REACT 2026: The Fourth Multiple Appropriate Facial Reaction Generation Challenge: Personalised MAFRG and Appropriate EEG Reaction Prediction

2026-06-05

AI Summary

This work addresses the challenge of generating personalized, diverse, and speaker-synchronized realistic facial responses tailored to specific listeners by introducing a novel approach that integrates Big Five personality traits with electroencephalography (EEG) signals for the first time. Leveraging generative deep learning models and the MARS multimodal dataset, the study establishes a new paradigm for mapping a single input to multiple personalized outputs by jointly modeling facial behavior, personality characteristics, and neurophysiological signals. The project defines four subtasks—offline/online and generic/personalized—and introduces the REACT 2026 Challenge, providing benchmark protocols and baseline models. This framework delivers a reproducible evaluation platform for multimodal response generation in dyadic interactions, substantially advancing the research frontier in this domain.

Abstract

In dyadic interactions, various human facial reactions could be appropriate for responding to each human speaker behaviour. Following the successful organisation of the REACT 2023, 2024 and 2025 challenge series, a body of generative deep learning (DL) models have been developed for the problem of multiple appropriate facial reaction generation (MAFRG). This year, we propose the REACT 2026 challenge encouraging the development and benchmarking of Machine Learning (ML) models that can generate multiple personalised, appropriate, diverse, realistic and synchronised human-style facial reactions expressed by a specific human listener for responding to each given speaker behaviour. As a key of the challenge, we continuously provide challenge participants with MARS dataset introduced by REACT 2025 but additionally provide individual-level Big-Five personality labels and EEG recordings. This introduces a new one-to-many personalised facial reaction generation setting combining human expressive behavioural, affective and neurophysiological signals, which remains largely unexplored in current dyadic interaction modelling. This paper also presents the challenge guidelines and new baselines on the four proposed sub-challenges: Offline generic and personalised MAFRG as well as Online generic and personalised MAFRG, respectively, which are publicly available at https://github.com/reactmultimodalchallenge/baseline_react2026.

Problem

• personalised facial reaction
• multiple appropriate facial reaction generation
• dyadic interaction
• EEG reaction prediction
• personality-aware generation

Innovation

• personalised MAFRG
• EEG reaction prediction
• multimodal dyadic interaction
• generative deep learning
• Big-Five personality