Ray LC

Kexue Fu, Jiaye Leng, Yawen Zhang et al.

Balancing scientific exposition and narrative engagement is a central challenge in science communication. To examine how to achieve balance, we conducted a formative study with four science communicators and a literature review of science communication practices, focusing on their workflows and strategies. These insights revealed how creators iteratively shift between exposition and engagement but often lack structured support. Building on this, we developed SpatialBalancing, a co-writing system that connects human spatial reasoning with the linguistic intelligence of large language models. The system visualizes revision trade-offs in a dual-axis space, where users select strategy-based labels to generate, compare, and refine versions during the revision process. This spatial externalization transforms revision into spatial navigation, enabling intentional iterations that balance scientific rigor with narrative appeal. In a within-subjects study (N=16), SpatialBalancing enhanced metacognitive reflection, flexibility, and creative exploration, demonstrating how coupling spatial reasoning with linguistic generation fosters monitoring in iterative science communication writing.

Yushang Yang, Fanxu Meng, Fiona Fui-Hoon Nah et al.

The ways people remember and recall places reveal an invisible aspect of cultural heritage (CH), reflecting how individuals and communities relate to these places. Heritage is communal, emerging through collaboratively constructed narratives rather than individual records. To probe how people may share collective memories, we designed an immersive two-person workflow for collaboratively co-designing 3D artifacts and environments in virtual heritage locations, using Generative AI (GenAI) to instantiate these intangible memories. Observations of the co-creation process revealed that participants merged prompts and model placements when negotiating different perspectives. They used spatial operations to compose scenes, and also to express personal and embodied experiences of CH. When GenAI failed to meet their needs, participants engaged in creative appropriation, re-purposing unsatisfactory generated objects as sources of design inspiration to further shared narratives. While GenAI may have a homogenizing effect on CH expression, this work shows how people may overcome limitations in immersive collaborative workflows.

Zhihan Jiang, Qianhui Chen, Chu Zhang et al.

In human conversation, empathic dialogue requires nuanced temporal cues indicating whether the conversational partner is paying attention. This type of "active listening" is overlooked in the design of Conversational Agents (CAs), which use the same pacing for one conversation. To model the temporal cues in human conversation, we need CAs that dynamically adjust response pacing according to user input. We qualitatively analyzed ten cases of active listening to distill five context-aware pacing strategies: Reflective Silence, Facilitative Silence, Empathic Silence, Holding Space, and Immediate Response. In a between-subjects study (N=50) with two conversational scenarios (relationship and career-support), the context-aware agent scored higher than static-pacing control on perceived human-likeness, smoothness, and interactivity, supporting deeper self-disclosure and higher engagement. In the career support scenario, the CA yielded higher perceived listening quality and affective trust. This work shows how insights from human conversation like context-aware pacing can empower the design of more empathic human-AI communication.

Suifang Zhou, Qi Gong, Ximing Shen et al.

LLM-assisted technologies are increasingly used to support cognitive processing and information interpretation, yet their role in aiding memory recall, and how people choose to engage with them, remains underexplored. We studied participants who watched a short robbery video (approximating a one-time eyewitness scenario) and composed recall statements using either a default GPT or a guided GPT prompted with a standardized eyewitness protocol. Results show that, in the default condition, participants who believed they had a clearer understanding of the event were more likely to trust GPT's output, whereas in the guided condition, participants showed stronger alignment between subjective clarity and actual recall. Additionally, participants evaluated the legitimacy of the individuals in the incident differently across conditions. Interaction analysis further revealed that default-GPT users spontaneously developed diverse strategies, including building on existing recollections, requesting potentially missing details, and treating GPT as a recall coach. This work shows how GPT-user interplay can subconsciously shape beliefs and perceptions of remembered events.

Xuehan Huang, Canwen Wang, Yifei Hao et al.

Chatbots are increasingly applied to domains previously reserved for human actors. One such domain is comedy, whereby both the general public working with ChatGPT and research-based LLM-systems have tried their hands on making humor. In formative interviews with professional comedians and video analyses of stand-up comedy in humans, we found that human performers often use their ethnic, gender, community, and demographic-based identity to enable joke-making. This suggests whether the identity of AI itself can empower AI humor generation for human audiences. We designed a machine-identity-based agent that uses its own status as AI to tell jokes in online performance format. Studies with human audiences (N=32) showed that machine-identity-based agents were seen as funnier than baseline-GPT agent. This work suggests the design of human-AI integrated systems that explicitly utilize AI as its own unique identity apart from humans.

Long Ling, Xiyu Zheng, Gengchen Cao et al.

People traditionally divine the future by interpreting natural phenomena as oracular signals, especially in societies adhering to traditional beliefs like China. With the advent of Generative AI (GenAI), people gain access to new ways of probing digital oracles for predicting the future. To understand how people use and interpret GenAI for divination in China, we interviewed 22 participants who habitually use GenAI platforms for fortune-telling, complemented by a three-week digital ethnography with 1,842 community posts. Qualitative analysis showed that people who seek psychological comfort are particularly receptive to GenAI-based decision-making. Users valued GenAI's accessibility, convenience, and efficiency while perceiving its lack of spiritual mystique. We observed community dynamics forming around GenAI tools, where users reinforce interpretations by sharing and discussing with each other, repeating queries until responses align with expectations. Our work uncovers how AI technologies change the way people and communities engage in traditional cultural practices while yearning for the same goals.

Qinshi Zhang, Weipeng Deng, Zhihan Jiang et al.

In model-based learning, the agent learns behaviors by simulating trajectories based on world model predictions. Standard world models typically learn a stationary transition function that maps states and actions to next states, when an action and an outcome frequently co-occur in training data, the model tends to internalize this correlation as a general causal rule while ignoring action preconditions. In interactive environments, however, agent actions can reshape the future affordance space. At each timestep, an action may becomes executable only after its prerequisites are met, or non-executable when they are destroyed. We term such events structure-changing events (SC events). As a result, a conventional world model often fails to determine whether a given action is executable in the current state, especially in multi-step predictions. Each imagined step is conditioned on an incorrect affordance state, and therefore the prediction error compounds over the rollout horizon. In this paper, we propose AGWM (Affordance-Grounded World Model), which learns an abstract affordance structure represented as a DAG of prerequisite dependencies to explicitly track the dynamic executability of actions. Experiments on game-based simulated environments demonstrate the effectiveness of our method by achieving lower multi-step prediction error, better generalization to novel configurations, and improved interpretability.

Sijia Liu, Hoi Ching Silvester Mok, Long Ling et al.

Chinese ceramic-making involves complex and interdependent steps, making it technically demanding. Digital fabrication methods attempt to make the process more accessible, but for craft-creators, technical challenges such as CAD and CAM skills remain major obstacles. To address this, we designed a hybrid workflow that integrates Generative AI with clay 3D printing to support new creative possibilities. We evaluated the workflow through ClayScape, a design tool that operationalizes this approach, with four ceramic creators. Our findings show that the workflow supports accessible ceramic creation while revealing both expanded opportunities for creative exploration and challenges in balancing agency and control. This work demonstrates how hybrid workflows can lower barriers to digital fabrication while supporting creative possibilities in culturally grounded ceramic practices.