MER-R1: Multimodal Emotion Reasoning via Slow-Fast Thinking Synergy
Explicit reasoning does not necessarily improve multimodal emotion recognition accuracy but makes predictions more interpretable. Fast thinking (direct answers) improves recall, while slow thinking (deliberative reasoning) favors precision. MER-R1 is a reinforcement learning framework that jointly optimizes both through dual-objective disentanglement and confidence calibration, achieving state-of-the-art performance.
[2606.27652] MER-R1: Multimodal Emotion Reasoning via Slow-Fast Thinking Synergy
[Submitted on 26 Jun 2026]
Title:MER-R1: Multimodal Emotion Reasoning via Slow-Fast Thinking Synergy
View a PDF of the paper titled MER-R1: Multimodal Emotion Reasoning via Slow-Fast Thinking Synergy, by Zhiyuan Han and 10 other authors
View PDF HTML (experimental)
Abstract:We find that explicit reasoning does not necessarily translate into better multimodal emotion recognition (MER) accuracy, even though it makes predictions more interpretable. Specifically, for reasoning-based MLLMs, fast thinking by triggering direct answers often outperforms slow thinking after deliberative reasoning. Our empirical analyses show that fast thinking improves recall with broader and more confident predictions, whereas slow thinking favors precision through conservative filtering of incorrect categories. Building on these insights, we propose MER-R1, a reinforcement learning framework that turns slow-fast complementarity into explicit optimization. Dual-objective disentanglement separates recall and precision into two optimization signals, allowing them to be jointly optimized rather than traded off against each other. Slow-fast confidence calibration further aligns the final slow-thinking answer with fast-thinking intuition, strengthening correct emotions while suppressing incorrect ones. In this way, MER-R1 unifies the recall-oriented intuition of fast thinking with the precision-oriented selectivity of slow thinking. We further provide theoretical justification for this synergy, showing that it mitigates variance-induced interference during optimization. Extensive experiments on MER-UniBench and MME-Emotion show that MER-R1 achieves state-of-the-art performance and makes reasoning genuinely benefit emotion recognition.
Comments: Under review
Subjects:
Artificial Intelligence (cs.AI)
Cite as: arXiv:2606.27652 [cs.AI]
(or arXiv:2606.27652v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2606.27652
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Zhiyuan Han [view email] [v1] Fri, 26 Jun 2026 02:07:53 UTC (6,953 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled MER-R1: Multimodal Emotion Reasoning via Slow-Fast Thinking Synergy, by Zhiyuan Han and 10 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.AI
new | recent | 2026-06
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)