Results 61 to 70 of about 24,277 (306)

The Future of Research in Cognitive Robotics: Foundation Models or Developmental Cognitive Models?

Advanced Robotics Research, EarlyView.
Research in cognitive robotics founded on principles of developmental psychology and enactive cognitive science would yield what we seek in autonomous robots: the ability to perceive its environment, learn from experience, anticipate the outcome of events, act to pursue goals, and adapt to changing circumstances without resorting to training with ...
David Vernon
wiley   +1 more source

A Systematic Literature Review on the Negative Impacts of AI-Generated Virtual Digital Humans

IEEE Access
AI-generated virtual digital humans are profoundly reshaping digital innovation and consumer ecosystems. However, the dynamic evolution of their application scenarios, inherent conceptual ambiguities, and continuously advancing technological features may
Yongzhong Yang, Shihui Li, Shuoli Qiu
doaj   +1 more source

Grounding Large Language Models for Robot Task Planning Using Closed‐Loop State Feedback

Advanced Robotics Research, EarlyView.
BrainBody‐Large Language Model (LLM) introduces a hierarchical, feedback‐driven planning framework where two LLMs coordinate high‐level reasoning and low‐level control for robotic tasks. By grounding decisions in real‐time state feedback, it reduces hallucinations and improves task reliability.
Vineet Bhat, Ali Umut Kaypak, Prashanth Krishnamurthy, Ramesh Karri, Farshad Khorrami   +4 more
wiley   +1 more source

Real-time fMRI neurofeedback modulates induced hallucinations and underlying brain mechanisms

Communications Biology
Hallucinations can occur in the healthy population, are clinically relevant and frequent symptoms in many neuropsychiatric conditions, and have been shown to mark disease progression in patients with neurodegenerative disorders where antipsychotic ...
Herberto Dhanis, Nicolas Gninenko, Elenor Morgenroth, Jevita Potheegadoo, Giulio Rognini, Nathan Faivre, Olaf Blanke, Dimitri Van De Ville   +7 more
doaj   +1 more source

Context and Layers in Harmony: A Unified Strategy for Mitigating LLM Hallucinations

Mathematics
Large language models, despite their strong performance, frequently produce hallucinated content due to excessive reliance on pre-trained knowledge while insufficiently integrating newly provided context.
Sangyeon Yu, Gyunyeop Kim, Sangwoo Kang
doaj   +1 more source

Feature Hallucination for Self-supervised Action Recognition

Understanding human actions in videos requires more than raw pixel analysis; it relies on high-level semantic reasoning and effective integration of multimodal features.
Koniusz, Piotr, Wang, Lei
core   +1 more source

Multimodal Human–Robot Interaction Using Human Pose Estimation and Local Large Language Models

Advanced Robotics Research, EarlyView.
A multimodal human–robot interaction framework integrates human pose estimation (HPE) and a large language model (LLM) for gesture‐ and voice‐based robot control. Speech‐to‐text (STT) enables voice command interpretation, while a safety‐aware arbitration mechanism prioritizes gesture input for rapid intervention.
Nasiru Aboki, Ilche Georgievski, Marco Aiello   +2 more
wiley   +1 more source

Survey and analysis of hallucinations in large language models: attribution to prompting strategies or model behavior

Frontiers in Artificial Intelligence
Hallucination in Large Language Models (LLMs) refers to outputs that appear fluent and coherent but are factually incorrect, logically inconsistent, or entirely fabricated.
Dang Anh-Hoang, Vu Tran, Le-Minh Nguyen
doaj   +1 more source

Dysconnectivity in Hallucinations

, 2018
Abnormalities in brain connectivity are associated with hallucinations. Several networks including sensory and resting-state networks have been pointed out as crucial in various hallucination modalities. Here we review the literature on brain connectivity relevant to auditory verbal and visual hallucinations with an emphasis on the most recent studies.
Ćurčić-Blake, Branislava, Houenou, Josselin, Jardri, Renaud   +2 more
openaire   +2 more sources

LLM‐Integrated Human–Robot Interaction System for Microrobots

Advanced Robotics Research, EarlyView.
This paper proposes an LLM‐based control framework for guiding microrobots using human natural language. This framework can convert the natural human speech into safe and executable command sets for reliable navigation in complex environments. The experimental results show high accuracy and robustness in task performance, demonstrating the potential of
Bairong Zhu, Amar Salehi, Tingting Yu
wiley   +1 more source