← Search

Lizheng Zu

2 accepted papers

2026

Learning to Decode Against Compositional Hallucination in Video Multimodal Large Language Models

ICML 2026poster

Current research on video hallucination mitigation primarily focuses on isolated error types, leaving *compositional* hallucinations—arising from incorrect reasoning over multiple interacting spatial and temporal factors largely underexplored. We introduce **OmniVCHall**, a benchmark designed to sys…

Cited by 0SourceScholar
2025

Collaborative Tree Search for Enhancing Embodied Multi-Agent Collaboration

CVPR 2025poster

Embodied agents based on large language models (LLMs) face significant challenges in collaborative tasks, requiring effective communication and reasonable division of labor to ensure efficient and correct task completion. Previous approaches with simple communication patterns carry erroneous or inco…

Cited by 0SourcePDFScholar