Models model transformer benchmark announce feature reasoning

SURE: Synergistic Uncertainty-aware Reasoning for Multimodal Emotion Recognition in Conversations

arXiv cs.CLby Yiqiang Cai, Chengyan Wu, Bolei Ma, Bo Chen, Yun Xue, Julia Hirschberg, Ziwei GongApril 4, 20261 min read0 views

Source Quiz

arXiv:2604.01916v1 Announce Type: new Abstract: Multimodal emotion recognition in conversations (MERC) requires integrating multimodal signals while being robust to noise and modeling contextual reasoning. Existing approaches often emphasize fusion but overlook uncertainty in noisy features and fine-grained reasoning. We propose SURE (Synergistic Uncertainty-aware REasoning) for MERC, a framework that improves robustness and contextual modeling. SURE consists of three components: an Uncertainty-Aware Mixture-of-Experts module to handle modality-specific noise, an Iterative Reasoning module for multi-turn reasoning over context, and a Transformer Gate module to capture intra- and inter-modal interactions. Experiments on benchmark MERC datasets show that SURE consistently outperforms state-o

View PDF HTML (experimental)

Abstract:Multimodal emotion recognition in conversations (MERC) requires integrating multimodal signals while being robust to noise and modeling contextual reasoning. Existing approaches often emphasize fusion but overlook uncertainty in noisy features and fine-grained reasoning. We propose SURE (Synergistic Uncertainty-aware REasoning) for MERC, a framework that improves robustness and contextual modeling. SURE consists of three components: an Uncertainty-Aware Mixture-of-Experts module to handle modality-specific noise, an Iterative Reasoning module for multi-turn reasoning over context, and a Transformer Gate module to capture intra- and inter-modal interactions. Experiments on benchmark MERC datasets show that SURE consistently outperforms state-of-the-art methods, demonstrating its effectiveness in robust multimodal reasoning. These results highlight the importance of uncertainty modeling and iterative reasoning in advancing emotion recognition in conversational settings.

Comments: ICASSP 2026

Subjects:

Computation and Language (cs.CL)

Cite as: arXiv:2604.01916 [cs.CL]

(or arXiv:2604.01916v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2604.01916

arXiv-issued DOI via DataCite (pending registration)