arXiv subjects

Xiruo Wang

Publications and source records attributed to Xiruo Wang.

3 recordsLinked to original sources

arXiv2026

One Kiss: Emojis as Agents of Genre Flux in Generative Comics

Generative AI has made visual storytelling widely accessible, yet current prompt-based interactions often force users into a trade-off between precise control and creative flow. We present One Kiss, a co-creative comic generation system that introduces "Affective Steering". Instead of writing text prompts, users guide the tone of their story through emoji inputs, whose semantic ambiguity becomes a resource rather than a limitation. Unlike traditional text-to-image tools that rely on explicit descriptions, One Kiss uses a dual-stream input in which users define structural pacing by sketching panel frames and set atmospheric tone by pairing keywords with emojis. This mechanism enables "Genre Flux," where emotional inputs accumulate across panels and gradually shift the genre of a story. A preliminary study (N = 6) suggests that this soft steering approach may reframe the user's role from prompt engineer to narrative director, with ambiguity serving as a source of creative surprise rather than a loss of control.

cs.HC↗

arXiv2025

"I Like Your Story!": A Co-Creative Story-Crafting Game with a Persona-Driven Character Based on Generative AI

While generative AI is advancing writing support tools, creative writing is often seen as the exclusive domain of skilled writers. This paper introduces "1001 Nights", a co-creative story-crafting game that transforms writing into a playful and rewarding activity. In this game, the AI agent takes on the role of a "moody" king with distinct storytelling preferences, not merely assisting but actively influencing the narrative. Players engage with the king agent through strategic storytelling, guiding him to mention weapon-related keywords, which materialize as battle equipment. The king agent provides dynamic feedback, expressing satisfaction or displeasure, prompting players to adjust their approach. By combining storytelling, game mechanics, and AI-driven responses, our system motivates creativity through playful constraints. Inspired by Oulipo's literary techniques, this approach demonstrates how AI-powered game experiences can make creative writing more accessible and engaging, encouraging players to explore their creative potential.

cs.HC↗

arXiv2020

MDEA: Malware Detection with Evolutionary Adversarial Learning

Malware detection have used machine learning to detect malware in programs. These applications take in raw or processed binary data to neural network models to classify as benign or malicious files. Even though this approach has proven effective against dynamic changes, such as encrypting, obfuscating and packing techniques, it is vulnerable to specific evasion attacks where that small changes in the input data cause misclassification at test time. This paper proposes a new approach: MDEA, an Adversarial Malware Detection model uses evolutionary optimization to create attack samples to make the network robust against evasion attacks. By retraining the model with the evolved malware samples, its performance improves a significant margin.

cs.CR↗