Applied & Human-Centered · Computer Science & AI
Human-Computer Interaction
The newest papers in Human-Computer Interaction that ReadSearch has read, newest first. Each links to its own page, with its authors, date, where it was published and the original.
1,000 papers, from 31 August 2026 to 5 November 2026: 993 arXiv preprints and 7 OpenAlex records.
Get the few papers worth your time in Human-Computer Interaction every morning.
Follow Human-Computer Interaction and ReadSearch reads its new papers each day, then brings you the few worth reading, each with its key finding in a sentence.
Newest papers, page 27
SpheriColor: Colormaps for Spherical Geospatial Input Topographies
Multivariate geospatial data visualization often relies on multiple coordinated views, where color can be used to either link views or encode data attributes.Design Creativity Bench: Measuring creativity in LLM-Generated UI
As leading LLMs improve on capability evaluations, their limitations in producing creative outputs on design tasks remain insufficiently characterised.NeuroDivSim: An Interactive Tool for Model-Based Reflection on Cognitive Diversity in Interface Design
Recent approaches to simulated and synthetic users offer new ways to support design, but raise questions about how computational representations of users should contribute to design practice.From Surface to Depth: Towards Cognitive Appraisal Reasoning in Multimodal Emotion Understanding
Recent multimodal large language models (MLLMs) increasingly incorporate explainable reasoning for emotion understanding."Hot-Blooded" vs "Cold-Blooded": Simulating the Behavioral Phenotypes of Childhood Aggression via Generative Agents
This study examines the construct validity of LLM-based generative agents in simulating reactive, proactive, and co-occurring aggression in children.Hybrid Cinematography: Previsualizing and Managing Hallucination Risk in Generative Video Reshooting
On a film set, the camera move is committed during a take.Structural and Representational Agency in LLM-Driven Timbre Generation and Interpolation
Generative creative interfaces routinely report the user's position within a space of possibilities.r/ADHD: Community-Based Understandings of Time Management Challenges in Digital Environments
Community accounts of ADHD can complement clinical understandings by foregrounding members' own definitions of time-management difficulties and support.Incremental Retrieval-Augmented Generation for Human-in-the-Loop Decision Support
We introduce iRAG, a human-in-the-loop decision-support system combining Retrieval-Augmented Generation (RAG) with Hybrid Decision-Making.Activating the Annotator: Operationalising Lived Experience in Data Annotation
Perspectivist NLP has established that annotator positionality shapes labels for subjective tasks, but the field still lacks methods for operationalising it.Bridging Human and Model Attention: Explainability Analysis of CNN, Mamba, and ViT Architectures with Gaze-Based Validation
High-risk applications of deep learning require precise characterization of model decision-making.AssemblyLens: Exploring the Role of Structural Roadmaps and Strategies of Furniture Assembly Used by Blind and Low Vision Individuals
Instructions to assemble flat-packed furniture rely on visuals, making them inaccessible to Blind and Low Vision (BLV) individuals.Generative AI Steering and Human Authoring: Complementary Search-as-Learning Scaffolds in Cross-Session Aggregated Academic Search
Aggregated academic search interfaces combine resources from heterogeneous sources, such as scholarly libraries and reference encyclopedias, into a single workspace.Reading Position Is the Baseline to Beat: A Time-Ordered Evaluation of Personalised Highlight Prediction
A reader's first highlights on a page are the cheapest personal signal a reading product has.AI-Assisted Submissions in Online Research Are Rare and Highly Concentrated but Routinely Approved
Online research platforms underpin much of what science claims about people, on the assumption that a human produced each response.Beyond Activation: Gaze Invocation with Visible Status for an Embodied AR Assistant in Co-Located Collaboration
Wake words face an inherent trade-off: higher sensitivity reduces missed commands but increases accidental activations.Many Brains, One Geometry: A Shared Visual-Semantic Space for Cross-Dataset fMRI Decoding
Visual decoding from fMRI is typically siloed by participant and experiment, obscuring whether heterogeneous neural measurements can be organized within a common computational geometry.The Confidence Game: Strategic Miscalibration in Human-AI Delegation
Calibrated uncertainty quantification is essential to ensuring AI agents are trustworthy and reliable.TutorLoop: Regulating Student Learning Behaviors via Sensor-in-the-Loop Generative Feedback
We present TutorLoop, a sensor-in-the-loop system that regulates student learning behaviors by delivering adaptive feedback based on real-time cognitive states.Before Bringing It Up: When and How AI Companions Should Use Memory
Memory can sustain AI companionship, yet even accurate recollection can be inappropriate to use.