Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Yihua, Jia, Qi, Xu, Cong, Chen, Feiyu, Liu, Yuhan, Zhang, Haotian, Jin, Liang, Liu, Lu, Wang, Zhichun
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Multi-View Incongruity Learning for Multimodal Sarcasm Detection
by: Guo, Diandian, et al.
Published: (2024)

Multimodal Conditional Information Bottleneck for Generalizable AI-Generated Image Detection
by: Qin, Haotian, et al.
Published: (2025)

URMF: Uncertainty-aware Robust Multimodal Fusion for Multimodal Sarcasm Detection
by: Wang, Zhenyu, et al.
Published: (2026)

Do LLMs Overcome Shortcut Learning? An Evaluation of Shortcut Challenges in Large Language Models
by: Yuan, Yu, et al.
Published: (2024)

RCLMuFN: Relational Context Learning and Multiplex Fusion Network for Multimodal Sarcasm Detection
by: Wang, Tongguan, et al.
Published: (2024)

EvoCoT: Overcoming the Exploration Bottleneck in Reinforcement Learning
by: Liu, Huanyu, et al.
Published: (2025)

Commander-GPT: Dividing and Routing for Multimodal Sarcasm Detection
by: Zhang, Yazhou, et al.
Published: (2025)

A Survey of Multimodal Sarcasm Detection
by: Farabi, Shafkat, et al.
Published: (2024)

Sparse Shortcuts: Facilitating Efficient Fusion in Multimodal Large Language Models
by: Zhang, Jingrui, et al.
Published: (2026)

Understand the Effectiveness of Shortcuts through the Lens of DCA
by: Sun, Youran, et al.
Published: (2024)

CORE: Data Augmentation for Link Prediction via Information Bottleneck
by: Dong, Kaiwen, et al.
Published: (2024)

Seeing Sarcasm Through Different Eyes: Analyzing Multimodal Sarcasm Perception in Large Vision-Language Models
by: Chen, Junjie, et al.
Published: (2025)

GDCNet: Generative Discrepancy Comparison Network for Multimodal Sarcasm Detection
by: Zhang, Shuguang, et al.
Published: (2026)

Target-Augmented Shared Fusion-based Multimodal Sarcasm Explanation Generation
by: Goel, Palaash, et al.
Published: (2025)

Was that Sarcasm?: A Literature Survey on Sarcasm Detection
by: Bagga, Harleen Kaur, et al.
Published: (2024)

Fusion Meets Diverse Conditions: A High-diversity Benchmark and Baseline for UAV-based Multimodal Object Detection with Condition Cues
by: Chen, Chen, et al.
Published: (2025)

Learning Optimal Multimodal Information Bottleneck Representations
by: Wu, Qilong, et al.
Published: (2025)

MMSD3.0: A Multi-Image Benchmark for Real-World Multimodal Sarcasm Detection
by: Zhao, Haochen, et al.
Published: (2025)

RAM-SD: Retrieval-Augmented Multi-agent framework for Sarcasm Detection
by: Zhou, Ziyang, et al.
Published: (2026)

Teaching Sarcasm: Few-Shot Multimodal Sarcasm Detection via Distillation to a Parameter-Efficient Student
by: Jana, Soumyadeep, et al.
Published: (2025)

Refining the Information Bottleneck via Adversarial Information Separation
by: Ning, Shuai, et al.
Published: (2026)

Multimodal Information Bottleneck for Deep Reinforcement Learning with Multiple Sensors
by: You, Bang, et al.
Published: (2024)

Enhancing Multimodal Entity and Relation Extraction with Variational Information Bottleneck
by: Cui, Shiyao, et al.
Published: (2023)

SemIRNet: A Semantic Irony Recognition Network for Multimodal Sarcasm Detection
by: Zhou, Jingxuan, et al.
Published: (2025)

MuVaC: A Variational Causal Framework for Multimodal Sarcasm Understanding in Dialogues
by: Guo, Diandian, et al.
Published: (2026)

Spoken in Jest, Detected in Earnest: A Systematic Review of Sarcasm Recognition -- Multimodal Fusion, Challenges, and Future Prospects
by: Gao, Xiyuan, et al.
Published: (2025)

MiMu: Mitigating Multiple Shortcut Learning Behavior of Transformers
by: Zhao, Lili, et al.
Published: (2025)

Towards an Incremental Unified Multimodal Anomaly Detection: Augmenting Multimodal Denoising From an Information Bottleneck Perspective
by: Long, Kaifang, et al.
Published: (2026)

SCALE: Selective Resource Allocation for Overcoming Performance Bottlenecks in Mathematical Test-time Scaling
by: Xiao, Yang, et al.
Published: (2025)

Lower or higher 25‐hydroxyvitamin D levels associated with adverse pregnancy outcomes: comment on the article by Madanchi et al
by: Gang Wang, et al.
Published: (2025)

Lower environmental temperature and higher relative humidity had significant associations with worsened Raynaud phenomenon in systemic sclerosis: comment on the article by Taylor et al
by: Gang Wang, et al.
Published: (2025)

Associations of fire smoke and other pollutants with incident rheumatoid arthritis and rheumatoid arthritis–associated interstitial lung disease: comment on the article by Kronzer et al
by: Gang Wang, et al.
Published: (2025)

Febuxostat use is associated with a significantly greater risk of mild to moderate perturbation of liver function compared to benzbromarone in patients with gout: comment on the article by Sun et al
by: Gang Wang, et al.
Published: (2025)

Learning with Logical Constraints but without Shortcut Satisfaction
by: Li, Zenan, et al.
Published: (2024)

Skill-CMIB: Multimodal Agent Skill for Consistent Action via Conditional Multimodal Information Bottleneck
by: Huang, Zihan, et al.
Published: (2026)

Can Large Vision-Language Models Understand Multimodal Sarcasm?
by: Wang, Xinyu, et al.
Published: (2025)

Learning to Think in Physics: Breaking Shortcut Learning in Scientific Diffusion via Representation Alignment
by: Jia, Haozhe, et al.
Published: (2026)

Fusion of the Power from Citations: Enhance your Influence by Integrating Information from References
by: Qi, Cong, et al.
Published: (2023)

Protecting Your LLMs with Information Bottleneck
by: Liu, Zichuan, et al.
Published: (2024)

Adapter-state Sharing CLIP for Parameter-efficient Multimodal Sarcasm Detection
by: Jana, Soumyadeep, et al.
Published: (2025)