Results 51 to 60 of about 81,815 (304)
LLM Critics Help Catch LLM Bugs
Reinforcement learning from human feedback (RLHF) is fundamentally limited by the capacity of humans to correctly evaluate model output. To improve human evaluation ability and overcome that limitation this work trains "critic" models that help humans to more accurately evaluate model-written code. These critics are themselves LLMs trained with RLHF to
McAleese, Nat +5 more
openaire +2 more sources
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 multi-dimensional concept for evaluating NLP-based robots in healthcare scenarios
Current Directions in Biomedical EngineeringBackground: In the past decades, robots have transformed the healthcare sector by supporting clinical staff in various tasks. Applications of range from robot-supported surgical interventions and imaging, via healthcare logistics to cleaning and social ...
Wittenberg Thomas +7 more
doaj +1 more source
Editorial Introduction to Issue 40 of CSIMQ: Managing Different Forms of Complexity
Complex Systems Informatics and Modeling QuarterlyThe systems considered in the presented research can be characterized as dynamically complex open systems, which means that “the system’s coherence lies not only within the system itself but also in its relationship with the environment”.
Małgorzata Pańkowska, Erika Nazaruka
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 +4 more
wiley +1 more source
Bio-inspired analog parallel array processor chip with programmable spatio-temporal dynamics [PDF]
, 2002 A bio-inspired model for an analog parallel array processor (APAP), based on studies on the vertebrate retina, permits the realization of complex spatio-temporal dynamics in VLSI.
Carmona Galán, Ricardo +4 more
core +1 more source
Set-LLM: A Permutation-Invariant LLM
While large language models (LLMs) demonstrate impressive capabilities across numerous applications, their robustness remains a critical concern. This paper is motivated by a specific vulnerability: the order sensitivity of LLMs. This vulnerability manifests itself as the order bias observed when LLMs decide between possible options (for example, a ...
Egressy, Beni, Stühmer, Jan
openaire +2 more sources
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 +2 more
wiley +1 more source
Advanced Science, EarlyView.We introduce AutomataGPT, a generative pretrained transformer (GPT) trained on synthetic spatiotemporal data from 2D cellular automata to learn symbolic rules. Demonstrating strong performance on both forward and inverse tasks, AutomataGPT establishes a scalable, domain‐agnostic framework for interpretable modeling, paving the way for future ...
Jaime A. Berkovich +2 more
wiley +1 more source