Multimodal Sarcasm Understanding (MSU) comprises multiple subtasks, demanding both incongruity perception and intent reasoning. However, this progress is impeded by two bottlenecks. First, the lack of a unified benchmark for holistic satirical cognition hinders comprehensive evaluation of MSU. Second, jointly modeling these heterogeneous subtasks often leads to feature entanglement. Specifically, while subtasks share a dependence on incongruity, they diverge in granular focus, causing specific execution patterns to erode the fundamental perception capability. To address these challenges, we make two contributions. First, we introduce DocMSU-PLUS, a comprehensive benchmark covering five cognitive dimensions of MSU. All tasks are reformulated into multiple-choice questions (MCQs), enabling a unified accuracy-based evaluation. Second, we propose the Dual Orthogonal Stream Experts (DOSE) framework. DOSE structurally decouples experts into orthogonal shared perception and private execution streams to physically block gradient interference between tasks. Experiments demonstrate that DOSE achieves superior performance on DocMSU-PLUS, effectively balancing general perception with task-specific adaptation.

Multimodal sarcasm detection (MSD) is essential for various downstream tasks. Existing MSD methods tend to rely on spurious correlations. These methods often mistakenly prioritize non-essential features yet still make correct predictions, demonstrating poor generalizability beyond training environments. Regarding this phenomenon, this paper undertakes several initiatives. Firstly, we identify two primary causes that lead to the reliance of spurious correlations. Secondly, we address these challenges by proposing a novel method that integrate Multimodal Incongruities via Contrastive Learning (MICL) for multimodal sarcasm detection. Specifically, we first leverage incongruity to drive multi-view learning from three views: token-patch, entity-object, and sentiment. Then, we introduce extensive data augmentation to mitigate the biased learning of the textual modality. Additionally, we construct a test set, SPMSD, which consists potential spurious correlations to evaluate the the model’s generalizability. Experimental results demonstrate the superiority of MICL on benchmark datasets, along with the analyses showcasing MICL’s advancement in mitigating the effect of spurious correlation.

Video Question Answering (VideoQA) aims to answer questions about the visual content of a video. Current methods mainly focus on improving joint representations of video and text. However, these methods pay little attention to the fine-grained semantic interaction between video and text. In this paper, we propose Mulan: a Multi-Level Alignment Model for Video Question Answering, which establishes alignment between visual and textual modalities at the object-level, frame-level, and video-level. Specifically, for object-level alignment, we propose a mask-guided visual feature encoding method and a visual-guided text description method to learn fine-grained spatial information. For frame-level alignment, we introduce the use of visual features from individual frames, combined with a caption generator, to learn overall spatial information within the scene. For video-level alignment, we propose an expandable ordinal prompt for textual descriptions, combined with visual features, to learn temporal information. Experimental results show that our method outperforms the state-of-the-art methods, even when utilizing the smallest amount of extra visual-language pre-training data and a reduced number of trainable parameters.