Shu Zhong
Biographic Data
| ID | 9560232 |
|---|---|
| NAME | Shu Zhong |
| GIVEN NAMES | Shu |
| FAMILY NAME | Zhong |
| SIGNATURE | ZHONG S |
| AFFILIATIONS | University College London |
| ORCID | 0000-0002-1820-6424 |
| VERIFIED | Yes |
| TOTAL WORKS | 3 |
| TOTAL CITATIONS | 0 |
| WORKS AS AUTHOR | 3 |
| WORKS AS EDITOR | 0 |
| FIRST PUBLICATION YEAR | 2025 |
| LATEST PUBLICATION YEAR | 2026 |
| H-INDEX | 0 |
TouchAI
Aligning large language models (LLMs) behaviour with human intent is critical for future AI. An important yet often overlooked aspect of this alignment is the perceptual alignment. Perceptual modalities like touch are more multifaceted and nuanced compared to other sensory modalities such as vision. This study investigates how well LLMs can understand and interpret human touch experiences by focusing on their capacity to perceive the tactile qual…
Mindful touch
With perpetually stressful lives, people are prompted to consider slowing down through mindfulness meditation. We extend HCI research beyond its pre-existing focus on interaction-intensive meditation technologies, to focus simply on whether one’s sense of touch can facilitate meditation. We capitalise on the touchless nature of mid-air haptics by rendering subtle sensations on the palm during meditation, using one design derived from pilot testin…
LLM-mediated domain-specific voice agents
Developing domain-specific conversational agents (CAs) has been challenged by the need for extensive domain-focused data. Recent advancements in Large Language Models (LLMs) make them a viable option as a knowledge backbone. LLMs behaviour can be enhanced through prompting, instructing them to perform downstream tasks in a zero-shot fashion (i.e. without training). To this end, we incorporated structural knowledge into prompts and used prompted L…
No prominent works on this page.
Mindful touch
With perpetually stressful lives, people are prompted to consider slowing down through mindfulness meditation. We extend HCI research beyond its pre-existing focus on interaction-intensive meditation technologies, to focus simply on whether one’s sense of touch can facilitate meditation. We capitalise on the touchless nature of mid-air haptics by rendering subtle sensations on the palm during meditation, using one design derived from pilot testin…
LLM-mediated domain-specific voice agents
Developing domain-specific conversational agents (CAs) has been challenged by the need for extensive domain-focused data. Recent advancements in Large Language Models (LLMs) make them a viable option as a knowledge backbone. LLMs behaviour can be enhanced through prompting, instructing them to perform downstream tasks in a zero-shot fashion (i.e. without training). To this end, we incorporated structural knowledge into prompts and used prompted L…
TouchAI
Aligning large language models (LLMs) behaviour with human intent is critical for future AI. An important yet often overlooked aspect of this alignment is the perceptual alignment. Perceptual modalities like touch are more multifaceted and nuanced compared to other sensory modalities such as vision. This study investigates how well LLMs can understand and interpret human touch experiences by focusing on their capacity to perceive the tactile qual…
Computer Science (2 works) · Psychology (2 works) · Action Observation and Synchronization (1 work) · Cognitive psychology (1 work) · Communication (1 work) · Domain (mathematical analysis) (1 work) · Everyday life (1 work) · Haptic technology (1 work) · Human–computer interaction (1 work) · Mathematics (1 work)