[Submitted on 24 Sep 2024 (v1), last revised 27 Feb 2025 (this version, v4)] View a PDF of the paper […]
Billion-Scale Time Series Foundation Models with Mixture of Experts Read Post »
[Submitted on 21 Feb 2025 (v1), last revised 27 Feb 2025 (this version, v2)] View a PDF of the paper
A Petri Dish for Studying Chain-of-Thought Learning from In-Context Demonstrations Read Post »
[Submitted on 26 Dec 2024 (v1), last revised 27 Feb 2025 (this version, v2)] View a PDF of the paper
[Submitted on 26 Feb 2025 (v1), last revised 27 Feb 2025 (this version, v2)] View a PDF of the paper
Assessing the True Comprehension Capabilities of LLMs for Multiple Choice Questions Read Post »
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals
A Modular LLM-Enhanced Agent-Based Framework for Realistic Human Trajectory Simulation Read Post »
arXiv:2502.18690v1 Announce Type: new Abstract: In role-playing games (RPGs), the level of immersion is critical-especially when an in-game agent conveys
Hybrid Voting-Based Task Assignment in Role-Playing Games Read Post »
arXiv:2502.18744v1 Announce Type: new Abstract: Recent advancements in Large Language Model (LLM) alignment have sought to mitigate the cost of
arXiv:2502.18725v1 Announce Type: new Abstract: Traditional psychological experiments utilizing naturalistic stimuli face challenges in manual annotation and ecological validity. To
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals
arXiv:2502.19231v1 Announce Type: cross Abstract: The advent of Generative Artificial Intelligence (GAI) has heralded an inflection point that changed how
AI-Powered Bayesian Inference Read Post »