Human-Computer Interaction Papers of the Week

Without a deeper understanding of whether, and in what ways, human and LLM perceptions of visualizations align, there is a real risk of deploying low-quality agents that do not reflect human judgment. We study this question through a pilot experiment - we formulate the problem as a preference task over curated chart pairs and compare the judgments of state-of-the-art vision models with those of a panel of human annotators.

Two foundational aspects of human cognition, abstractness and gender, are typically examined as separable. Here, we find they are systematically linked throughout the entire space of concepts spanning single (N = 40,000) and multi-word expressions (N = 67,000): across billions of words and millions of images on the internet -- and across numerous measurement techniques -- more abstract concepts are more associated with men, an effect which replicates in languages around the world.

Recent advances in computer-use agents (CUAs) enable richer understanding and operation of existing interfaces, while generative UI (GenUI) makes it practical to generate new ones. We examine how these advances expand software modification through a design space of what can be changed and a framework for how modifications can be implemented.

We propose Pandora, a psychotherapy client simulation framework that models how psychological experience becomes situated, individual expression.

We then measure the impact of one vital design space dimension on user comprehension: the number of alternatives displayed. Through a user study (n=48) in the data analysis domain, we find that participants rarely consider alternative paths of their own volition, but AI overreliance reduces when alternative paths are visualized for them.

To identify why, we conducted two experiments with U.S. adults recruited online (total N = 2,193) that removed possible causes one at a time.

The paper at hand proposes an attention-enhanced lightweight Convolutional Neural Network (CNN) architecture for interpretable SLR, exploiting the Convolutional Block Attention Module (CBAM) to improve both classification performance and model transparency.

Inspired by the unified direction introduced by UI-UG, we present UI-UG 2, a compact 4B-parameter multimodal large language model (MLLM) that advances mobile UI Understanding and Generation with broader task coverage, a front-end-aligned taxonomy, and online render-aware reinforcement learning.

We present EmbryoProfiler, a visual analytics system collaboratively developed with embryologists, biologists, and machine learning researchers to support clinicians in visually assessing embryo viability from time-lapse microscopy imagery.

We introduce Human-AI Collaborative Correction, which reframes correction as communicate intent $\rightarrow$ regenerate $\rightarrow$ verify: users express what should change through text, voice, or guided clarification, the AI regenerates the linked dietary record, and users verify the result.

Existing benchmarks predominantly focus on static mental state perception or short-horizon decision-making, overlooking the dynamic mental trajectories inherent in multi-party, multi-turn interactions. To bridge this gap, we introduce M$^3$WME-Bench, a benchmark designed to evaluate mental world modeling conditioned on the evolving actions of interactants.

How do large language models (LLMs) perform gender under zero-shot prompting, and how do people interpret those performances in conversation?

We present a mixed-methods study of 190 TikTok videos tagged with hashtag harassment and their 66,337 comments.

We present a large-scale study (N=200) in which participants experienced one of 10 pieces of 360-degree videos in virtual reality.

We present IMUdrape, which generates garment-mounted virtual IMU data from text through physics-based cloth simulation.

Through this approach we aim to create a community-informed system to close the model data loop, so that AI also enriches data to further enable scientific discovery.

This paper examines the psychological drivers behind Gen Z's willingness to pay (WTP) high emotional premiums for feature-incomplete AI hardware, and investigates how hardware enterprises can leverage proactive retention mechanisms to optimize LTV/CAC ratios and valuation multiples .

We introduce Hybrid Computer Use (HCU), a unified interface for general agents that combines three complementary channels: programmatic interaction through code and command-line tools, semantic interaction through accessibility (AX), and visual interaction through graphical user interfaces (GUI).

This study studies perceptions of inequality in the online simulation game "Whiteout Survival," using semi-structured interviews and think-aloud gameplay walkthrough protocols.

This work shows how collaborative play can foster creative support.