5 papers
COAL: Counterfactual and Observation-Enhanced Alignment Learning for Discriminative Referring Multi-Object Tracking
Shukun Jia, Shiyu Hu, Yipei Wang +3
Referring Multi-Object Tracking (RMOT) faces a fundamental structural contradiction between the high-discriminability demand and the sparse semantic supervision. This mismatch is p…
EduVerse: A User-Defined Multi-Agent Simulation Space for Education Scenario
Yiping Ma, Shiyu Hu, Buyuan Zhu +4
Reproducing cognitive development, group interaction, and long-term evolution in virtual classrooms remains a core challenge for educational AI, as real classrooms integrate open-e…
SOI is the Root of All Evil: Quantifying and Breaking Similar Object Interference in Single Object Tracking
Yipei Wang, Shiyu Hu, Shukun Jia +6
In this paper, we present the first systematic investigation and quantification of Similar Object Interference (SOI), a long-overlooked yet critical bottleneck in Single Object Tra…
When LLMs Learn to be Students: The SOEI Framework for Modeling and Evaluating Virtual Student Agents in Educational Interaction
Yiping Ma, Shiyu Hu, Xuchen Li +4
Recent advances in large language models (LLMs) have enabled intelligent tutoring systems, yet the development of LLM-based Virtual Student Agents (LVSAs) remains underexplored. Su…
FIOVA: A Multi-Annotator Benchmark for Human-Aligned Video Captioning
Shiyu Hu, Xuchen Li, Xuzhao Li +4
Despite rapid progress in large vision-language models (LVLMs), existing video caption benchmarks remain limited in evaluating their alignment with human understanding. Most rely o…