MER-R1: Multimodal Emotion Reasoning via Slow-Fast Thinking Synergy
For researchers in multimodal emotion recognition, this work provides a method to make reasoning beneficial for accuracy, addressing a key bottleneck where reasoning previously hurt performance.
The paper identifies that explicit reasoning does not always improve multimodal emotion recognition accuracy, with fast thinking outperforming slow thinking. They propose MER-R1, a reinforcement learning framework that synergizes fast and slow thinking via dual-objective disentanglement and confidence calibration, achieving state-of-the-art performance on MER-UniBench and MME-Emotion.
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.