Yanghao Zhou, Haitian Li, Rexar Lin, Heyan Huang, Jinxing Zhou, Changsen Yuan, Tian Lan, Ziqin Zhou, Yudong Li, Jiajun Xu, Jingyun Liao, YiMing Cheng, Xuefeng Chen, Xian-Ling Mao, Yousheng Feng. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Natural language-guided drone geo-localization (DGL) provides an intuitive and scalable mode of human-drone interaction for tasks such as search, rescue, and surveillance. Recent Vision-Language Models (VLMs) can learn semantic correspondences between text and images during fine-tuning. However, their performance in DGL tasks remains constrained, as complex instructions and cluttered scenes often cause semantic dilution and granularity mismatch, leading to weak cross-modal alignment. Consequently, the models struggle with ambiguous targets and suffer from reduced localization accuracy. To address these challenges, we propose SAA-DGL, a framework for interpretable language-guided Drone Geo-Localization that enriches Semantic Attribute Alignment (SAA) with large language models (LLMs). It introduces two parameter-free cross-modal fusion modules: (1) the LLM-driven Cross-modal Semantic Attribute Enrichment (LCSAE) module, which extracts fine-grained attributes (e.g., color, shape, position) from text and embeds them into visual features as explicit semantic anchors, producing semantically enriched cross-modal representations; and (2) the Bidirectional Feature Alignment (BFA) module, which builds fusion relationships between visual and textual features via similarity-driven mechanisms, enabling effective integration of enriched visual and textual information. This design improves cross-modal consistency and interpretability while preserving pretrained alignment priors and enhancing training stability. Experiments on the GeoText-1652 benchmark show that SAA-DGL achieves state-of-the-art performance and strong robustness under complex visual and linguistic disturbances, validating its effectiveness for challenging geo-localization scenarios. We will release the code.

The task of brain tumor segmentation necessitates the processing of long Magnetic Resonance Imaging (MRI) sequences across multiple imaging modalities. Traditional convolutional neural networks often exhibit suboptimal ability of long-term memory, while Transformers demand substantial computational resources. To mitigate computational requirements and optimally utilize the information from various imaging modalities, we propose Mamba-based Vote and Cooperate Segmentation (VCSeg), for brain tumor segmentation. Features from the imaging sequences of each modality are extracted from multiple spatial orientations, and assigned different weights based on both modality and orientation considerations, enabling the model to adaptively learn modality-specific feature distribution for adult and child patient situation. The model employs a multi-modal cooperate module to further enhance the feature encoding capabilities. Additionally, deep supervision is applied to achieve progressive mask generation, thereby improving decoding quality. Experiments conducted on the BraTS2019-MEN and BraTS2023-PED datasets have demonstrated that VCSeg achieves state-of-the-art results, demonstrating the effectiveness of our advanced method.

Document-level relation extraction (RE) extends the identification of entity/mentions’ relation from the single sentence to the long document. It is more realistic and poses new challenges to relation representation and reasoning skills. In this article, we propose a novel model, SRLR , using S eparate Relation R epresentation and L ogical R easoning considering the indirect relation representation and complex reasoning of evidence sentence problems. Specifically, we first expand the judgment of relational facts from the entity-level to the mention-level, highlighting fine-grained information to capture the relation representation for the entity pair. Second, we propose a logical reasoning module to identify evidence sentences and conduct relational reasoning. Extensive experiments on two publicly available benchmark datasets demonstrate the effectiveness of our proposed SRLR as compared to 19 baseline models. Further ablation study also verifies the effects of the key components.

Document-level Event-Event Relation Extraction (DERE) aims to extract relations between events in a document.It challenges conventional sentence-level task (SERE) with difficult long-text understanding.In this paper, we propose a novel DERE model (SENDIR) for better document-level reasoning.Different from existing works that build an event graph via linguistic tools, SENDIR does not require any prior knowledge.The basic idea is to discriminate event pairs in the same sentence or span multiple sentences by assuming their different information density: 1) low density in the document suggests sparse attention to skip irrelevant information.Our module 1 designs various types of attention for event representation learning to capture long-distance dependence.2) High density in a sentence makes SERE relatively easy.Module 2 uses different weights to highlight the roles and contributions of intra-and intersentential reasoning, which introduces supportive event pairs for joint modeling.Extensive experiments demonstrate great improvements in SENDIR and the effectiveness of various sparse attention for document-level representations.Codes will be released later.

Video visual relation inference aims at extracting the relation triplets in the form of$>$in videos. With the development of deep learning, existing approaches are designed based on data-driven neural networks. But the datasets are always biased in terms of objects and relation triplets, which make relation inference challenging. Existing approaches often describe the relationships from visual, spatial, and semantic characteristics. The semantic description plays a key role to indicate the potential linguistic connections between objects, that are crucial to transfer knowledge across relationships, especially for the determination of novel relations. However, in these works, the semantic features are not emphasized, but simply obtained by mapping object labels, which can not reflect sufficient linguistic meanings. To alleviate the above issues, we propose a novel network, termed Concept-Enhanced Relation Network (CERN), to facilitate video visual relation inference. Thanks to the attributes and linguistic contexts implied in concepts, the semantic representations aggregated with related concept knowledge of objects are of benefit to relation inference. To this end, we incorporate retrieved concepts with local semantics of objects via the gating mechanism to generate the concept-enhanced semantic representations. Extensive experimental results show that our approach has achieved state-of-the-art performance on two public datasets: ImageNet-VidVRD and VidOR.

The Graph Convolutional Network (GCN) is a universal relation extraction method that can predict relations of entity pairs by capturing sentences’ syntactic features. However, existing GCN methods often use dependency parsing to generate graph matrices and learn syntactic features. The quality of the dependency parsing will directly affect the accuracy of the graph matrix and change the whole GCN’s performance. Because of the influence of noisy words and sentence length in the distant supervised dataset, using dependency parsing on sentences causes errors and leads to unreliable information. Therefore, it is difficult to obtain credible graph matrices and relational features for some special sentences. In this article, we present a Multi-Graph Cooperative Learning model (MGCL), which focuses on extracting the reliable syntactic features of relations by different graphs and harnessing them to improve the representations of sentences. We conduct experiments on a widely used real-world dataset, and the experimental results show that our model achieves the state-of-the-art performance of relation extraction.

Distant supervision for relation extraction is an efficient method to reduce labor costs and has been widely used to seek novel relational facts in large corpora, which can be identified as a multi-instance multi-label problem. However, existing distant supervision methods suffer from selecting important words in the sentence and extracting valid sentences in the bag. Towards this end, we propose a novel approach to address these problems in this paper. Firstly, we propose a linear attenuation simulation to reflect the importance of words in the sentence with respect to the distances between entities and words. Secondly, we propose a non-independent and identically distributed (non-IID) relevance embedding to capture the relevance of sentences in the bag. Our method can not only capture complex information of words about hidden relations, but also express the mutual information of instances in the bag. Extensive experiments on a benchmark dataset have well-validated the effectiveness of the proposed method.