{"id":32,"date":"2021-01-19T15:16:35","date_gmt":"2021-01-19T15:16:35","guid":{"rendered":"https:\/\/cix.cs.uni-saarland.de\/?page_id=32"},"modified":"2021-02-01T10:45:47","modified_gmt":"2021-02-01T10:45:47","slug":"publications","status":"publish","type":"page","link":"https:\/\/cix.cs.uni-saarland.de\/?page_id=32","title":{"rendered":"Publications"},"content":{"rendered":"\n
<\/a><\/form>

2026<\/h3>
\"Efficient<\/div>

Liao, Yi-Chi; Belo, Jo\u00e3o; Moon, Hee-Seung; Steimle, J\u00fcrgen; Feit, Anna Maria<\/p>

Efficient Human-in-the-Loop Optimization via Priors Learned from User Models<\/a> Proceedings Article<\/span> <\/p>

In: <\/span>Proceedings of the ACM CHI Conference on Human Factors in Computing Systems, <\/span>Association for Computing Machinery, <\/span>New York, NY, USA, <\/span>2026<\/span>, ISBN: 979-8-4007-2278-3\/26\/04<\/span>.<\/p>

Abstract<\/a><\/span> | Links<\/a><\/span> | BibTeX<\/a><\/span><\/p>

@inproceedings{10.1145\/3772318.3791976,
\r\ntitle = {Efficient Human-in-the-Loop Optimization via Priors Learned from User Models},
\r\nauthor = {Yi-Chi Liao and Jo\u00e3o Belo and Hee-Seung Moon and J\u00fcrgen Steimle and Anna Maria Feit},
\r\nurl = {https:\/\/lnkd.in\/e4nYASE6
\r\nhttps:\/\/arxiv.org\/abs\/2510.07754
\r\nhttps:\/\/lnkd.in\/eg2hjQed},
\r\ndoi = {10.1145\/3772318.3791976},
\r\nisbn = {979-8-4007-2278-3\/26\/04},
\r\nyear  = {2026},
\r\ndate = {2026-04-13},
\r\nurldate = {2026-04-13},
\r\nbooktitle = {Proceedings of the ACM CHI Conference on Human Factors in Computing Systems},
\r\nnumber = {416},
\r\npublisher = {Association for Computing Machinery},
\r\naddress = {New York, NY, USA},
\r\nabstract = {Human-in-the-loop optimization identifies optimal interface designs by iteratively observing user performance. However, it often requires numerous iterations due to the lack of prior information. While recent approaches have accelerated this process by leveraging previous optimization data, collecting user data remains costly and often impractical. We present a conceptual framework, Human-in-the-Loop Optimization with Model-Informed Priors (HOMI), which augments human-in-the-loop optimization with a training phase where the optimizer learns adaptation strategies from diverse, synthetic user data generated with predictive models before deployment. To realize HOMI, we introduce Neural Acquisition Function+ (NAF+), a Bayesian optimization method featuring a neural acquisition function trained with reinforcement learning. NAF+ learns optimization strategies from large-scale synthetic data, improving efficiency in real-time optimization with users. We evaluate HOMI and NAF+ with mid-air keyboard optimization, a representative VR input task. Our work presents a new approach for more efficient interface adaptation by bridging in situ and in silico optimization processes.},
\r\nkeywords = {},
\r\npubstate = {published},
\r\ntppubtype = {inproceedings}
\r\n}
\r\n<\/pre><\/div>
Close<\/a><\/p><\/div>
Human-in-the-loop optimization identifies optimal interface designs by iteratively observing user performance. However, it often requires numerous iterations due to the lack of prior information. While recent approaches have accelerated this process by leveraging previous optimization data, collecting user data remains costly and often impractical. We present a conceptual framework, Human-in-the-Loop Optimization with Model-Informed Priors (HOMI), which augments human-in-the-loop optimization with a training phase where the optimizer learns adaptation strategies from diverse, synthetic user data generated with predictive models before deployment. To realize HOMI, we introduce Neural Acquisition Function+ (NAF+), a Bayesian optimization method featuring a neural acquisition function trained with reinforcement learning. NAF+ learns optimization strategies from large-scale synthetic data, improving efficiency in real-time optimization with users. We evaluate HOMI and NAF+ with mid-air keyboard optimization, a representative VR input task. Our work presents a new approach for more efficient interface adaptation by bridging in situ and in silico optimization processes.<\/div>
Close<\/a><\/p><\/div>