Publications (10)
Select-then-Solve: Paradigm Routing as Inference-Time Optimization for LLM Agents
Heng Zhou, Zelin Tan, Zhemeng Zhang +15
When an LLM-based agent improves on a task, is the gain from the model itself or from the reasoning paradigm wrapped around it? We study this question by comparing six inference-ti…
ParaTutor: Coordinating Parent and Child Math Tutoring through Role Separated LLM Scaffolding
Lan Luo, Anqi Wang, Muzhi Zhou +4
ParaTutor is an LLM‑driven tutoring system that provides role‑specific scaffolding for parents and children during home math word‑problem sessions, using strategy prompts for paren…
Edu-Theater: A Data-Efficient Agent Framework for Scalable Learner Behavior Simulation through Staging Roll-Call
Weibo Gao, Qi Liu, Linan Yue +6
Large-scale learner-task interaction data are crucial for intelligent educational systems but are costly to collect and constrained by privacy and learner engagement. Learner simul…
Interoperability of the Metaverse: A Digital Ecosystem Perspective Review
Liang Yang, Shi-Ting Ni, Yuyang Wang +3
The Metaverse is at the vanguard of the impending digital revolution, with the potential to significantly transform industries and lifestyles. However, in 2023, skepticism surfaced…
BridgeDiff: Bridging Human Observations and Flat-Garment Synthesis for Virtual Try-Off
Shuang Liu, Ao Yu, Linkang Cheng +5
Virtual try-off (VTOFF) aims to recover canonical flat-garment representations from images of dressed persons for standardized display and downstream virtual try-on. Prior methods…
Reading Seeing: Diagnosing and Closing the Typography Gap in Vision-Language Models
Heng Zhou, Ao Yu, Li Kang +5
Vision-Language Models achieve near-perfect accuracy at reading text in images, yet prove largely typography-blind: capable of recognizing what text says, but not how it looks. We…
LiveSearchBench: An Automatically Constructed Benchmark for Retrieval and Reasoning over Dynamic Knowledge
Heng Zhou, Ao Yu, Yuchen Fan +10
Evaluating large language models (LLMs) on question answering often relies on static benchmarks that reward memorization and understate the role of retrieval, failing to capture th…
Toward Site-Aware MR Art Exhibitions: A SLAM-Based Deployment Pipeline for Spatial Coherence and Exhibition Experience
Yawei Zhao, Yuming Zhu, Hao Li +4
Mixed Reality (MR) is increasingly being used in exhibition settings to bring digital artworks into relation with the physical environment. However, existing MR exhibition systems…
Exploring LLM-Powered Role and Action-Switching Pedagogical Agents for History Education in Virtual Reality
Zihao Zhu, Ao Yu, Xin Tong +1
Multi-role pedagogical agents can create engaging and immersive learning experiences, helping learners better understand knowledge in history learning. However, existing pedagogica…
Ego to World: Collaborative Spatial Reasoning in Embodied Systems via Reinforcement Learning
Heng Zhou, Li Kang, Yiran Qin +12
Understanding the world from distributed, partial viewpoints is a fundamental challenge for embodied multi-agent systems. Each agent perceives the environment through an ego-centri…