← Search

Zhaodong Wang

2 accepted papers

2025

LayerDAG: A Layerwise Autoregressive Diffusion Model for Directed Acyclic Graph Generation

ICLR 2025spotlight

Directed acyclic graphs (DAGs) serve as crucial data representations in domains such as hardware synthesis and compiler/program optimization for computing systems. DAG generative models facilitate the creation of synthetic DAGs, which can be used for benchmarking computing systems while preserving i…

2020

Efficient Deep Reinforcement Learning via Adaptive Policy Transfer

IJCAI 2020poster

Transfer learning has shown great potential to accelerate Reinforcement Learning (RL) by leveraging prior knowledge from past learned policies of relevant tasks. Existing approaches either transfer previous knowledge by explicitly computing similarities between tasks or select appropriate source pol…