human-computer-interaction

Tag

Cards List
#human-computer-interaction

Intuitive equals familiar

Lobsters Hottest ↗ · 2026-09-28

This paper investigates the equivalence between intuitive and familiar design in human-computer interaction.

0 favorites 0 likes
#human-computer-interaction

Relevance Does Not Imply Applicability: Experience Activation for Personal GUI Agents

Hugging Face Daily Papers ↗ · 2026-09-27 Cached

提出了 ExpActivator,一个免训练框架,通过在冻结的 GUI 骨干网络的潜在空间中匹配当前屏幕与历史状态,仅激活与当前情境相关的经验,而非盲目追加任务相关历史;在四个 GUI 骨干网络上将轨迹内步骤成功率平均提升 28%,同时仅使用约五分之一的历史 token。

0 favorites 0 likes
#human-computer-interaction

DataMagic: Authoring Data Videos through Declarative Multi-Agent Orchestration

Hugging Face Daily Papers ↗ · 2026-09-27 Cached

DataMagic introduces a declarative multi-agent orchestration framework (DVSpec) that turns raw tabular data into narrated data videos, improving quality from 2.13/5 to 3.89/5 over GPT-5 baselines and cutting task time by 79.7% in user studies.

0 favorites 0 likes
#human-computer-interaction

"AI Is Turning Too Human": How Teenagers Experience and Negotiate AI in Everyday Life

arXiv cs.CL ↗ · 2026-09-24 Cached

This paper examines how teenagers experience and negotiate AI's increasingly human-like characteristics in their daily lives, focusing on societal and ethical implications.

0 favorites 0 likes
#human-computer-interaction

Training Intelligent Voice Assistant Wakeup with Controllable Synthetic Conversations

arXiv cs.AI ↗ · 2026-09-24 Cached

This paper introduces an intelligent wake-up system for virtual assistants that uses contextual trigger detection and synthetic conversational data to improve natural interactions. The authors release code, a dataset, and trained models to promote reproducibility.

0 favorites 0 likes
#human-computer-interaction

Building Socio-Affective Artificial Intelligence for Interactive Multi-Agent Simulations

arXiv cs.AI ↗ · 2026-09-24 Cached

This paper presents design principles and the 'AGIMUD' software for enabling socio-affective interactions between humans and multiple AI agents in simulated dynamic worlds, leveraging generative AI and distributed processing.

0 favorites 0 likes
#human-computer-interaction

@LinusEkenstam: This will create cambrian explosion in HCI forever.

X AI KOLs Following ↗ · 2026-09-22 Cached

This tweet thread claims that Brain-Computer Interface (BCI) technology will cause a 'cambrian explosion' in Human-Computer Interaction (HCI), detailing the development of a wearable BCI and the training of a brain foundation model.

0 favorites 0 likes
#human-computer-interaction

Why do computers look like this anyway?

Lobsters Hottest ↗ · 2026-09-21 Cached

The desktop GUI evolved from military radar research through Engelbart's demos to Xerox PARC's development, before Apple commercialized it with the Macintosh, establishing the standard interface still used today.

0 favorites 0 likes
#human-computer-interaction

Gricea: An Open Science Platform for Conversational AI Research

Hugging Face Daily Papers ↗ · 2026-09-18 Cached

Gricea is an open-science platform for conversational AI research that enables configurable and deployable research artifacts to support replication, extension, and cumulative knowledge building.

0 favorites 0 likes
#human-computer-interaction

Learning to Refer from Estimated Listener Gaze

arXiv cs.CL ↗ · 2026-09-15 Cached

This paper proposes a method to enhance referring expression generation in vision-language models by leveraging listener gaze data for training, leading to more efficient and successful communication.

0 favorites 0 likes
#human-computer-interaction

The House with a Million Windows: Interactive Fiction for Narrative Restorying

arXiv cs.CL ↗ · 2026-09-14 Cached

The House with a Million Windows is an LLM-based interactive fiction system designed to help users explore and reinterpret personal stories through narrative restorying, addressing meaning flattening in AI-assisted writing.

0 favorites 0 likes
#human-computer-interaction

@OpenAI: "Put That There" clip courtesy of MIT Media Laboratory, Chris Schmandt, and Eric Hulteen.

X AI KOLs ↗ · 2026-09-03

OpenAI shared a clip titled 'Put That There' credited to MIT Media Laboratory, Chris Schmandt, and Eric Hulteen, likely showcasing a historical or research-related demonstration in AI or HCI.

0 favorites 0 likes
#human-computer-interaction

@MaximeRivest: Writing as an input device is here.

X AI KOLs Timeline ↗ · 2026-08-25 Cached

The tweet announces that writing can now be used as an input device, indicating a potential advancement in technology interaction.

0 favorites 0 likes
#human-computer-interaction

Language as a Material Interface for Creative LLM Interaction

arXiv cs.CL ↗ · 2026-07-29 Cached

This paper explores how creative practitioners use language as a material interface for interacting with LLMs, through a two-week study with a tangible device called the Memetic Mixer.

0 favorites 0 likes
#human-computer-interaction

How Does Empowering Users with Greater System Control Affect News Filter Bubbles?

arXiv cs.AI ↗ · 2026-07-20 Cached

This paper investigates how providing users with transparency and control over a political news recommendation system affects filter bubbles. A user study found that the enhanced interface increased awareness of filter bubbles but had heterogeneous effects on news consumption diversity.

0 favorites 0 likes
#human-computer-interaction

A Graph Neural Network Model for Real-Time Gesture Recognition Based on sEMG Signals

arXiv cs.AI ↗ · 2026-07-10 Cached

This paper introduces a graph neural network model for real-time hand gesture recognition using surface electromyography (sEMG) signals from the forearm. The method achieves 99% classification accuracy with an average processing time of 48ms on an M1 Pro CPU, outperforming existing state-of-the-art techniques.

0 favorites 0 likes
#human-computer-interaction

LUMOS: A Semantic Operating-System Layer for Accessibility-Grounded AI Agents

Hugging Face Daily Papers ↗ · 2026-06-29 Cached

LUMOS introduces a semantic interaction layer that converts operating system metadata into machine-readable formats, enabling AI agents to interact with computer interfaces more efficiently by reducing dependence on screenshots and visual methods.

0 favorites 0 likes
#human-computer-interaction

GUI vs. CLI: Execution Bottlenecks in Screen-Only and Skill-Mediated Computer-Use Agents

arXiv cs.AI ↗ · 2026-06-24 Cached

This paper investigates execution bottlenecks in computer-use agents, comparing screen-only GUI-based approaches with skill-mediated CLI-based methods, identifying key performance differences.

0 favorites 0 likes
#human-computer-interaction

Indirect Computing Model with Indirect Formal Method

arXiv cs.CL ↗ · 2026-06-15 Cached

This paper proposes an indirect computing model and indirect formal method for optimizing cloud computing, using Chinese information data as an example to transition from data centers to knowledge centers.

0 favorites 0 likes
#human-computer-interaction

Explain Like I'm 5 or Whatever I Choose: Evaluating the Interactive Potential of Language Model Responses

arXiv cs.CL ↗ · 2026-06-08 Cached

This paper proposes a framework for evaluating LLMs' ability to generate multiple responses to scientific queries at different language complexity levels. The study finds that models often vary complexity inconsistently, with Claude Sonnet 4.5 performing best but only shifting complexity correctly 46% of the time.

0 favorites 0 likes
← Previous
Next →
← Back to home

Submit Feedback