Jinhe Wen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jinhe Wen has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Haojian Jin
University of California San Diego, La Jolla, California, USA
3 shared publications - Tauhidur Rahman
University of California San Diego, La Jolla, California, USA
2 shared publications - Zhongyang Zhang
University of California at San Diego, San Diego, USA
2 shared publications - Bijan Arbab
University of California at San Diego, San Diego, USA
1 shared publication - Dara Arbab
Arizona State University, Phoenix, USA
1 shared publication - Kent Giard
Intel Corporation, Hillsboro, USA
1 shared publication
Latest Publications
- Open Access
- 30 September 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
- Vol. 10 (3) , 1-32
PreTap: Implicit Reachability Analysis and Tap Prediction for One-handed Mobile Interaction
One-handed interaction on large-screen smartphones often leads to ergonomic discomfort and disruption, while existing solutions typically rely on explicit gestures, additional hardware, or static ergonomic models, limiting their deployability and adaptability. We present PreTap, an anticipatory system that implicitly infers reachability and predicts imminent tap regions from zero-permission inertial signals, enabling proactive interface adaptation during the pre-tap phase. Realizing this capability introduces challenges, including the extremely short prediction horizon, substantial inter-user variability in reachability zones, and IMU signal patterns. To address these challenges, PreTap combines an on-device (i.e., 180K-parameter) CNN-Attention model with an unsupervised reachability analysis algorithm that captures user-specific ergonomic constraints and supports user-specific adaptation goals. An empirical study with 50 participants on commodity smartphones shows that PreTap can accurately predict the tap intent and proactively adapt the UI approximately 220 ms before contact, while maintaining low runtime overhead suitable for real-time deployment. These results demonstrate the potential of implicit motion sensing to enable intelligent, reachability-aware mobile interfaces that better align with users' motor intent.
- 30 September 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
- Vol. 10 (3) , 1-32
Open AccessPreTap: Implicit Reachability Analysis and Tap Prediction for One-handed Mobile Interaction
One-handed interaction on large-screen smartphones often leads to ergonomic discomfort and disruption, while existing solutions typically rely on explicit gestures, additional hardware, or static ergonomic models, limiting their deployability and adaptability. We present PreTap, an anticipatory system that implicitly infers reachability and predicts imminent tap regions from zero-permission inertial signals, enabling proactive interface adaptation during the pre-tap phase. Realizing this capability introduces challenges, including the extremely short prediction horizon, substantial inter-user variability in reachability zones, and IMU signal patterns. To address these challenges, PreTap combines an on-device (i.e., 180K-parameter) CNN-Attention model with an unsupervised reachability analysis algorithm that captures user-specific ergonomic constraints and supports user-specific adaptation goals. An empirical study with 50 participants on commodity smartphones shows that PreTap can accurately predict the tap intent and proactively adapt the UI approximately 220 ms before contact, while maintaining low runtime overhead suitable for real-time deployment. These results demonstrate the potential of implicit motion sensing to enable intelligent, reachability-aware mobile interfaces that better align with users' motor intent.
- Open Access
- 5 October 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 9 (6) , 329-354
Predicting Quality of Video Gaming Experience using Global-Scale Telemetry Data and Federated Learning
Frames Per Second (FPS) significantly affects the gaming experience. Providing players with accurate FPS estimates prior to purchase benefits both players and game developers. However, we have a limited understanding of how to predict a game's technical performance on a specific device. In this paper, we first conduct a comprehensive analysis of a wide range of factors that may affect game FPS on a global-scale dataset to identify the determinants of FPS. This includes player-side and game-side characteristics, as well as country-level socio-economic statistics. Furthermore, recognizing that accurate FPS predictions require extensive user data, which raises privacy concerns, we propose a federated learning-based model to ensure user privacy. Each player and game is assigned a unique learnable knowledge kernel that gradually extracts latent features for improved accuracy. We also introduce a novel training and prediction scheme that allows these kernels to be dynamically plug-and-play, effectively addressing cold start issues. To train this model with minimal bias, we collected a large telemetry dataset from 224 countries and regions, 100,000 users, and 835 games. Our model achieved a mean Wasserstein distance of 0.469 between predicted and ground truth FPS distributions, outperforming all baseline methods.
