AI & ML New Capability

AIM enables post-training modulation of large models to change utility levels or focus features without any retraining or additional data.

arXiv · March 16, 2026 · 2603.12755

Zihan Wang, Zhongkui Ma, Xinguo Feng, Zhiyang Mei, Ethan Ma, Derui Wang, Minhui Xue, Guangdong Bai

Why it matters

By redistributing logits based on statistical properties, owners can dynamically control model output quality or feature attention for different users/tiers. This provides a lightweight alternative to maintaining multiple fine-tuned versions of the same backbone model.

From the abstract

Large-scale models are typically adapted to meet the diverse requirements of model owners and users. However, maintaining multiple specialized versions of the model is inefficient. In response, we propose AIM, a novel model modulation paradigm that enables a single model to exhibit diverse behaviors to meet the specific end requirements. AIM enables two key modulation modes: utility and focus modulations. The former provides model owners with dynamic control over output quality to deliver varyin