KeySense: LLM-Powered Hands-Down, Ten-Finger Typing on Commodity Touchscreens
Tony Li, Yan Ma, Zhuojun Li, Chun Yu, I. V. Ramakrishnan, Xiaojun Bi
Abstract
Existing touchscreen software keyboards prevent users from resting their hands, forcing slow and fatiguing index-finger tapping (“chicken typing”) instead of familiar hands-down ten-finger typing. We present KeySense, a purely software solution that preserves physical keyboard motor skills. KeySense isolates intentional taps from resting-finger noise with cognitive–motor timing patterns, and then uses a fine-tuned LLM decoder to turn the resulting noisy letter sequence into the intended word. In controlled component tests, this decoder substantially outperforms 2 statistical baselines (top-1 accuracy 84.8% vs 75.7% and 79.3%). A 12-participant study shows clear ergonomic and performance benefits: compared with the conventional hover-style keyboard, users rated KeySense as markedly less physically demanding (NASA-TLX median 1.5 vs 4.0), and after brief practice, typed significantly faster (WPM 28.3 vs 26.2, p <0.01). These results indicate that KeySense enables accurate, efficient and comfortable ten-finger text entry on commodity touchscreens, without any extra hardware.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 1064f7cd-71bf-408c-8d6b-a9d54d827ca6Builds on16
- LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
- Finetuned Language Models are Zero-Shot LearnersJason Wei, Maarten Bosma, Vincent Y. Zhao, Kelvin Guu et al.ICLR 2022 · 4,966 citations
- TapType: Ten-finger text entry on everyday surfaces via Bayesian inferencePaul Streli, Jiaxi Jiang, Andreas Rene Fender, Manuel Meier et al.CHI 2022 · 48 citations
- Decoding Surface Touch Typing from Hand-TrackingMark Richardson, Matt Durasoff, Robert WangUIST 2020 · 40 citations
- GlanceWriter: Writing Text by Glancing Over Letters with GazeWenzhe Cui, Rui Liu, Zhi Li, Yifan Wang et al.CHI 2023 · 28 citations
Related papers
- LLM Powered Text Entry Decoding and Flexible Typing on SmartphonesYan Ma, Dan Zhang, I. V. Ramakrishnan, Xiaojun BiCHI 2025 · 1 citation
- Can Capacitive Touch Images Enhance Mobile Keyboard Decoding?Piyawat Lertvittayakumjorn, Shanqing Cai, Billy Dou, Cedric Ho et al.UIST 2024 · 1 citation
- TypeAnywhere: A QWERTY-Based Text Entry Solution for Ubiquitous ComputingMingrui Ray Zhang, Shumin Zhai, Jacob O. WobbrockCHI 2022 · 27 citations
- ResType: Invisible and Adaptive Tablet Keyboard Leveraging Resting FingersZhuojun Li, Chun Yu, Yizheng Gu, Yuanchun ShiCHI 2023 · 6 citations
- PalmBoard: Leveraging Implicit Touch Pressure in Statistical Decoding for Indirect Text EntryXin Yi, Chen Wang, Xiaojun Bi, Yuanchun ShiCHI 2020 · 14 citations
