Author name cluster

Zhichun Wang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

1 author row

AAAI Conference 2026 Conference Paper

Conditional Information Bottleneck for Multimodal Fusion: Overcoming Shortcut Learning in Sarcasm Detection

Yihua Wang
Qi Jia
Cong Xu
Feiyu Chen
Yuhan Liu
Haotian Zhang
Liang Jin
Lu Liu

Multimodal sarcasm detection is a complex task that requires distinguishing subtle complementary signals across modalities while filtering out irrelevant information. Many advanced methods rely on learning shortcuts from datasets rather than extracting intended sarcasm-related features. However, our experiments show that shortcut learning impairs the model's generalization in real-world scenarios. Furthermore, we reveal the weaknesses of current modality fusion strategies for multimodal sarcasm detection through systematic experiments, highlighting the necessity of focusing on effective modality fusion for complex emotion recognition. To address these challenges, we construct MUStARD++R by removing shortcut signals from MUStARD++. Then, a Multimodal Conditional Information Bottleneck (MCIB) model is introduced to enable efficient multimodal fusion for sarcasm detection. Experimental results show that the MCIB achieves the best performance without relying on shortcut learning.

PDF Details DOI

AAAI Conference 2026 Conference Paper

SciMKG: A Multimodal Knowledge Graph for Science Education with Text, Image, Video and Audio

Tong Lu
Zhichun Wang
Yaoyu Zhou
Yiming Guan
Zhiyong Bai
Junsheng Du

Knowledge graphs (KGs) play a vital role in intelligent education by offering structured representations of educational content. However, constructing multimodal educational knowledge graphs (EKGs) from diverse open educational resources remains a challenge due to the reliance on costly manual annotations and the lack of multimodal integration. In this work, we propose an automated framework that harnesses the reasoning capabilities of large language models (LLMs) to construct multimodal EKGs from open courses efficiently. In our framework, an Extraction-Verification-Integration-Augmentation pipeline is designed to incrementally extract and refine disciplinary concepts from learning resources. Texts, images, videos and audios are aligned with their corresponding concepts. To ensure semantic consistency across modalities, we propose a cross-modal alignment method based on shared structural and semantic features. Using our framework, we build SciMKG, a large-scale multimodal EKG for Chinese K12 education in sciences (biology, physics, and chemistry), encompassing 1,356 knowledge points, 34,630 multimodal concepts, and 403,400 relational triples. Experimental results show that our method improves concept extraction F1 score by 9 % over state-of-the-art baselines; both automatic and human evaluations confirm the robustness of our multimodal alignment method. SciMKG and our construction toolkit will be publicly released to support further research and applications in AI-driven education.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Task-Aware Meta-Learning on Heterogeneous Knowledge Graph for POI Recommendation

Jingyuan Wang
Zhichun Wang
Tong Lu
Yiming Guan

Point-of-Interest (POI) recommendation plays a pivotal role in location-based services by guiding users to discover new and relevant places. While graph-based methods have shown promising results, effectively modeling the diversity and dynamics of user preferences remains a key challenge. Addressing this requires richer representations of both POIs and user interests, as well as more adaptive learning strategies. In this work, we propose TMHKG, a Task-aware Meta-learning framework with a Heterogeneous Knowledge Graph for POI recommendation. To enhance representation learning, TMHKG constructs a dual-view POI knowledge graph that integrates geographical proximity and user-aware category transitions, and models users' evolving interests from sequential visit histories. On top of enriched features, TMHKG adopts a task-aware meta-learning paradigm, treating each user's recommendation task as a separate meta-task. A generalizable recommendation policy is first learned from diverse training tasks and then quickly adapted to each user's unique behavior, enabling highly personalized predictions. Extensive experiments on two real-world datasets demonstrate that TMHKG consistently outperforms state-of-the-art baselines, highlighting its effectiveness in capturing complex user-POI interactions.

PDF Details DOI

AAAI Conference 2020 Short Paper

Rception: Wide and Deep Interaction Networks for Machine Reading Comprehension (Student Abstract)

Xuanyu Zhang
Zhichun Wang

Most of models for machine reading comprehension (MRC) usually focus on recurrent neural networks (RNNs) and attention mechanism, though convolutional neural networks (CNNs) are also involved for time efﬁciency. However, little attention has been paid to leverage CNNs and RNNs in MRC. For a deeper understanding, humans sometimes need local information for short phrases, sometimes need global context for long passages. In this paper, we propose a novel architecture, i. e. , Rception, to capture and leverage both local deep information and global wide context. It fuses different kinds of networks and hyper-parameters horizontally rather than simply stacking them layer by layer vertically. Experiments on the Stanford Question Answering Dataset (SQuAD) show that our proposed architecture achieves good performance.

PDF Details

IJCAI Conference 2013 Conference Paper

Boosting Cross-Lingual Knowledge Linking via Concept Annotation

Zhichun Wang
Juanzi Li
Jie Tang

Automatically discovering cross-lingual links (CLs) between wikis can largely enrich the cross-lingual knowledge and facilitate knowledge sharing across different languages. In most existing approaches for cross-lingual knowledge linking, the seed CLs and the inner link structures are two important factors for finding new CLs. When there are insufficient seed CLs and inner links, discovering new CLs becomes a challenging problem. In this paper, we propose an approach that boosts cross-lingual knowledge linking by concept annotation. Given a small number of seed CLs and inner links, our approach first enriches the inner links in wikis by using concept annotation method, and then predicts new CLs with a regression-based learning model. These two steps mutually reinforce each other, and are executed iteratively to find as many CLs as possible. Experimental results on the English and Chinese Wikipedia data show that the concept annotation can effectively improve the quantity and quality of predicted CLs. With 50, 000 seed CLs and 30% of the original inner links in Wikipedia, our approach discovered 171, 393 more CLs in four runs when using concept annotation.

PDF Details DOI