# Efficient Visual Appearance Optimization by Learning from Prior Preferences

arXiv: https://arxiv.org/abs/2507.15355 · HTML: https://mlsanity.com/paper/2507.15355/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 76 references that are in the map.
- First posted on arXiv 21 Jul 2025.

## Builds on (most cited first, 23 of 23)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [A Tutorial on Bayesian Optimization](https://mlsanity.com/paper/1807.02811/) (2018)
- [RL2: Fast Reinforcement Learning via Slow Reinforcement Learning](https://mlsanity.com/paper/1611.02779/) (2016)
- [Recent Advances in Bayesian Optimization](https://mlsanity.com/paper/2206.03301/) (2022)
- [Preferential Bayesian Optimization](https://mlsanity.com/paper/1704.03651/) (2017)
- [Few-Shot Bayesian Optimization with Deep Kernel Surrogates](https://mlsanity.com/paper/2101.07667/) (2021)
- [Meta-Learning Acquisition Functions for Transfer Learning in Bayesian Optimization](https://mlsanity.com/paper/1904.02642/) (2019)
- [Image Aesthetic Assessment: An Experimental Survey](https://mlsanity.com/paper/1610.00838/) (2016)
- [Meta-learning in natural and artificial intelligence](https://mlsanity.com/paper/2011.13464/) (2020)
- [Compress, Then Prompt: Improving Accuracy-Efficiency Trade-off of LLM Inference with Transferable Prompt](https://mlsanity.com/paper/2305.11186/) (2023)
- [Transfer Learning for Bayesian Optimization: A Survey](https://mlsanity.com/paper/2302.05927/) (2023)
- [Sequential Gallery for Interactive Visual Design Optimization](https://mlsanity.com/paper/2005.04107/) (2020)
- [Reinforced Few-Shot Acquisition Function Learning for Bayesian Optimization](https://mlsanity.com/paper/2106.04335/) (2021)
- [SituationAdapt: Contextual UI Optimization in Mixed Reality with Situation Awareness via LLM Reasoning](https://mlsanity.com/paper/2409.12836/) (2024)
- [TransBO: Hyperparameter Optimization via Two-Phase Transfer Learning](https://mlsanity.com/paper/2206.02663/) (2022)
- [FontCraft: Multimodal Font Design Using Interactive Bayesian Optimization](https://mlsanity.com/paper/2502.11399/) (2025)
- [Investigating Positive and Negative Qualities of Human-in-the-Loop Optimization for Designing Interaction Techniques](https://mlsanity.com/paper/2204.07641/) (2022)
- [Fly Away: Evaluating the Impact of Motion Fidelity on Optimized User Interface Design via Bayesian Optimization in Automated Urban Air Mobility Simulations](https://mlsanity.com/paper/2501.11829/) (2025)
- [Continual Human-in-the-Loop Optimization](https://mlsanity.com/paper/2503.05405/) (2025)
- [Analyzing User Activities, Demographics, Social Network Structure and User-Generated Content on Instagram](https://mlsanity.com/paper/1410.8099/) (2014)
- [Button Simulation and Design via FDVV Models](https://mlsanity.com/paper/2001.04352/) (2020)
- [Improving External Communication of Automated Vehicles Using Bayesian Optimization](https://mlsanity.com/paper/2501.10792/) (2025)
- [Constrained Preferential Bayesian Optimization and Its Application in Banner Ad Design](https://mlsanity.com/paper/2505.10954/) (2025)

## Built on by (most cited first, 2 of 2)

- [When Should Users Check? Modeling Confirmation Frequency in Multi-Step Agentic AI Tasks](https://mlsanity.com/paper/2510.05307/) (2025)
- [Agentic Aerial Cinematography: From Dialogue Cues to Cinematic Trajectories](https://mlsanity.com/paper/2509.16176/) (2025)

## Abstract (arXiv)

Adjusting visual parameters such as brightness and contrast is common in our everyday experiences. Finding the optimal parameter setting is challenging due to the large search space and the lack of an explicit objective function, leaving users to rely solely on their implicit preferences. Prior work has explored Preferential Bayesian Optimization (PBO) to address this challenge, involving users to iteratively select preferred designs from candidate sets. However, PBO often requires many rounds of preference comparisons, making it more suitable for designers than everyday end-users. We propose Meta-PO, a novel method that integrates PBO with meta-learning to improve sample efficiency. Specifically, Meta-PO infers prior users' preferences and stores them as models, which are leveraged to intelligently suggest design candidates for the new users, enabling faster convergence and more personalized results. An experimental evaluation of our method for appearance design tasks on 2D and 3D content showed that participants achieved satisfactory appearance in 5.86 iterations using Meta-PO when participants shared similar goals with a population (e.g., tuning for a ``warm'' look) and in 8 iterations even generalizes across divergent goals (e.g., from ``vintage'', ``warm'', to ``holiday''). Meta-PO makes personalized visual optimization more applicable to end-users through a generalizable, more efficient optimization conditioned on preferences, with the potential to scale interface personalization more broadly.