Models

14 stories in Models.

  1. Models category illustration

    Small Open-Weight Language Models for Crowd Decision-Making: Capabilities and Limits of Output-Level Fusion and Linguistic Aggregation (opens the original at arxiv.org in a new tab)

    Small open-weight language models can run crowd decision-making (CDM) on an institution's own infrastructure, which keeps the checkpoint, the inference settings and the opinions under its control.

  2. Models category illustration

    Exploring faster language models suited to hardware implementation using reservoir computing (opens the original at techxplore.com in a new tab)

    Large language models have transformed natural language processing through their ability to generate and interpret humanlike text. Most modern language models rely on transformer architectures, whose self-attention mechanisms provide powerful capabilities for learning relationships within long sequences. However, training and running these models can require substantial computational resources and energy, creating challenges for their wider use in embedded systems, edge devices and other environments where computing resources are limited.