paper-with-me

홈 › Papers

5% > 100%: Flatness Preference is All You Need for Multimodal Parameter-Efficient Fine-Tuning

2026-06-09 · Yifan Zhu, Can Lin, Hangjie Yuan, Zixiang Zhao, Pengfei Zhang, Tao Feng, Zhonghong Ou arxiv

Parameter-Efficient Fine-Tuning (PEFT) methods provide a streamlined and efficient tool for adapting large models to domain-specific multimodal downstream tasks. Although these methods proved their tangible effects in practice, their principal aspects remain under-explored. Therefore we remain curious about the underlying generalization mechanisms in various PEFT methods and how they can be further enhanced. In this paper, we reveal the flatness preference widely present in various PEFTs, where a small fraction of sharp dimensions dominates the generalization of PEFT. This finding suggests an appealing possibility: we may be satisfied with a better generalization by merely attending to this small fraction of sharp dimensions instead of all of them. Furthermore, we propose Flatness Preference Optimization (FlatPO) to flatten these key sharpness dimensions, leading various PEFTs toward better generalization. Extensive experiments demonstrate the effectiveness of our findings and the proposed method. Code is available at https://github.com/Can-Lin/FlatPO.

📄 PDF Abstract BibTeX arXiv:2606.10488

Code (0)

등록된 구현이 없습니다.

Tasks

parameter-efficient fine-tuning

Similar Papers 제목 키워드 기반

FAM: Relative Flatness Aware Minimization

2023-07-05 · Linara Adilova, Amr Abourayya, Jianning Li, Amin Dada 외

Flatness of the loss curve around a model at hand has been shown to empirically correlate with its generalization ability. Optimizing for flatness has been proposed as early as 1994 by Hochreiter and Schmidthuber, and wa…

Does SGD Seek Flatness or Sharpness? An Exactly Solvable Model

2026-02-04 · Yizhou Xu, Pierfrancesco Beneventano, Isaac Chuang, Liu Ziyin arxiv

A large body of theory and empirical work hypothesizes a connection between the flatness of a neural network's loss landscape during training and its performance. However, there have been conceptually opposite pieces of …

The Uncanny Valley: Exploring Adversarial Robustness from a Flatness Perspective

2024-05-27 · Nils Philipp Walter, Linara Adilova, Jilles Vreeken, Michael Kamp

Flatness of the loss surface not only correlates positively with generalization but is also related to adversarial robustness, since perturbations of inputs relate non-linearly to perturbations of weights. In this paper,…

Adversarial Robustness

Relative Flatness and Generalization

2020-01-03 · NeurIPS 2021 12 · Henning Petzka, Michael Kamp, Linara Adilova, Cristian Sminchisescu 외

Flatness of the loss curve is conjectured to be connected to the generalization ability of machine learning models, in particular neural networks. While it has been empirically observed that flatness measures consistentl…

Generalization Bounds

A Reparameterization-Invariant Flatness Measure for Deep Neural Networks

2019-11-29 · Henning Petzka, Linara Adilova, Michael Kamp, Cristian Sminchisescu

The performance of deep neural networks is often attributed to their automated, task-related feature construction. It remains an open question, though, why this leads to solutions with good generalization, even in cases …

Open-Ended Question Answering