According to the recently introduced theory of artistic support tools, creativity support tools exert normative influences over artistic production, instantiating a normative ground that shapes both the process and product of artistic expression.We argue that the normative ground of most existing automated writing tools is misaligned with writerly values and identify a potential alternative frame-material writing support-for experimental poetry tools that flexibly support the finding, processing, transforming, and shaping of text(s).Based on this frame, we introduce Phraselette, an artistic material writing support interface that helps experimental poets search for words and phrases.To provide material writing support, Phraselette is designed to counter the dominant mode of automated writing tools, while offering language model affordances in line with writerly values.We further report on an extended expert evaluation involving 10 published poets that indicates support for both our framing of material writing support and for Phraselette itself.

Figure 1: Fuzzy linkography allows for the rapid translation of user activity logs from digital creativity support tools (and other traces of creative activity) into rough graphical summaries, suitable for visual and quantitative inspection by researchers.

Generative AI has established the opportunity to readily transform content from one medium to another.This capability is especially powerful for storytelling, where visual illustrations can illuminate a story originally expressed in text.In this paper, we focus on the task of narrative scene illustration, which involves automatically generating an image depicting a scene in a story.Motivated by recent progress on textto-image models, we consider a pipeline that uses LLMs as an interface for prompting textto-image models to generate scene illustrations given raw story text.We apply variations of this pipeline to a prominent story corpus in order to synthesize illustrations for scenes in these stories.We conduct a human annotation task to obtain pairwise quality judgments for these illustrations.The outcome of this process is the SCENEILLUSTRATIONS dataset, which we release as a new resource for future work on crossmodal narrative transformation.Through our analysis of this dataset and experiments modeling illustration quality, we demonstrate that LLMs can effectively verbalize scene knowledge implicitly evoked by story text.Moreover, this capability is impactful for generating and evaluating illustrations.

The virtual live streaming format of Vtubers is gaining immense popularity worldwide, aided by advancements in large language models (LLMs) and 2D/3D avatar simulation technologies. The emergence of pure AI-driven Vtubers represents a promising trend in content creation. However, research has not adequately explored the interactive capabilities between live streaming platforms and Vtubers, nor their implications on parasocial relationships. We developed “Blibug,” an AI-Vtuber on the Chinese Bilibili platform, who can be interacted with through “Danmu” messages (real-time comments overlaid on the video playback, also called a “bullet curtain”). By implementing an interactive AI-Vtuber action and dialogue response system, we translate relatable daily activities into virtual engagements and establish a real-time, one-to-many AI-Human dialogue framework. Our study aims to investigate the entertainment and narrative dimensions of Vtubers and to understand AI’s role as a social agent and its impact on parasocial relationships.

This artwork presents an intelligent chatbot called Wander. This work used knowledge-based story generation to facilitate a narrative AI chatbot on daily communication platforms, producing interactive fiction with the most accessible natural language input: text messages. On social media platforms such as Discord and WeChat, Wander can generate a science-fiction style travelogue about the future earth, including text, images and global coordinates (GPS) based on real-world locations (e.g. Paris). The journeys are visualised in real-time on an interactive map that can be updated with participants' data. Based on Viktor Shklovsky's defamiliarization technique, we present how an AI agent can become a storyteller through common messages in daily life and lead participants to see the world from new perspectives. The website of this work is: https://wander001.com/

We developed Wander[00l] as an experiment to discuss several visions toward the metaverse: through crowd contribution, how an AI agent can become a highly accessible storyteller, and how to link the virtual and physical world through AI-generated content (AIGC). In this artwork, we implement a hybrid AIGC and user-generated content (UGC) system to facil-itate a narrative AI chatbot, Wander, that produces interactive fiction through knowledge graphs with text messages input by users on instant messaging social platforms. On Discord and WeChat, Wander can generate science-fiction-style travelogues about the future earth, including text, style-transferred images and global coordinates (GPS) based on real-world locations (e.g. Paris). The crowd interactions with Wander are visualised on an interactive globe map in real time, documenting the players' asynchronous contributions to exploring the speculative future earth. This paper presents Wander's concept, development and user study to demonstrate how people would interact with an AI agent in a narrative context for the future metaverse.

We introduce PoCoPo, the first handheld pin-based shape display that can render various 2.5D shapes in hand in realtime. We designed the display small enough for a user to hold it in hand and carry it around, thereby enhancing the haptic experiences in a virtual environment. PoCoPo has 18 motor-driven pins on both sides of a cuboid, providing the sensation of skin contact on the user's palm and fingers. We conducted two user studies to understand the capability of PoCoPo. The first study showed that the participants were generally successful in distinguishing the shapes rendered by PoCoPo with an average success rate of 88.5%. In the second study, we investigated the acceptable visual size of a virtual object when PoCoPo rendered a physical object of a certain size. The result led to a better understanding of the acceptable differences between the perceptions of visual size and haptic size.

We present PaCaPa, a handheld device that renders haptics on a user's palm when the user interacts with virtual objects using virtual tools such as a stick. PaCaPa is a cuboid device with two wings that open and close. As the user's stick makes contact with a virtual object, the wings open by a specific degree to dynamically change the pressure on the palm and fingers. The open angle of the wings is calculated from the angle between the virtual stick and hand direction. As the stick bites into the target object, a large force is generated. Our device enables three kinds of renderings: size, shape, and stiffness. We conducted user studies to evaluate the performance of our device. We also evaluated our device in two application scenarios. User feedback and qualitative ratings indicated that our device can make indirect interaction with handheld tools more realistic.

The absence of tactile cues such as keys and buttons makes touchscreens difficult to navigate for people with visual impairments. Increasing tactile feedback and tangible interaction on touchscreens can improve their accessibility. However, prior solutions have either required hardware customization or provided limited functionality with static overlays. Prior investigation of tactile solutions for large touchscreens also may not address the challenges on mobile devices. We therefore present Interactiles, a low cost, portable, and unpowered system that enhances tactile interaction on Android touchscreen phones. Interactiles consists of 3D-printed hardware interfaces and software that maps interaction with that hardware to manipulation of a mobile app. The system is compatible with the built-in screen reader without requiring modification of existing mobile apps. We describe the design and implementation of Interactiles, and we evaluate its improvement in task performance and the user experience it enables with people who are blind or have low vision.

PaCaPa is a handheld device that presents haptic stimuli on a user's palm when the user interacts with virtual objects using virtual tools. It is a box-shaped device and has two wings. This device can present the contact force and contact angle by opening and closing the wings based on the angle between the direction of the virtual tool and hand. By changing these haptic sensations on the palm and fingers, it enables the users to perceive different size, shape, and stiffness of virtual objects.