paper-with-me

홈 › Papers

AI Wizards at EXIST 2026: Hierarchical Soft-Label Learning for Multimodal Sexism Identification in Memes

2026-07-05 · Matteo Fasulo, Antonio Gravina, Luca Tedeschini, Luca Babboni hf

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

📄 PDF Abstract BibTeX arXiv:2607.04410

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Applying the Wizard-of-Oz Technique to Multimodal Human-Robot Dialogue

2017-03-10 · Matthew Marge, Claire Bonial, Brendan Byrne, Taylor Cassidy 외

Our overall program objective is to provide more natural ways for soldiers to interact and communicate with robots, much like how soldiers communicate with other soldiers today. We describe how the Wizard-of-Oz (WOz) met…

Dialogue ManagementManagementRobot Navigation

The acquisition and dialog act labeling of the EDECAN-SPORTS corpus

2012-05-01 · LREC 2012 5 · Llu{\'\i}s-F. Hurtado, Fern Garc{\'\i}a, o, Emilio Sanchis 외

In this paper, we present the acquisition and labeling processes of the EDECAN-SPORTS corpus, which is a corpus that is oriented to the development of multimodal dialog systems acquired in Spanish and Catalan. Two Wizard…

Speech Recognition

AIWizards at MULTIPRIDE: A Hierarchical Approach to Slur Reclamation Detection

2026-02-13 · Luca Tedeschini, Matteo Fasulo arxiv

Detecting reclaimed slurs represents a fundamental challenge for hate speech detection systems, as the same lexcal items can function either as abusive expressions or as in-group affirmations depending on social identity…

Hate Speech Detection

On LLM Wizards: Identifying Large Language Models' Behaviors for Wizard of Oz Experiments

2024-07-10 · Jingchao Fang, Nikos Arechiga, Keiichi Namaoshi, Nayeli Bravo 외

The Wizard of Oz (WoZ) method is a widely adopted research approach where a human Wizard ``role-plays'' a not readily available technology and interacts with participants to elicit user behaviors and probe the design spa…

A Transformer-Based Model With Self-Distillation for Multimodal Emotion Recognition in Conversations

2023-10-31 · Hui Ma, Jian Wang, Hongfei Lin, Bo Zhang 외

Emotion recognition in conversations (ERC), the task of recognizing the emotion of each utterance in a conversation, is crucial for building empathetic machines. Existing studies focus mainly on capturing context- and sp…

Emotion RecognitionEmotion Recognition in ConversationMultimodal Emotion Recognition