<ul data-eligibleForWebStory="false"><li>A new study introduces Dualformer, a Transformer model that can operate in two reasoning modes, fast and slow, by training on randomized reasoning traces.</li><li>Dualformer outperforms baselines in terms of performance and computational efficiency across all modes, achieving a high optimal rate on maze tasks and producing more diverse reasoning traces.</li><li>The model can be configured to execute in either fast or slow mode, or automatically decide which mode to engage at inference time.</li><li>Dualformer's capabilities extend beyond task-specific models, showing improved performance in math reasoning problems through Large Language Models fine-tuning.</li></ul>

Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces

Discover more