4 papers
Learning to Access Computation: Accessibility Plasticity as a Principle of Adaptive Intelligence
Zhaowen Fan
Modern neural networks primarily adapt through parameter modification within predefined computational structures. While recent methods introduce modularity, conditional computation…
Event-Centric World Modeling with Memory-Augmented Retrieval for Embodied Decision-Making
Zhaowen Fan, Rongchao Zhang, Yunxiang Han
Autonomous agents operating in dynamic environments increasingly demand decision-making systems that are both efficient and interpretable. Hence we propose the Event-Retrieve-Actio…
Attention in Geometry: Scalable Spatial Modeling via Adaptive Density Fields and FAISS-Accelerated Kernels
Zhaowen Fan, Yunxiang Han
Spatial computation in geographic systems increasingly requires query-conditioned, local, interpretable aggregation under metric constraints. Many classical approaches rely on glob…
SPIN: Decentralized Swarm Control via Tensorized Policy Coordination
Zhaowen Fan, Yunxiang Han
Decentralized multi-agent swarm coordination remains fundamentally challenged by the combinatorial scaling of joint action spaces and high-overhead training or optimization loops w…