MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal Understanding

Understand

Vision-language alignment in multi-modal large language models (MLLMs) relies on supervised fine-tuning (SFT) or reinforcement learning (RL).

• To align multi-modal large language models (MLLMs) in the post-training stage, supervised fine-tuning (SFT) is a stable choice but requires human annotations and lacks task generalizations, while Reinforcement Learning (RL) searches for better answers from reward signals but suffers from computational overhead and instability.
• To achieve balance among scalability, efficiency, and alignment generalizations, we propose MergeMix, a unified paradigm that bridges SFT and RL with an efficient Token Merge based Mixup augmentation.
• As for the Mixup policy, we generate contextual aligned mixed images with the corresponding labels according to the merged attention maps with cluster regions.