Too Human or Not Enough? User Preferences for AI Error Recovery Messages
14th Nordic Conference on Human-Computer Interaction (NordiCHI 2026)
Publications
Papers, tech notes, and highlights from our focus areas - LLM efficiency, AI memory, human–computer interaction, and 3D generation.
Evaluating the Applicability of LLM Inference Optimizations on Apple Silicon
On-Device Intelligence: Foundation Models under Real-World Constraints (ODI) @ NeurIPS 2026
Rigid 3D Object Alignment: Optimization vs. Feed-Forward Prediction
7th Workshop on Open-World 3D Scene Understanding and Representations (OpenSUN3D) @ ECCV 2026
GenRA: End-to-end Framework for LLM-Driven Animation of Rigged 3D Models
7th Workshop on Open-World 3D Scene Understanding and Representations (OpenSUN3D) @ ECCV 2026
Memory Belongs to the User: Portable Memory, an Open Standard Proposal for Cross-Vendor AI Memory
MacArena: Benchmarking Computer Use Agents on an Online macOS Environment
2nd AIWILD Workshop @ ICML 2026
Help, Don’t Control: Measuring User Emotional Background in AI Assistant Interaction
Conversational AI: Agency and Identities 2026
Composable AI Pipelines: Write Intent, Not Infrastructure
GUIrilla: A Scalable Framework for Automated Desktop UI Exploration
3rd DATA-FM Workshop @ ICLR 2026
Fast-dLLM on MLX: Training-Free Acceleration for Diffusion Language Models on Apple Silicon
Do Our Design Principles Ever Really Change, or Do We Just Change the Methods of Achieving Them?
The International Conference on Computer Graphics, Interaction, Visualization Theory and Applications (GRIVAPP 2026)
Best Poster Award
GLiNER2 for Swift: Unified Schema-Based Information Extraction on Apple Silicon
Demonstrating Headphone-Sensed, Accessibility-Informed Head Pointing with Snapping for Inclusive Interaction
Deep Language Geometry: Constructing a Metric Space from LLM Weights
RANLP 2025 Recent Advances in Natural Language Processing
Screen2AX: Vision-Based Approach for Automatic macOS Accessibility Generation
Measure Twice, Cut Once: the Best* Way to Calculate macOS File Hierarchy Size
Mousetraps: Reliably distinguishing free apps and trial versions of paid macOS apps on public app marketplaces
SwiftEval: Developing a Language-Specific Benchmark for LLM-generated Code Evaluation
FORGE 2025 The 2nd ACM International Conference on AI Foundation Models and Software Engineering
Towards Generating App Feature Descriptions Automatically with LLMs: the Setapp Case Study
FORGE 2025 The 2nd ACM International Conference on AI Foundation Models and Software Engineering
Case Study: Using EEG to Assess Cognitive Load in Infinite Interfaces
HCI 2025 27TH International Conference on Human-Computer Interaction
Datasets: Inside Mac App Store Applications Metadata
R+R: State of the Application Sandboxing on macOS: A Differentiated Replication
Evaluating a multi-method approach for user emotional dynamics assessment in Software UX
Position Paper: Think Globally, React Locally — Bringing Real-time Reference-based Website Phishing Detection on macOS
STAST'24, 14th International Workshop on Socio-Technical Aspects in Security, Affiliated with the 9th IEEE European Symposium on Security and Privacy