Call for Papers: Special Issue on When Affective Computing Meets Multimodal Large And Reasoning Language Models

DEADLINES:

Open for Submissions: 1 May 2026

Submissions due: 30 December 2026

Final Decision Notification: 1 May 2027

Affective computing plays an important role in our daily conversations and helps people convey their underlying intentions. With the rapid advancement of embodied artificial intelligence (AI), affective computing has attracted growing interest from academia and industry, as it contributes significantly to enhancing the emotional intelligence of robots and enabling them to better understand human instructions.

Affective computing has been developed and studied for a long time, and previous work in this field has mainly focused on a fixed emotion space, such as basic emotions or dimensional emotions. Recently, multimodal large language models (MLLMs) have provided new opportunities for affective computing. Specifically, MLLMs possess a rich vocabulary, thereby enabling recognition beyond basic emotion categories. At the same time, they can help interpret multimodal cues (e.g., gestures, facial expressions, and vocal tones), allowing a shift from simple emotional word recognition to evidence-based emotion understanding, which enhances the interpretability and reliability of prediction results. This shift in research trends also opens up new research directions and topics, such as generative emotions (e.g. open-vocabulary emotions and descriptive emotions), emotion hallucinations and conflicts in MLLMs, and effective approaches to constructing emotion foundation models.

This special issue seeks to align with the current research trend of MLLM-driven affective computing and to explore both the opportunities and challenges in this field. In particular, we emphasize advances in emotion theory, dataset construction, training strategies, model architectures, and evaluation benchmarks. We also welcome contributions focusing on downstream applications in embodied AI and emotional support. Our goal is to bring together researchers from the community to discuss the opportunities and challenges of this emerging research direction, and to drive affective computing into its next stage of development.

In this special issue, we welcome submissions on topics including, but not limited to:

• Emotion recognition and reasoning in the era of multimodal large language model
•  Generative emotion understanding based on MLLM-driven approaches
• Open-vocabulary or descriptive emotion recognition based on MLLMs
• Zero-shot, few-shot, and chain-of-thought prompting techniques for affective computing 1
• Emotion foundation models and exploration of their scaling laws
• Instruction datasets, model framework, and supervised fine-tuning strategies for multi modal emotion recognition
• Reinforcement learning and reward design for understanding human emotions
• Datasets and benchmarks for evaluating LLMs’ emotion recognition performance
• Interpretability of deep learning methods in affective computing
• Multi-agent frameworks and their applications in emotion recognition and emotional support
• LLM-driven affective computing in embodied AI
• Emotion hallucinations and conflicts in large language models
• Theory of mind and its applications in affective computing
• Fairness and bias mitigation in AI for affective computing
• Responsive and trustworthy AI in affective computing
• Multimodal and conversational emotion recognition

For author information and guidelines on submission criteria, visit the TAC Author Information page. When submitting your paper, please be sure to select the special issue or special section name. Manuscripts should not be published or currently submitted for publication elsewhere. Please submit only full papers intended for review, not abstracts, to the IEEE Author Portal submission system and select the article type: “Affective Computing Meets Multimodal Large and Reasoning Language Models”

In addition to submitting your paper to TAFFC, you are also encouraged to upload the data related to your paper to IEEE DataPort. IEEE DataPort is IEEE’s data platform that supports the storage and publishing of datasets while also providing access to thousands of research datasets. Uploading your dataset to IEEE DataPort will strengthen your paper and support research reproducibility. Your paper and the dataset can be linked, providing a good opportunity for you to increase the number of citations you receive. Data can be uploaded to IEEE DataPort prior to submitting your paper or concurrent with the paper submission. Thank you!

All submissions will undergo rigorous peer review in accordance with IEEE TAFFC standards.

• Zheng Lian, Tongji University (Lead Guest Editor)
• Rui Liu, Inner Mongolia University (Guest Editor)
• Xiaojiang Peng, Shenzhen Technology University (Guest Editor)
• Jufeng Yang, Nankai University (Guest Editor)
• Guoying Zhao, University of Oulu (Commissioning Guest Editor)
• Bjorn Schuller, Technische University at Munchen (Commissioning Guest Editor)
• Carlos Busso, Carnegie Mellon University (Commissioning Guest Editor)
• Jianhua Tao, Tsinghua University (Commissioning Guest Editor)