4 papers
NarrativeSteward: Coordinating Delegation, Guidance, and Verification in Agent-Assisted Interactive Narrative Authoring
Wenjin Wang, Jiazhen Lei, Yuxin Sha +6
Autonomous AI agents can turn authors' goals into interactive narratives by independently organizing and carrying out generation and revision. As agents generate and revise extensi…
MAIN-VLA: Modeling Abstraction of Intention and eNvironment for Vision-Language-Action Models
Zheyuan Zhou, Liang Du, Zixun Sun +5
Despite significant progress in Visual-Language-Action (VLA), in highly complex and dynamic environments that involve real-time unpredictable interactions (such as 3D open worlds a…
OIG-Bench: A Multi-Agent Annotated Benchmark for Multimodal One-Image Guides Understanding
Jiancong Xie, Wenjin Wang, Zhuomeng Zhang +5
Recent advances in Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities. However, evaluating their capacity for human-like understanding in One-Image…
Stable Heterogeneous Treatment Effect Estimation across Out-of-Distribution Populations
Yuling Zhang, Anpeng Wu, Kun Kuang +3
Heterogeneous treatment effect (HTE) estimation is vital for understanding the change of treatment effect across individuals or subgroups. Most existing HTE estimation methods focu…