Mixture-of-Visual-Thoughts: Exploring Context-Adaptive Reasoning Mode Selection for General Visual Reasoning
This addresses the need for more general visual reasoning models, though it appears incremental as it builds on existing reasoning modes with adaptive selection.
The paper tackles the problem of limited general reasoning capabilities in visual reasoning by proposing Mixture-of-Visual-Thoughts (MoVT), a context-adaptive paradigm that unifies multiple reasoning modes and selects them based on context, achieving consistent improvements across various scenarios.
Current visual reasoning methods mainly focus on exploring specific reasoning modes. Although improvements can be achieved in particular domains, they struggle to develop general reasoning capabilities. Inspired by this, we propose a novel adaptive reasoning paradigm, Mixture-of-Visual-Thoughts (MoVT), which unifies different reasoning modes within a single model and guides it to select the appropriate mode based on context. To achieve this, we introduce AdaVaR, a two-stage Adaptive Visual Reasoning learning framework: different modes are unified and learned during the supervised cold-start stage, and the mode selection capability is induced via an RL process with a carefully designed AdaGRPO algorithm. Extensive experiments show that AdaVaR effectively guides the model to learn and differentiate multiple modes and perform context-adaptive mode selection, achieving consistent improvement across various scenarios, highlighting MoVT as an effective solution for building general visual reasoning models.