4 papers
Development of the RIOT 2 for use in LA-supported classrooms
Gina M. Quan, Cassandra Paul, Nithin Keshavamurthy +3
This paper describes the development of the RIOT 2, an observational tool that can be used to study classrooms in which there are multiple members of an instructional team. The RIO…
FaithCoT-Bench: Benchmarking Instance-Level Faithfulness of Chain-of-Thought Reasoning
Xu Shen, Song Wang, Zhen Tan +5
Large language models (LLMs) increasingly rely on Chain-of-Thought (CoT) prompting to improve problem-solving and provide seemingly transparent explanations. However, growing evide…
Geometry- and Relation-Aware Diffusion for EEG Super-Resolution
Laura Yao, Gengwei Zhang, Moajjem Chowdhury +2
Recent electroencephalography (EEG) spatial super-resolution (SR) methods, while showing improved quality by either directly predicting missing signals from visible channels or ada…
Metacognitive Self-Correction for Multi-Agent System via Prototype-Guided Next-Execution Reconstruction
Xu Shen, Qi Zhang, Song Wang +8
Large Language Model based multi-agent systems (MAS) excel at collaborative problem solving but remain brittle to cascading errors: a single faulty step can propagate across agents…