Author

Xiangnan Wu

Observed name: Wu, Xiangnan

Institutions: Chinese Academy of Sciences, Institute of Automation, University of Chinese Academy of Sciences

Observed institutions: Chinese Academy of Sciences, Institute of Automation, University of Chinese Academy of Sciences

OpenAlex ID: A5158753613

AWARE: Action-Entropy-Weighted and Attention-Guided Retrieval of Observation Evidence for Vision-Language-Action Models

2026 · Yang, Jiabing, Chen, Yixiang, et al. · arXiv (Cornell University) · 6

Can World and Action Modeling Benefit Each Other under Unified Causal Training?

2026 · Su, Yue, Lin, Bokai, et al. · arXiv (Cornell University) · 1

Coupling Execution Horizon and Sampling Depth in Flow-Matching VLA Policies

2026 · Yang, Jiabing, Xu, Yuan, et al. · arXiv (Cornell University)

Scaling in Games: Continued Pre-Training For Embodied Agents In Diverse Virtual Worlds

2026 · Zhang, Kuan, Chen, Yukun, et al. · arXiv (Cornell University)

Video-Arena: A Scalable Agentic Video Benchmark for Spatiotemporal Capability

2026 · Zhang, Kuan, Chen, Yukun, et al. · arXiv (Cornell University)

Works count: 5

Citation count: 7

H-index: 1

I10-index: