In image–text retrieval, users often express abstract, incomplete, or polysemous intents rather than fully concrete visual descriptions. In contrast, existing retrieval benchmarks predominantly rely on object- and action-centric captions that presuppose detailed and visually grounded descriptions, leaving model behavior under semantically fuzzy queries largely underexplored. To address this gap, we introduce Flickr-ABS, an abstraction-aware image–text retrieval benchmark built upon Flickr30k. For each image, Flickr-ABS associates retrieval queries at three explicitly defined semantic levels, ranging from concrete scene descriptions to high-level conceptual interpretations. Extensive evaluations on a wide range of vision–language models reveal a substantial degradation in retrieval performance as query abstraction increases, highlighting the fragility of current retrieval systems under abstract semantic intent. We further demonstrate that jointly leveraging supervision from multiple abstraction levels can improve retrieval robustness for abstract queries while preserving performance on concrete ones. We further propose a semantic recall protocol that accounts for conceptual equivalence, enabling more faithful evaluation under high-level abstraction. Together, Flickr-ABS and the proposed evaluation protocol offer a practical benchmark for analyzing and improving abstraction-aware image–text retrieval. Our code is available at https://github.com/LT1anY/Flickr-abs.

Interactive image retrieval iteratively interacts with users to capture retrieval intent and refine textual queries, effectively mitigating the ambiguity and performance degradation inherent in single-round text-to-image retrieval. However, existing LLM-based methods largely rely on image captions or dialogue history to extract features within a limited candidate space. Consequently, they often generate questions that are either irrelevant to the target’s distinctive characteristics or fail to capture fine-grained visual differences. Furthermore, an effective question should efficiently distinguish the target from non-target samples—a critical aspect overlooked by prior works, resulting in suboptimal retrieval efficiency. To bridge this gap, we present A2R (Ask-to-Retrieve), a visually grounded framework designed to maximize information gain. Specifically, a Diversity Candidate Perception (DCP) module constructs a compact visual grid to capture diverse visual semantics. Subsequently, a Discriminative Question Generation (DQG) module observes this grid to propose discriminative questions. Finally, a Maximum Information Gain Decision (IGD) module evaluates these questions and selects the one maximizing entropy reduction. Experiments on VisDial, COCO, and Flickr30k demonstrate that our method achieves superior retrieval accuracy and efficiency compared to strong baselines.

Event forecasting requires modeling historical event data to predict future events, and achieving accurate predictions depends on effectively capturing the relevant historical information that aids forecasting.Most existing methods focus on entities and structural dependencies to capture historical clues but often overlook implicitly relevant information.This limitation arises from overlooking event semantics and deeper factual associations that are not explicitly connected in the graph structure but are nonetheless critical for accurate forecasting.To address this, we propose a dual-criteria constraint strategy that leverages event semantics for relevance modeling and incorporates a self-supervised semantic filter based on factual event associations to capture implicitly relevant historical information.Building on this strategy, our method, termed ITHI (Integrating Three types of Historical Information), combines sequential event information, periodically repeated event information, and relevant historical information to achieve context-aware event forecasting.We evaluated the proposed ITHI method on three public benchmark datasets, achieving state-of-the-art performance and significantly outperforming existing approaches.Additionally, we validated its effectiveness on two structured temporal knowledge graph forecasting dataset 1 .

Recently, multilingual Vision-Language Pre-training (mVLP) has shown remarkable progress in learning joint representations across different modalities and languages. However, most existing methods learn semantic alignment at a coarse-grained level and fail to capture fine-grained correlations between different languages and modalities. To address this, we propose a Multi-grained Multilingual Vision-Language Pre-training (M2-VLP) model, which aims to learn cross-lingual cross-modal alignment at different semantic granular levels. In cross-lingual interaction, the model learns the global alignment of parallel sentence pairs and the word-level correlations. In cross-modal interaction, the model aligns images with captions and image regions with corresponding words. To integrate the cross-lingual and cross-modal alignment above, we propose a unified multi-grained contrastive learning paradigm. Under zero-shot cross-lingual and fine-tuned multilingual settings, extensive experiments on vision-language downstream tasks across twenty languages demonstrate the effectiveness of M2-VLP over competitive contrastive models. Code and models are available at https://github.com/ahtamjan/M2-VLP.

Multilingual pre-trained language models (mPLMs) have achieved remarkable performance on zero-shot cross-lingual transfer learning. However, most mPLMs implicitly encourage cross-lingual alignment in pre-training stage, making it hard to capture accurate word alignment across languages. In this paper, we propose Word-align ADapters for Cross-lingual transfer (WAD-X) to explicitly align word representations of mPLMs via language-specific subspace. Taking a mPLM as the backbone model, WAD-X constructs subspace for each source-target language pair via adapters. The adapters use statistical alignment as the prior knowledge to guide word-level aligning in the corresponding bilingual semantic subspace. We evaluate our model across a set of target languages on three zero-shot cross-lingual transfer tasks: part-of-speech tagging (POS), dependency parsing (DP), and sentiment analysis (SA). Experimental results demonstrate that our proposed model improves zero-shot cross-lingual transfer on three benchmarks, with improvements of 2.19, 2.50, and 1.61 points in POS, DP, and SA tasks over strong baselines.