MER 2026: From Discriminative Emotion Recognition to Generative Emotion Understanding

2026-04-21

AI Summary

Traditional emotion recognition approaches are often confined to discrete categorical labels, limiting their capacity to capture the nuanced affective states inherent in human interactions. This work proposes a generative emotion understanding framework that systematically integrates dyadic interaction modeling, fine-grained semantic descriptions, human preference learning, and physiological signals. Built upon multimodal large language models (MLLMs), the framework synergistically combines multimodal data fusion, natural language generation, and preference-aware learning. The study establishes four challenge tracks and introduces a large-scale benchmark platform and dataset, thereby advancing affective computing toward a new paradigm characterized by generative capabilities, multimodal integration, interpretability, and human-centered evaluation.

Technology Category

• Cognitive Modeling & Cognitive Systems: Affective Computing
• Machine Learning: Large Multimodal Models (LMMs)
• Humans and AI: Emotional Intelligence

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

MER2026 marks the fourth edition of the MER series of challenges. The MER series provides valuable data resources to the research community and offers tasks centered on recent research trends, establishing itself as one of the largest challenges in the field. Throughout its history, the focus of MER has shifted from discriminative emotion recognition to generative emotion understanding. Specifically, MER2023 concentrated on discriminative emotion recognition, restricting the emotion recognition scope to fixed basic labels. In MER2024 and MER2025, we transitioned to generative emotion understanding and introduced two new tasks: fine-grained emotion recognition and descriptive emotion analysis, aiming to leverage the extensive vocabulary and multimodal understanding capabilities of Multimodal Large Language Models (MLLMs) to facilitate fine-grained and explainable emotion recognition. Building on this trajectory, MER2026 continues to follow these research trends and contains four tracks: MER-Cross shifts the focus from individual to dyadic interaction scenarios; MER-FG centers on fine-grained emotion recognition; MER-Prefer aims to predict human preferences regarding different emotion descriptions; MER-PS focuses on emotion recognition based on physiological signals. More details regarding the dataset and baselines are available at https://zeroqiaoba.github.io/MER-Challenge.

Problem

• emotion recognition
• generative emotion understanding
• fine-grained emotion
• multimodal learning
• human preference

Innovation

• generative emotion understanding
• multimodal large language models
• fine-grained emotion recognition
• dyadic interaction
• physiological signals