human–computer interaction
PulseAugur coverage of human–computer interaction — every cluster mentioning human–computer interaction across labs, papers, and developer communities, ranked by signal.
7 day(s) with sentiment data
-
Screencasts proposed as scalable data for AI user emulation
A new approach proposes using continuous screencasts and user input data to train and evaluate AI models designed to emulate individual users. This method aims to capture a user's preferences and knowledge without requi…
-
MyoInteract framework speeds up HCI biomechanics research with RL
Researchers have developed MyoInteract, a new framework designed to accelerate the prototyping of biomechanical human-computer interaction (HCI) tasks using reinforcement learning (RL). This framework significantly redu…
-
New visual analytics tool enhances personalized item ranking creation
Researchers have developed "Ranking Companion," a novel visual analytics system designed to improve the creation of personalized item rankings. This approach addresses the challenge of users lacking domain knowledge or …
-
AI chatbots use dynamic personas to boost human rapport · arXiv paper
Researchers have developed a new method to improve human-AI rapport by generating dynamic in-group personas for chatbots. This approach identifies a user's main concern and personal context, then creates a synthetic per…
-
Chatbots that self-correct errors maintain user trust better, study finds
A new study published on arXiv explores how social chatbots can maintain user trust after making errors. Researchers found that chatbots which self-correct are perceived as more trustworthy and expert than those that re…
-
LLMs Generate Synthetic Ground Truth for Emotion Classification in VR
Researchers have developed a novel method for generating synthetic ground truth data for audio-based emotion classification, particularly within immersive virtual reality environments. This approach utilizes large langu…
-
LLM content moderation system enhances sensitivity to minority speech
Researchers have developed Mod-Guide, an LLM-based system designed to improve content moderation for sensitive speech targeting minority communities. The system focuses on the Hindu and Chakma communities in Bangladesh,…
-
CS Researchers Distrust LLM Leaderboards But Still Use Them
A new study reveals that computer science researchers hold a paradoxical view of Large Language Model (LLM) leaderboards. Despite widespread distrust in their reliability and robustness, researchers continue to use thes…
-
New frameworks boost 3D hand pose estimation for egocentric cameras
Researchers have developed two new frameworks for improving 3D hand pose estimation from egocentric camera views. EgoForce utilizes a differentiable forearm representation and a unified transformer to achieve state-of-t…
-
Study reveals user-LLM interactions stabilize quickly, limiting exploration
A new research paper analyzes 140,000 chatbot sessions from over 7,900 users to understand how user interactions with large language models are shaped over time. The study found that user interaction patterns stabilize …
-
New concept 'knowledge affordance' aims to guide human-AI information seeking
This paper introduces the concept of knowledge affordance (KA) to help agents identify opportunities for information seeking in hybrid human-AI environments. KAs are described as declarative, semantically grounded descr…
-
New ML method trains agents to assess GUI usability, outperforming larger models
Researchers have developed a new machine learning method to train computer use agents (CUAs) for assessing the usability of graphical user interfaces (GUIs). This approach prioritizes key interaction flows, simulates hu…
-
LLMs can adjust work environments to enhance focus and well-being
A new research paper explores how Large Language Models (LLMs) can be used to create more responsive and supportive hybrid work environments. The study, titled "Emotive Architectures," investigates how LLMs like ChatGPT…
-
Generative UI can bridge accessibility gaps in user-generated content platforms
A research paper proposes using generative UI to improve web accessibility, particularly for user-generated content platforms. The paper draws on studies from 2022-2025 involving visually impaired and older adult users …
-
AI prayer systems risk diminishing user authenticity, study finds
Researchers have developed four conceptual value-sensitive AI systems designed to explore the impact of AI on prayer experiences. A diary study revealed that while AI could potentially assist prayer, participants valued…
-
ReFinE plugin bridges HCI research and UI design workflows
Researchers have developed ReFinE, a Figma plugin designed to help UI designers integrate insights from HCI research papers into their workflows. The tool analyzes mockups and surfaces relevant design implications from …
-
Study: AI detection tools may influence writing, but humans still struggle to identify AI-generated text
A recent study explored whether people write differently when they know their AI-assisted text will be scrutinized for AI generation. Researchers found that participants warned about AI detection were more likely to be …
-
OMSCS CS6200 (Introduction to OS) Review and Tips
Eugene Yan has published reviews for several courses within Georgia Tech's Online Master of Science in Computer Science (OMSCS) program. These reviews cover topics ranging from Artificial Intelligence and Machine Learni…