AI Model Modulation with Logits Redistribution

Files

hdl_148153.pdf (4.99 MB)
  (Published version)

Date

2025

Authors

Wang, Z.
Ma, Z.
Feng, X.
Mei, Z.
Ma, E.
Wang, D.
Xue, M.
Bai, G.

Editors

Advisors

Journal Title

Journal ISSN

Volume Title

Type:

Conference paper

Citation

Proceedings of the ACM Web Conference (WWW'25), 2025, pp.4699-4709

Statement of Responsibility

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

Conference Name

ACM Web Conference (WWW) (28 Apr 2025 - 2 May 2025 : Sydney, NSW, Australia)

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 varying utility levels, and the latter offers users precise control to shift model’s focused input features. Aim introduces a logits redistribution strategy that operates in a training data-agnostic and retraining-free manner. We establish a formal foundation to ensure Aim’s regulation capability, based on the statistical properties of logits ordering via joint probability distributions. Our evaluation confirms Aim’s practicality and versatility for AI model modulation, with tasks spanning image classification, semantic segmentation and text generation, and prevalent architectures including ResNet, SegFormer and Llama.

School/Discipline

Dissertation Note

Provenance

Description

Poster Session 9

Access Status

Rights

© 2025 Copyright held by the owner/author(s). This work is licensed under a Creative Commons Attribution 4.0 International License.

License

Call number

Persistent link to this record