problems across both text-only and interleaved text-image modalities. These challenges encompass a wide range of disciplines spanning seven fields and 62 international Olympic competitions, rigorously examined for data leakage. We argue that the challenges in Olympic competition problems are ideal for evaluating AI's cognitive reasoning due to their complexity and interdisciplinary nature, which are essential for tackling complex scientific challenges and facilitating discoveries. Beyond evaluating performance across various disciplines using answer-only criteria, we conduct detailed experiments and analyses from multiple perspectives. We delve into the models' cognitive reasoning abilities, their performance across different modalities, and their outcomes in process-level evaluations, which are vital for tasks requiring complex reasoning with lengthy solutions. Our extensive evaluations reveal that even advanced models like GPT-4o only achieve a 39.97\% overall accuracy (28.67\% for mathematics and 29.71\% for physics), illustrating current AI limitations in complex reasoning and multimodal integration. Through the OlympicArena, we aim to advance AI towards superintelligence, equipping it to address more complex challenges in science and beyond. We also provide a comprehensive set of resources to support AI research, including a benchmark dataset, an open-source annotation platform, a detailed evaluation tool, and a leaderboard with automatic submission features.

Generalization remains a central challenge in machine learning. In this work, we propose *Learning from Teaching* (**LoT**), a novel regularization technique for deep neural networks to enhance generalization. Inspired by the human ability to capture concise and abstract patterns, we hypothesize that generalizable correlations are expected to be easier to imitate. LoT operationalizes this concept to improve the generalization of the main model with auxiliary student learners. The student learners are trained by the main model and, in turn, provide feedback to help the main model capture more generalizable and imitable correlations. Our experimental results across several domains, including Computer Vision, Natural Language Processing, and methodologies like Reinforcement Learning, demonstrate that the introduction of LoT brings significant benefits compared to training models on the original dataset. The results suggest the effectiveness and efficiency of LoT in identifying generalizable information at the right scales while discarding spurious data correlations, thus making LoT a valuable addition to current machine learning. Code is available at https://github.com/jincan333/LoT.

Generalized quantifiers (e.g., few, most) are used to indicate the proportions predicates are satisfied (for example, some apples are red).One way to interpret quantifier semantics is to explicitly bind these satisfactions with percentage scopes (e.g., 30%-40% of apples are red).This approach can be helpful for tasks like logic formalization and surface-form quantitative reasoning (Gordon and Schubert, 2010;Roy et al., 2015).However, it remains unclear if recent foundation models possess this ability, as they lack direct training signals.To explore this, we introduce QuRe, a crowdsourced dataset of human-annotated generalized quantifiers in Wikipedia sentences featuring percentage-equipped predicates.We explore quantifier comprehension in language models using PRESQUE, a framework that combines natural language inference and the Rational Speech Acts framework.Experimental results on the HVD dataset and QuRe illustrate that PRESQUE, employing pragmatic reasoning, performs 20% better than a literal reasoning baseline when predicting quantifier percentage scopes, with no additional training required 1 .

Atmospheric data assimilation is essential for numerical weather prediction. Ensemble data assimilation connects multiple instances of an atmospheric model through a Kalman filter-based algorithm, which is regarded as a challenging computing task today. In this work, we build a fast, low-cost, and scalable atmospheric data assimilation prototype, DIDA, for the new-generation Sunway supercomputer, including: (1) a framework that enables flexible deployment of components, and manages and optimizes data communication among modules, achieving maximum resource efficiency; (2) an accurate, robust, UNet-based surrogate model for atmospheric dynamic simulation to generate the background ensemble; (3) a batch-LETKF algorithm with high-performance eigenvalue decomposition, which is up to 7.37 times faster than existing numerical libraries while exhibiting almost linear scalability. Experimental evaluations show that our AI-integrated ensemble data assimilation prototype can complete hour-cycle assimilation in minutes, maintain linear scalability, and save an order of magnitude of computing resources, compared with the traditional method.

Pretrained language models (PLMs) have been shown to accumulate factual knowledge during pretraining (Petroni et al., 2019).Recent works probe PLMs for the extent of this knowledge through prompts either in discrete or continuous forms.However, these methods do not consider symmetry of the task: object prediction and subject prediction.In this work, we propose Symmetrical Prompt Enhancement (SPE), a continuous prompt-based method for factual probing in PLMs that leverages the symmetry of the task by constructing symmetrical prompts for subject and object prediction.Our results on a popular factual probing dataset, LAMA, show significant improvement of SPE over previous probing methods.

Contextual representations learned by language models can often encode undesirable attributes, like demographic associations of the users, while being trained for an unrelated target task.We aim to scrub such undesirable attributes and learn fair representations while maintaining performance on the target task.In this paper, we present an adversarial learning framework "Adversarial Scrubber" (ADS), to debias contextual representations.We perform theoretical analysis to show that our framework converges without leaking demographic information under certain conditions.We extend previous evaluation techniques by evaluating debiasing performance using Minimum Description Length (MDL) probing.Experimental evaluations on 8 datasets show that ADS generates representations with minimal information about demographic attributes while being maximally informative about the target task.

Current grammatical error correction (GEC) models typically consider the task as sequence generation, which requires large amounts of annotated data and limit the applications in data-limited settings. We try to incorporate contextual information from pre-trained language model to leverage annotation and benefit multilingual scenarios. Results show strong potential of Bidirectional Encoder Representations from Transformers (BERT) in grammatical error correction task.

The traditional method is used to deal with massive remote sensing data stored in low efficiency and poor scalability. This article presents a parallel processing method based on MapReduce and HBase. The filling of remote sensing images by the Hilbert curve makes the MapReduce method construct pyramids in parallel to reduce network communication between nodes. Then, the authors design a massive remote sensing data storage model composed of metadata storage model, index structure and filter column family. Finally, this article uses MapReduce frameworks to realize pyramid construction, storage and query of remote sensing data. The experimental results show that this method can effectively improve the speed of data writing and querying, and has good scalability.

The responsibility of resource server is to store and manage the reusable and product-specific assets produced in the process of software development applying software product line principals. Separately designed for each specific resource type, classical resource server could not satisfy the demands for mass storage of various resource types in collaborative development environment. Interception design pattern is introduced as a novel means to implement resource server. Interceptors with specific functionalities are developed and configured for various resource types in domain to provide a uniform framework to deal with distinct types of resource, including customized resource type. The description of the resource handling process using Pi calculus demonstrates the validity of the approach.