Tag
This paper investigates the lack of standardized reporting on computational and environmental costs of LLMs in AIED research, reviewing 396 AIED 2025 papers and proposing an open-source method to measure and report these impacts.
This paper evaluates LLM-based coding agents (Claude Code and Codex) in social science analysis, finding they match or exceed human methodological diversity while remaining vulnerable to interpretation bias through verdict-layer manipulation.
A Zhejiang University researcher shared a comprehensive PhD guide on GitHub, covering the entire research lifecycle from topic selection to rebuttals, specifically tailored for the 3D Vision direction.