Lyumanshan Ye
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Lyumanshan Ye has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
- Bingyi Liu
University of Michigan
3 shared publications - Yibo Meng
Cornell University
3 shared publications - Danni Chang
School of Design, Shanghai Jiao Tong University, Shanghai 200240, China
2 shared publications - Dayuan Fu
Artificial intelligence, Beijing University of Posts and telecommunications, Beijing, beijing, China and artificial intelligence, Beijing University of Posts and telecommunications, Beijing, beijing, China
1 shared publication - Hao Jin
Northeastern University, Khoury College of Computer Science, United States
1 shared publication - Huidi Lu
Saïd Business School, University of Oxford, Oxford, United Kingdom
1 shared publication
Latest Publications
- Open Access
- 24 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-18
Balancing Safety and Autonomy: Accessibility-Oriented Interventions in Generative AI for Cognitive Impairment
- 24 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-18
Open AccessBalancing Safety and Autonomy: Accessibility-Oriented Interventions in Generative AI for Cognitive Impairment
- Open Access
- 10 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 237-241
"Everyone Says Them": Deception Typologies, Probabilistic Trust, and Grassroots Safety Knowledge Among Gay Dating App Users in China
- 10 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 237-241
Open Access"Everyone Says Them": Deception Typologies, Probabilistic Trust, and Grassroots Safety Knowledge Among Gay Dating App Users in China
- Open Access
- 13 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 666-683
"Creating the World with Order!': Designing Tangible Toolkit to Support Creative Expression and Wellbeing for Individuals with ASD
- 13 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 666-683
Open Access"Creating the World with Order!': Designing Tangible Toolkit to Support Creative Expression and Wellbeing for Individuals with ASD
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Interaction as Intelligence: A Transparent, Fine-Grained Multi-Agent Deep Research System for Human-Agent Collaboration
As AI systems engage in extended thinking processes for research tasks, interaction becomes increasingly important for effective long-horizon research. In these tasks, many current deep research systems still follow an “input–wait–output” paradigm: users submit a query and receive results only after a non-interruptible process with limited visibility into intermediate decisions. In multi-agent systems, delayed feedback can amplify early errors, limit query refinement during investigation and reduce opportunities for expertise integration. To address these limitations, we introduce Deep Cognition, a multi-agent deep research system that enables users to monitor and steer an ongoing research process through targeted interventions during execution. Deep Cognition provides two key capabilities: (1) Transparent, controllable, and interruptible interaction that reveals AI reasoning, exposing intermediate plans and evidence and allowing users to intervene at intermediate checkpoints; (2) Fine-grained bidirectional dialogue that enables per-subagent control during execution.
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Open AccessInteraction as Intelligence: A Transparent, Fine-Grained Multi-Agent Deep Research System for Human-Agent Collaboration
As AI systems engage in extended thinking processes for research tasks, interaction becomes increasingly important for effective long-horizon research. In these tasks, many current deep research systems still follow an “input–wait–output” paradigm: users submit a query and receive results only after a non-interruptible process with limited visibility into intermediate decisions. In multi-agent systems, delayed feedback can amplify early errors, limit query refinement during investigation and reduce opportunities for expertise integration. To address these limitations, we introduce Deep Cognition, a multi-agent deep research system that enables users to monitor and steer an ongoing research process through targeted interventions during execution. Deep Cognition provides two key capabilities: (1) Transparent, controllable, and interruptible interaction that reveals AI reasoning, exposing intermediate plans and evidence and allowing users to intervene at intermediate checkpoints; (2) Fine-grained bidirectional dialogue that enables per-subagent control during execution.
- Open Access
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Colin: A Multimodal Human-AI Co-Creation Storytelling System to Support children’s Multi-Level Narrative Skills
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessColin: A Multimodal Human-AI Co-Creation Storytelling System to Support children’s Multi-Level Narrative Skills
- Open Access
- 13 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-3
SenseBot: Leveraging Embodied Asymmetric Interaction and Social Robotic to Enhance Intergenerational Communication
Embodied communication, which uses physical cues to convey meaning and emotions, is essential for building social connections. In this work, we introduce SenseBot, an augmented reality (AR)-enabled robotic representative designed to facilitate embodied communication. SenseBot acts as a local agent for remote users, allowing them to engage more interactively and meaningfully with people on-site.
- 13 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Open AccessSenseBot: Leveraging Embodied Asymmetric Interaction and Social Robotic to Enhance Intergenerational Communication
Embodied communication, which uses physical cues to convey meaning and emotions, is essential for building social connections. In this work, we introduce SenseBot, an augmented reality (AR)-enabled robotic representative designed to facilitate embodied communication. SenseBot acts as a local agent for remote users, allowing them to engage more interactively and meaningfully with people on-site.
- Open Access
- 19 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-9
“Just Like Blooming Fireworks, And Match With Function Perfectly”: Explore and Evaluate User-Defined One-Handed Gestures of Smartwatch
One-handed gesture interaction is a more convenient input interaction method on smartwatches for some special scenarios, e.g. wearing a smartwatch when running or biking. To explore user-friendly one-handed gestures, what users are thinking when using the gesture, and what characteristic would make the user feel this one-handed gesture is friendly, we developed a series of one-handed gestures for 6 basic functions of the smartwatch. The end-user elicitation method resulted in 12 new one-hand gestures. We compared these 12 user-defined one-handed gestures with the Apple Watch one-handed gestures. We developed a Wizard of Oz model and evaluated these gestures by using qualitative and quantitative approaches. The results show that we generated a set of one-handed gestures that are more friendly than the existing Apple Watch one-handed gestures. Also, during the evaluation process, we collected quantitative data and interesting user perspectives. We also gave some design recommendations for one-handed gestures.
- 19 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Open Access“Just Like Blooming Fireworks, And Match With Function Perfectly”: Explore and Evaluate User-Defined One-Handed Gestures of Smartwatch
One-handed gesture interaction is a more convenient input interaction method on smartwatches for some special scenarios, e.g. wearing a smartwatch when running or biking. To explore user-friendly one-handed gestures, what users are thinking when using the gesture, and what characteristic would make the user feel this one-handed gesture is friendly, we developed a series of one-handed gestures for 6 basic functions of the smartwatch. The end-user elicitation method resulted in 12 new one-hand gestures. We compared these 12 user-defined one-handed gestures with the Apple Watch one-handed gestures. We developed a Wizard of Oz model and evaluated these gestures by using qualitative and quantitative approaches. The results show that we generated a set of one-handed gestures that are more friendly than the existing Apple Watch one-handed gestures. Also, during the evaluation process, we collected quantitative data and interesting user perspectives. We also gave some design recommendations for one-handed gestures.