Robotics Research (United States)

Multi-Bin Batching for Increasing LLM Inference Throughput

As large language models (LLMs) grow in popularity for their diverse capabilities, improving the efficiency of their inference systems has become increasingly critical. Batching LLM requests is a critical step in scheduling the inference jobs on servers (e.g. GPUs), enabling the...

Structure‐Engineered Nanoporous Vanadium Oxide Memristors for Reconfigurable Synapse–Neuron Integration and Synergistic Robotic Motion

ABSTRACT Neuromorphic sensory‐to‐motor interfaces require compact devices that can combine nonvolatile synaptic weight storage with volatile neuronal firing, yet these functions typically rely on distinct material and circuit mechanisms. Here, we report a structure‐engineered VO...

Magnetoelectric BaTiO 3 /CoFe 2 O 4 Thin‐Film Meshes for Neuronal Differentiation

ABSTRACT Magnetoelectric composites offer a powerful route for remotely converting magnetic stimuli into local electrical cues, with promising biomedical applications in electrical stimulation. In strain‐mediated magnetoelectric heterostructures, however, efficient coupling depen...