AI Wizards at EXIST 2026: Hierarchical Soft-Label Learning for Multimodal Sexism Identification in Memes
Not on the map. Why?
Abstract (arXiv)
We present the AI Wizards submission to EXIST 2026 for multimodal sexism identification in memes. The task is composed of three, increasingly harder subtasks. We model them hierarchically as conditional soft-label prediction over empirical annotator distributions. Our system maps fixed Gemini Embedding 2 vision-language representations through a lightweight Gated MLP trained with KL divergence and homoscedastic uncertainty weighting. Our submissions ranked first on Task 2.3 and fourth on Tasks 2.1 and 2.2 on the official Soft-Soft leaderboards. The code is available at https://github.com/NLP-AI-Wizards/EXIST-2026
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 11 of its 24 references that are in the map. First posted on arXiv 5 Jul 2026.
Builds on
11 of 24 references.
References · 11
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,048
- 2020GLU Variants Improve Transformercited by 1,724
- 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,345
- 2020The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memescited by 485
- 2022Hate-CLIPper: Multimodal Hateful Meme Classification based on Cross-modal Interaction of CLIP Featurescited by 55
- 2023SemEval-2023 Task 10: Explainable Detection of Online Sexismcited by 48
- 2023Pro-Cap: Leveraging a Frozen Vision-Language Model for Hateful Meme Detectioncited by 45
- 2025Mario at EXIST 2025: A Simple Gateway to Effective Multilingual Sexism Detectioncited by 4
- 2023Women's Perspectives on Harm and Justice after Online Harassmentcited by 2
- 2026Human-Centered Multimodal Fusion for Sexism Detection in Memes with Eye-Tracking, Heart Rate, and EEG Signalscited by 2
Built on by
Not cited yet.