Khalad Hasan

Wenqi Marshall Guo, Qingyun Qian, Khalad Hasan et al.

Over-aligning image generation models to a generalized aesthetic preference conflicts with user intent, particularly when "anti-aesthetic" outputs are requested for artistic or critical purposes. This adherence prioritizes developer-centered values, compromising user autonomy and aesthetic pluralism. We test this bias by constructing a wide-spectrum aesthetics dataset and evaluating state-of-the-art generation and reward models. This position paper finds that aesthetic-aligned generation models frequently default to conventionally beautiful outputs, failing to respect instructions for low-quality or negative imagery. Crucially, reward models penalize anti-aesthetic images even when they perfectly match the explicit user prompt. We confirm this systemic bias through image-to-image editing and evaluation against real abstract artworks. Our code, fine-tuned models, and datasets are available on our meta-expression intentionally anti-aesthetics webpage: https://weathon.github.io/icml2026_position/.

A K M Amanat Ullah, David Ahlström, Khalad Hasan

Large curved displays are ideal for viewing 360 degree content, such as 3D maps, but typically restrict users to a 180 degree viewport, leaving information off-screen. Since users naturally direct their heads toward regions on-screen before interacting, head movements offer a promising alternative for workspace manipulation to bring off-screen content into view. We explore rate control functions (linear, sigmoid, polynomial) and zone control functions (continuous, friction, interrupted, additive) to translate head rotations into workspace control, enabling users to access off-screen content. Polynomial rate control emerges as the best choice, achieving the fastest trial times and highest subjective ratings. Using a map navigation task, our second study demonstrates that users perform better with the polynomial head-based technique than with the industry-standard controller-based methods, click-and-drag and joystick-push, for 360\degree workspace navigation. Based on these findings, we provide guidelines to inform the design of future 360\degree workspace navigation techniques for large curved displays.

Xueshi Lu, Difeng Yu, Hai-Ning Liang et al.

Text entry is a common activity in virtual reality (VR) systems. There is a limited number of available hands-free techniques, which allow users to carry out text entry when users' hands are busy such as holding items or hand-based devices are not available. The most used hands-free text entry technique is DwellType, where a user selects a letter by dwelling over it for a specific period. However, its performance is limited due to the fixed dwell time for each character selection. In this paper, we explore two other hands-free text entry mechanisms in VR: BlinkType and NeckType, which leverage users' eye blinks and neck's forward and backward movements to select letters. With a user study, we compare the performance of the two techniques with DwellType. Results show that users can achieve an average text entry rate of 13.47, 11.18 and 11.65 words per minute with BlinkType, NeckType, and DwellType, respectively. Users' subjective feedback shows BlinkType as the preferred technique for text entry in VR.