ArXiv TLDR
← All categories

Human-Computer Interaction

Research on user interfaces, interaction design, accessibility, and UX.

cs.HC · 436 papers

Mind Modeling: A ToM-Based Framework for Personalization

Mind Modeling introduces a ToM-based framework for personalization by explicitly attributing and continuously updating user mental states from behavior.

2605.10306May 11, 2026Cristina Gena

Useful for Exploration, Risky for Precision: Evaluating AI Tools in Academic Research

AI tools aid early research stages but require human verification due to precision risks, explainability issues, and lack of transparency.

2605.10125May 11, 2026Anthea Dathe, Kiran Hoffmann, Aline Mangold

Explainability of Recurrent Neural Networks for Enhancing P300-based Brain-Computer Interfaces

This paper introduces PRM, an explainable RNN for P300-based BCIs, improving performance by 9% and revealing key spatio-temporal EEG patterns.

2605.10121May 11, 2026Christian Oliva, Vinicio Changoluisa, Francisco B Rodríguez +1

When Are LLM Inferences Acceptable? User Reactions and Control Preferences for Inferred Personal Information

Users are more curious than distressed by LLM inferences about personal data, with acceptability depending on context and third-party use.

2605.10013May 11, 2026Kyzyl Monteiro, Minjung Park, Alexander Ioffrida +6

Sketch-based Access Control: A Multimodal Interface for Translating User Preferences into Intent-Aligned Policies

SBAC is an AI-assisted sketch-based system that simplifies creating and refining access control policies using multimodal LLMs.

2605.10012May 11, 2026Kyzyl Monteiro, Sauvik Das

HapticLDM: A Diffusion Model for Text-to-Vibrotactile Generation

HapticLDM is the first text-to-vibrotactile diffusion model that generates realistic and semantically aligned haptic feedback from text.

2605.09971May 11, 2026Jiahao Xiong, Fei Wang, Anran Xu +4

Insight: Enhancing Mobile Accessibility for Blind and Visually Impaired Users with LLMs

Insight uses LLMs to provide natural language interaction and real-time screen summarization, significantly improving mobile accessibility for BVI users.

2605.09803May 10, 2026Joshua Owusu Ansah, Anuj Kapoor, Ayush Khanna +3

When Sounds Hurt and Voices Aren't Heard: An Experience Report on Misophonia, Sensory Trauma, and Trauma-Informed Design

This paper examines misophonia as sensory and epistemic trauma, urging trauma-informed design to address digital environments and social dismissal.

2605.09796May 10, 2026Tawfiq Ammari

Vibe Econometrics and the Analysis Contract

This paper introduces "vibe econometrics," highlighting how AI-assisted causal analysis democratizes inferential failures and proposes the Analysis Contract to mitigate them.

2605.08071May 8, 2026Lydia Ashton

ECNUClaw: A Learner-Profiled Intelligent Study Companion Framework for K-12 Personalized Education

ECNUClaw is an open-source AI framework creating adaptive study companions using multi-dimensional learner profiles for K-12 education.

2605.08040May 8, 2026Yizhou Zhou, Jiayin Li, Zhi Zhang

Hot Wire 5D+: Evaluating Cognitive and Motor Trade-offs of Visual Feedback for 5D Augmented Reality Trajectories

This paper evaluates AR visual feedback for 5D+ trajectory guidance, revealing cognitive-motor trade-offs and providing design guidelines for novice users.

2605.08008May 8, 2026Christian Masuhr, Julian Koch, Arne Wendt +1

Towards Apples to Apples for AI Evaluations: From Real-World Use Cases to Evaluation Scenarios

A human-centered process transforms real-world AI use cases into consistent evaluation scenarios, enabling "apples-to-apples" comparisons.

2605.07986May 8, 2026Yee-Yin Choong, Kristen Greene, Alice Qian +6

Exploring a Virtual Pet to Provide Context Notifications in a Tourism Recommender System: a Pilot Study

This paper explores using a virtual pet to deliver less intrusive context-aware notifications in tourism recommender systems, improving user acceptance.

2605.07960May 8, 2026Patrícia Alves, Joana Neto, Ana Barreiro +5

Sycophantic AI makes human interaction feel more effortful and less satisfying over time

Sycophantic AI provides immediate emotional support, but over time, it makes human interactions feel less satisfying and more effortful.

2605.07912May 8, 2026Lujain Ibrahim, Franziska Sofia Hafner, Myra Cheng +5

SpatialPrompt: XR-Based Spatial Intent Expression as Executable Constraints for AI Generative 3D Design

SpatialPrompt is an XR system enabling controllable 3D design by converting spatial sketches and voice prompts into executable AI constraints.

2605.07894May 8, 2026Yichen Andy Yu, Wanru Li, Qiaoran Wang +4

A Roadmap of Mixed Reality Body Doubling for Adults with ADHD

This paper introduces a 12-dimension framework for Mixed Reality Body Doubling to aid adults with ADHD, highlighting research gaps.

2605.07851May 8, 2026Valerie Tan, Kimberly Hegemann, Jens Gerken

A Spatial Knowledge Acquisition Comparison Between Digital Visual Thematic Maps, Non-Visual Interactive Text Thematic Maps, and Tables

This study compares digital visual maps, interactive text maps (ITMs), and tables for spatial knowledge acquisition, finding ITMs outperform tables for geographic tasks.

2605.07849May 8, 2026Brandon Biggs, Christopher Toth, James M. Coughlan +1

Analyzing Human Heuristics and Strategies in Everyday Decision-Making Conversations for Conversational AI Design

This paper analyzes human decision-making heuristics in real-world conversations to inform the design of more human-aligned conversational AI.

2605.07789May 8, 2026Sora Kang, Soyun Jeon, Jinsu Eun +4

Splitting User Stories Into Tasks with AI -- A Foe or an Ally?

AI tools can assist in splitting user stories into tasks, improving granularity and completeness, but require human oversight for accuracy.

2605.07320May 8, 2026Luka Pavlič, Reinhard Bernsteiner, Stephan Schlögl +1

Same Brain, Different Prediction: How Preprocessing Choices Undermine EEG Decoding Reliability

EEG decoding reliability is undermined by preprocessing choices, with up to 42% of predictions flipping, necessitating new tools for stability.

2605.07212May 8, 2026Dengzhe Hou, Zihao Wu, Lingyu Jiang +3
PreviousPage 2 of 22Next

📬 Weekly AI Paper Digest

Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.