Dayong Liang — accepted AI-conference papers

2026

Multi-Agent Undercover Gaming: Hallucination Removal Through Counterfactual Test for Multimodal Reasoning

Dayong Liang, Xiao-Yong Wei, Changmeng Zheng

AAAI 2026technical

Hallucination continues to pose a major obstacle in the reasoning capabilities of large language models (LLMs). Although the Multi-Agent Debate (MAD) paradigm offers a promising solution by promoting consensus among multiple agents to enhance reliability, it relies on the unrealistic assumption that

Cited by 0 Source ↗PDF ↗Scholar ↗

2019

An Object Attribute Guided Framework for Robot Learning Manipulations from Human Demonstration Videos

Qixiang Zhang, Junhong Chen, Dayong Liang, Huaping Liu, Xiaojing Zhou, Zihan Ye +1

IROS 2019poster

Learning manipulations from videos is an inspiriting way for robots to acquire new skills. In this paper, we propose a framework that can generate robotic manipulation plans by observing human demonstration videos without special marks or unnatural demonstrated behaviors. More specifically, the fram…

Cited by 4 Source ↗Scholar ↗