Zhipeng Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zhipeng Li has a total of 39 co-authors. Here are the top co-authors by number of shared publications:
- Christian Holz
Department of Computer Science, ETH Zurich, Zurich, Switzerland
8 shared publications - Yi-Chi Liao
Department of Computer Science, ETH Zurich, Zurich, Switzerland
4 shared publications - Yukang Yan
Department of Computer Science, University of Rochester, Rochester, USA
4 shared publications - Christoph Gebhardt
Department of Computer Science, ETH Zurich, Zurich, Switzerland
3 shared publications - Yuanchun Shi
Tsinghua University, Beijing, China
3 shared publications - David Lindlbauer
Human-Computer Interaction Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA
2 shared publications
Latest Publications
- Open Access
- 2 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-14
InvisiSpeech: Making Silent Speech Invisible through a Miniature Intraoral Sensor
- 2 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-14
Open AccessInvisiSpeech: Making Silent Speech Invisible through a Miniature Intraoral Sensor
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Retrofitting Existing 3D Objects with Surface-Conforming Capacitive Sensing
Augmenting the surface of 3D objects with capacitive sensing is particularly challenging when their volumes cannot be modified. In this paper, we present a computational fabrication pipeline that retrofits surface-only sensor layouts to 3D geometries for multi-touch interaction. Our system scans real-world objects to obtain their 3D mesh, generates and optimizes a 3D sensor design of drive and sense lines for mutual-capacitance sensing that complies with physical and hardware sensing constraints, and unfolds them into individual 2D stencils that can be cut from conductive material. Our fabrication pipeline cuts these from thin copper foil with a vinyl cutter and then assists manual sensor attachment by projecting the sensor design onto the dynamically registered real-world object. We connect the resulting electrode mesh to a mutual-capacitance scanning controller and resolve touch interaction in real time. We demonstrate our approach with four 3D geometries and evaluate our method and fabrication pipeline on them.
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Open AccessRetrofitting Existing 3D Objects with Surface-Conforming Capacitive Sensing
Augmenting the surface of 3D objects with capacitive sensing is particularly challenging when their volumes cannot be modified. In this paper, we present a computational fabrication pipeline that retrofits surface-only sensor layouts to 3D geometries for multi-touch interaction. Our system scans real-world objects to obtain their 3D mesh, generates and optimizes a 3D sensor design of drive and sense lines for mutual-capacitance sensing that complies with physical and hardware sensing constraints, and unfolds them into individual 2D stencils that can be cut from conductive material. Our fabrication pipeline cuts these from thin copper foil with a vinyl cutter and then assists manual sensor attachment by projecting the sensor design onto the dynamically registered real-world object. We connect the resulting electrode mesh to a mutual-capacitance scanning controller and resolve touch interaction in real time. We demonstrate our approach with four 3D geometries and evaluate our method and fabrication pipeline on them.
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-20
Automating UI Optimization through Multi-Agentic Reasoning
We present AutoOptimization, a novel multi-objective optimization framework for adapting user interfaces. From a user’s verbal preferences for changing a UI, our framework guides a prioritization-based Pareto frontier search over candidate layouts. It selects suitable objective functions for UI placement while simultaneously parameterizing them according to the user’s instructions to define the optimization problem. A solver then generates a series of optimal UI layouts, which our framework validates against the user’s instructions to adapt the UI with the final solution. Our approach thus overcomes the previous need for manual inspection of layouts and the use of population averages for objective parameters. We integrate multiple agents sequentially within our framework, enabling the system to leverage their reasoning capabilities to interpret user preferences, configure the optimization problem, and validate optimization outcomes. We evaluate each step of our framework inside a Mixed Reality use case and demonstrate that AutoOptimization effectively increases the usability of UI adaptation schemes.
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-20
Open AccessAutomating UI Optimization through Multi-Agentic Reasoning
We present AutoOptimization, a novel multi-objective optimization framework for adapting user interfaces. From a user’s verbal preferences for changing a UI, our framework guides a prioritization-based Pareto frontier search over candidate layouts. It selects suitable objective functions for UI placement while simultaneously parameterizing them according to the user’s instructions to define the optimization problem. A solver then generates a series of optimal UI layouts, which our framework validates against the user’s instructions to adapt the UI with the final solution. Our approach thus overcomes the previous need for manual inspection of layouts and the use of population averages for objective parameters. We integrate multiple agents sequentially within our framework, enabling the system to leverage their reasoning capabilities to interpret user preferences, configure the optimization problem, and validate optimization outcomes. We evaluate each step of our framework inside a Mixed Reality use case and demonstrate that AutoOptimization effectively increases the usability of UI adaptation schemes.
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-29
Preference-Guided Prompt Optimization for Text-to-Image Generation
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-29
Open AccessPreference-Guided Prompt Optimization for Text-to-Image Generation
- Open Access
- 27 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-23
Efficient Visual Appearance Optimization by Learning from Prior Preferences
- 27 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-23
Open AccessEfficient Visual Appearance Optimization by Learning from Prior Preferences
- Open Access
- 27 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-17
SwitchAR: Perceptual Manipulations in Augmented Reality
- 27 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-17
Open AccessSwitchAR: Perceptual Manipulations in Augmented Reality
- Open Access
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-18
Modeling the Impact of Visual Stimuli on Redirection Noticeability with Gaze Behavior in Virtual Reality
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-18
Open AccessModeling the Impact of Visual Stimuli on Redirection Noticeability with Gaze Behavior in Virtual Reality
- Open Access
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-4
SwitchAR: Enabling Perceptual Manipulations in Augmented Reality Leveraging Change Blindness and Inattentional Blindness
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-4
Open AccessSwitchAR: Enabling Perceptual Manipulations in Augmented Reality Leveraging Change Blindness and Inattentional Blindness
- Open Access
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-26
Continual Human-in-the-Loop Optimization
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-26
Open AccessContinual Human-in-the-Loop Optimization
- Open Access
- 13 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Demonstrating LLM-for-X: Application-agnostic Integration of Large Language Models to Support Writing Workflows
In this demonstration, we show LLM-for-X, a system-wide shortcut layer that connects any application to backend LLM support through a lightweight popup dialog. LLM-for-X provides users with quick and easy-to-use LLM assistance without context switching to support writing and reading tasks. We show the use of LLM-for-X across several applications, such as Microsoft Office, VSCode, and Adobe Acrobat, which our tool seamlessly connects to the backends of OpenAI ChatGPT and Google Gemini. We also demonstrate the use of our system inside web apps such as Overleaf.
- 13 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Open AccessDemonstrating LLM-for-X: Application-agnostic Integration of Large Language Models to Support Writing Workflows
In this demonstration, we show LLM-for-X, a system-wide shortcut layer that connects any application to backend LLM support through a lightweight popup dialog. LLM-for-X provides users with quick and easy-to-use LLM assistance without context switching to support writing and reading tasks. We show the use of LLM-for-X across several applications, such as Microsoft Office, VSCode, and Adobe Acrobat, which our tool seamlessly connects to the backends of OpenAI ChatGPT and Google Gemini. We also demonstrate the use of our system inside web apps such as Overleaf.