Latest Articles for Human-Computer Interaction

A new method improves how machines comprehend long videos.

Understanding human factors is key to developing safe automated vehicles.

Exploring the impact of long-term memory on conversational agents.

This study tests LLMs to reveal their weaknesses in understanding and reasoning.

This study evaluates language models' abilities in understanding thoughts and feelings.

A new approach enhances language models by focusing on human preferences in text generation.

A new method enables agents to follow safety rules in plain language.

Preference Flow Matching offers a new way to align AI outputs with user preferences.

A new system improves robot interactions by filtering overlapping speech.

Research shows non-humanoid agents can analyze human dance and create movements in sync with music.

This study examines how explanation attributes impact human decision-making with AI.

A new training method enhances how language models express certainty in answers.

A new method improves reward models using synthetic critiques for better alignment.

A new method improves language models by learning from real-time data.

A new method enhances trust and decision-making for AI-assisted advice.

Researchers enhance program synthesis systems for better understanding user needs.

New methods enhance machine understanding of dynamic interactions in video content.

Examining AI's struggle with honesty and its impact on user trust.

New methods improve head pose estimation for better accuracy in real-world settings.

A framework to enhance neural networks by integrating human knowledge into learning algorithms.

Examining how machine learning affects human choices and outcomes.

Examining how machines can learn to combine known concepts effectively.

New model improves predictions of object interactions using videos and images.

This article discusses role-playing and personalization in language models.

Examining over-optimization in DAAs and its impact on model performance.

Innovative approach to guide large language models using self-assessment.

New methods improve how machines recognize emotions in speech.

Research examines the link between AI explanations and user trust.

This study examines how language models perform language tasks similar to humans.

Synthetic dataset Hi5 improves hand pose recognition with diverse images.

Evaluating LLMs' strategic reasoning capabilities using diverse games.

This article reviews how language models perform in spatial reasoning tasks.

A new approach enhances language model alignment using limited human-annotated data.

A new method to develop adaptable agents using diverse environments.

A new method to assess commonsense reasoning in AI models through open-ended tasks.

This article examines how language models create and relate concepts to understanding.

Introducing BLSP-Emo, a model that understands speech and emotions for better interactions.

Systems must consider human values in decision-making for fair outcomes.

This article examines how LLMs understand human beliefs and feelings.

EDEN connects emotion recognition with cause analysis for better dialogue understanding.