Yibin Wang

Papers

Total Citations

H-Index

About

Yibin Wang is a rising researcher in artificial intelligence and machine learning, with a primary focus on decision-making systems and generative modeling. Their most cited work, "Behavior Generation with Latent Actions" (2024), tackles a fundamental challenge in AI: generating complex, multimodal behaviors from labeled datasets. Unlike language or image generation, decision-making requires modeling continuous-valued action vectors that are inherently multimodal and often drawn from uncurated sources. Wang's contribution lies in developing a framework that learns latent action representations, enabling more robust and flexible behavior generation across diverse tasks. This work has already garnered 3 citations in its first year, signaling growing interest in their approach. Wang's research bridges generative AI and reinforcement learning, addressing critical gaps in how machines learn to act in complex environments. Their work is particularly relevant for applications in robotics, autonomous systems, and interactive AI, where generating realistic, context-aware behaviors is essential. As an early-career researcher, Wang is establishing a reputation for tackling hard problems at the intersection of generative modeling and decision theory, with potential to influence how AI systems learn from demonstration and interact with the world.