[HTML][HTML] Knowledge-Empowered, Collaborative, and Co-Evolving AI Models: The Post-LLM Roadmap

F Wu, T Shen, T Bäck, J Chen, G Huang, Y **… - Engineering, 2024 - Elsevier
Large language models (LLMs) have significantly advanced artificial intelligence (AI) by
excelling in tasks such as understanding, generation, and reasoning across multiple …

Donald Trumps in the Virtual Polls: Simulating and Predicting Public Opinions in Surveys Using Large Language Models

S Jiang, L Wei, C Zhang - arxiv preprint arxiv:2411.01582, 2024 - arxiv.org
In recent years, large language models (LLMs) have attracted attention due to their ability to
generate human-like text. As surveys and opinion polls remain key tools for gauging public …

Minions: Cost-efficient Collaboration Between On-device and Cloud Language Models

A Narayan, D Biderman, S Eyuboglu, A May… - arxiv preprint arxiv …, 2025 - arxiv.org
We investigate an emerging setup in which a small, on-device language model (LM) with
access to local data communicates with a frontier, cloud-hosted LM to solve real-world tasks …

Performance evaluation of machine learning models for automated ticket routing systems (DistilBERT, DistilRoBERTa, XLM-RoBERTa)

E DUMBRĂVEANU - 2025 - repository.utm.md
This thesis focuses on the review and performance testing of machine learning models for
automated ticket routing systems, an essential instrument for raising customer satisfaction …

[PDF][PDF] System-2 as a Recurrent System-1 Assisted Multi-Token Autoregressive Predictor: A GenAI Reasoning Approach

DP Ghosh, DA Team - researchgate.net
This paper presents a novel AI framework that emulates human cognitive flexibility by
integrating fast, intuitive processing (System-1) with slow, analytical reasoning (System-2) …