- 5 October 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 9 (6) , 329-354
Open AccessPredicting Quality of Video Gaming Experience using Global-Scale Telemetry Data and Federated Learning
Frames Per Second (FPS) significantly affects the gaming experience. Providing players with accurate FPS estimates prior to purchase benefits both players and game developers. However, we have a limited understanding of how to predict a game's technical performance on a specific device. In this paper, we first conduct a comprehensive analysis of a wide range of factors that may affect game FPS on a global-scale dataset to identify the determinants of FPS. This includes player-side and game-side characteristics, as well as country-level socio-economic statistics. Furthermore, recognizing that accurate FPS predictions require extensive user data, which raises privacy concerns, we propose a federated learning-based model to ensure user privacy. Each player and game is assigned a unique learnable knowledge kernel that gradually extracts latent features for improved accuracy. We also introduce a novel training and prediction scheme that allows these kernels to be dynamically plug-and-play, effectively addressing cold start issues. To train this model with minimal bias, we collected a large telemetry dataset from 224 countries and regions, 100,000 users, and 835 games. Our model achieved a mean Wasserstein distance of 0.469 between predicted and ground truth FPS distributions, outperforming all baseline methods.
- Open Access
- 21 November 2024
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
- Vol. 8 (4) , 1-31
Governing Open Vocabulary Data Leaks Using an Edge LLM through Programming by Example
A major concern with integrating large language model (LLM) services (e.g., ChatGPT) into workplaces is that employees may inadvertently leak sensitive information through their prompts. Since user prompts can involve arbitrary vocabularies, conventional data leak mitigation solutions, such as string-matching-based filtering, often fall short. We present GPTWall, a privacy firewall that helps internal admins create and manage policies to mitigate data leaks in prompts sent to external LLM services. GPTWall's key innovations are (1) introducing a lightweight LLM running on the edge to obfuscate target information in prompts and restore the information after receiving responses, and (2) helping admins author fine-grained disclosure policies through programming by example. We evaluated GPTWall with 12 participants and found that they could create an average of 17.7 policies within 30 minutes, achieving an increase of 29% in precision and 22% in recall over the state-of-the-art data de-identification tool.
- 21 November 2024
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
- Vol. 8 (4) , 1-31
Open AccessGoverning Open Vocabulary Data Leaks Using an Edge LLM through Programming by Example
A major concern with integrating large language model (LLM) services (e.g., ChatGPT) into workplaces is that employees may inadvertently leak sensitive information through their prompts. Since user prompts can involve arbitrary vocabularies, conventional data leak mitigation solutions, such as string-matching-based filtering, often fall short. We present GPTWall, a privacy firewall that helps internal admins create and manage policies to mitigate data leaks in prompts sent to external LLM services. GPTWall's key innovations are (1) introducing a lightweight LLM running on the edge to obfuscate target information in prompts and restore the information after receiving responses, and (2) helping admins author fine-grained disclosure policies through programming by example. We evaluated GPTWall with 12 participants and found that they could create an average of 17.7 policies within 30 minutes, achieving an increase of 29% in precision and 22% in recall over the state-of-the-art data de-identification tool.
- Open Access
- 14 October 2024
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 8 (CHI PLAY) , 1-23
Folk Models of Loot Boxes in Video Games
Regulations require video games to provide transparency regarding loot box odds to keep players informed, leading many games to disclose probabilities in various ways; yet, the extent of players' comprehension of loot box mechanics remains unclear. We performed a content analysis on 80 online posts to understand players' perceptions of loot box odds in two popular video games (Genshin Impact and Honkai: Star Rail). We then conducted semi-structured interviews with 24 players to explore the causes of these folk models across more games. Utilizing a bottom-up open coding approach, we created a taxonomy of folk models players have about loot boxes. We found that participants generally possessed inaccurate mental models of how loot boxes work, and they wanted game companies to enhance loot box transparency in three areas of probability disclosures: granularity, longitude, and scope.
- 14 October 2024
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 8 (CHI PLAY) , 1-23
Open AccessFolk Models of Loot Boxes in Video Games
Regulations require video games to provide transparency regarding loot box odds to keep players informed, leading many games to disclose probabilities in various ways; yet, the extent of players' comprehension of loot box mechanics remains unclear. We performed a content analysis on 80 online posts to understand players' perceptions of loot box odds in two popular video games (Genshin Impact and Honkai: Star Rail). We then conducted semi-structured interviews with 24 players to explore the causes of these folk models across more games. Utilizing a bottom-up open coding approach, we created a taxonomy of folk models players have about loot boxes. We found that participants generally possessed inaccurate mental models of how loot boxes work, and they wanted game companies to enhance loot box transparency in three areas of probability disclosures: granularity, longitude, and scope.