Targeted control of fast prototyping through domain-specific interface

Yu-Zhe Shi, Mingchen Liu, Hanlu Ma, Qiao Xu, Huamin Qu, Kun He, Lecheng Ruan, Qining Wang
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54994-55015, 2025.

Abstract

Industrial designers have long sought a natural and intuitive way to achieve the targeted control of prototype models—using simple natural language instructions to configure and adjust the models seamlessly according to their intentions, without relying on complex modeling commands. While Large Language Models have shown promise in this area, their potential for controlling prototype models through language remains partially underutilized. This limitation stems from gaps between designers’ languages and modeling languages, including mismatch in abstraction levels, fluctuation in semantic precision, and divergence in lexical scopes. To bridge these gaps, we propose an interface architecture that serves as a medium between the two languages. Grounded in design principles derived from a systematic investigation of fast prototyping practices, we devise the interface’s operational mechanism and develop an algorithm for its automated domain specification. Both machine-based evaluations and human studies on fast prototyping across various product design domains demonstrate the interface’s potential to function as an auxiliary module for Large Language Models, enabling precise and effective targeted control of prototype models.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-shi25h, title = {Targeted control of fast prototyping through domain-specific interface}, author = {Shi, Yu-Zhe and Liu, Mingchen and Ma, Hanlu and Xu, Qiao and Qu, Huamin and He, Kun and Ruan, Lecheng and Wang, Qining}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {54994--55015}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/shi25h/shi25h.pdf}, url = {https://proceedings.mlr.press/v267/shi25h.html}, abstract = {Industrial designers have long sought a natural and intuitive way to achieve the targeted control of prototype models—using simple natural language instructions to configure and adjust the models seamlessly according to their intentions, without relying on complex modeling commands. While Large Language Models have shown promise in this area, their potential for controlling prototype models through language remains partially underutilized. This limitation stems from gaps between designers’ languages and modeling languages, including mismatch in abstraction levels, fluctuation in semantic precision, and divergence in lexical scopes. To bridge these gaps, we propose an interface architecture that serves as a medium between the two languages. Grounded in design principles derived from a systematic investigation of fast prototyping practices, we devise the interface’s operational mechanism and develop an algorithm for its automated domain specification. Both machine-based evaluations and human studies on fast prototyping across various product design domains demonstrate the interface’s potential to function as an auxiliary module for Large Language Models, enabling precise and effective targeted control of prototype models.} }
Endnote
%0 Conference Paper %T Targeted control of fast prototyping through domain-specific interface %A Yu-Zhe Shi %A Mingchen Liu %A Hanlu Ma %A Qiao Xu %A Huamin Qu %A Kun He %A Lecheng Ruan %A Qining Wang %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-shi25h %I PMLR %P 54994--55015 %U https://proceedings.mlr.press/v267/shi25h.html %V 267 %X Industrial designers have long sought a natural and intuitive way to achieve the targeted control of prototype models—using simple natural language instructions to configure and adjust the models seamlessly according to their intentions, without relying on complex modeling commands. While Large Language Models have shown promise in this area, their potential for controlling prototype models through language remains partially underutilized. This limitation stems from gaps between designers’ languages and modeling languages, including mismatch in abstraction levels, fluctuation in semantic precision, and divergence in lexical scopes. To bridge these gaps, we propose an interface architecture that serves as a medium between the two languages. Grounded in design principles derived from a systematic investigation of fast prototyping practices, we devise the interface’s operational mechanism and develop an algorithm for its automated domain specification. Both machine-based evaluations and human studies on fast prototyping across various product design domains demonstrate the interface’s potential to function as an auxiliary module for Large Language Models, enabling precise and effective targeted control of prototype models.
APA
Shi, Y., Liu, M., Ma, H., Xu, Q., Qu, H., He, K., Ruan, L. & Wang, Q.. (2025). Targeted control of fast prototyping through domain-specific interface. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:54994-55015 Available from https://proceedings.mlr.press/v267/shi25h.html.

Related Material