Human-Computer Interaction
Research on user interfaces, interaction design, accessibility, and UX.
cs.HC · 436 papersMetaphors as Scaffolds: Spatial, Embodied, Fantastical, and Relational Framings for Youth Usable Privacy Design
Different metaphors (spatial, embodied, fantastical, relational) significantly shape how youth reason about and manage digital privacy, impacting design.
From Standard English to Singlish: A Retrieval-Augmented Approach for Code-Switched Creole Generation in Large Language Models
A RAG framework generates code-switched Singlish by externalizing dialectal knowledge, achieving naturalness with minimal edits and high semantic preservation.
The University AI Didn't Replace -- Rethinking Universities in the AI Era
This paper proposes a framework for AI adoption in universities, moving from informal innovation to strategic integration and curriculum redesign.
Social Understanding, Placeness, and Identity Alignment: A Design Framework for Friendship-Supportive Youth Social Media
This paper introduces a design framework for youth social media, focusing on social understanding, placeness, and identity alignment to foster friendships.
Problem Space Attunement in Youth Social Media Design
This paper identifies and addresses three misattunements in youth social media design using novel methods to create more supportive platforms.
Exploring the "Banality" of Deception in Generative AI
This paper explores "banal deception" in generative AI, where subtle, normalized influences blur the line between assistance and manipulation.
AI and Consciousness: Shifting Focus Towards Tractable Questions
This paper argues that direct AI consciousness research is intractable, proposing a shift to studying the perception of AI consciousness and its societal impact.
From Surface Learning to Deep Understanding: A Grounded AI Tutoring System for Moodle
A Moodle plugin uses RAG and LLMs for Socratic tutoring and educator content generation, ensuring high-quality, hallucination-free education.
SIGMA-ASL: Sensor-Integrated Multimodal Dataset for Sign Language Recognition
SIGMA-ASL is a new multimodal dataset integrating vision, radar, and IMU data for robust and privacy-preserving sign language recognition.
Human-AI Co-Evolution and Epistemic Collapse: A Dynamical Systems Perspective
This paper models human-AI interaction as a coupled dynamical system, revealing how increasing AI reliance can lead to 'epistemic collapse' and reduced knowledge diversity.
LLM-Based Educational Simulation: Evaluating Temporal Student Persona Stability Across ADHD Profiles
LLMs can simulate student personas, but their stability, especially for ADHD profiles, depends on structured interaction design, crucial for valid educational applications.
LearnMate^2: Design and Evaluation of an LLM-powered Personalized and Adaptive Support System for Online Learning
LearnMate^2 is an LLM-powered system designed to provide personalized and adaptive support for online learning, improving outcomes and user experience.
RobotEQ: Transitioning from Passive Intelligence to Active Intelligence in Embodied AI
RobotEQ introduces the first benchmark for active intelligence, assessing if embodied AI can understand and adhere to social norms without explicit commands.
AffectGPT-RL: Revealing Roles of Reinforcement Learning in Open-Vocabulary Emotion Recognition
AffectGPT-RL uses reinforcement learning to optimize non-differentiable metrics in open-vocabulary multimodal emotion recognition, achieving SOTA results.
EventColumn: Integrating Event Sequences into Tabular Visualizations
EventColumn integrates event sequences into tabular visualizations, enabling simultaneous comparison with other data types.
Reality Check: How Avatar and Face Representation Affect the Perceptual Evaluation of Synthesized Gestures
This paper shows avatar and face rendering significantly bias perceptual judgments of synthesized gestures, offering guidelines for evaluation and deployment.
Visual Fingerprints for LLM Generation Comparison
This paper introduces visual fingerprints to compare LLM outputs across different generation conditions by analyzing linguistic choice distributions.
I see artifacts: ICA-based EEG artifact removal does not improve deep network decoding across three BCI tasks
ICA-based EEG artifact removal does not consistently improve deep network decoding across three BCI tasks, despite significant computational cost.
PersonaKit (PK): A Plug-and-Play Platform for User Testing Diverse Roles in Full-Duplex Dialogue
PersonaKit is an open-source platform for rapidly prototyping and evaluating diverse persona-specific turn-taking strategies in full-duplex dialogue systems.
Intentmaking and Sensemaking: Human Interaction with AI-Guided Mathematical Discovery
This paper introduces "intentmaking," an iterative process for defining experimental goals when mathematicians interact with AI for discovery.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.