10 papers
ReMAP: Neural Reparameterization for Scalable MAP Inference in Arbitrary-Order Markov Random Fields
Yaomin Wang, Chaolong Ying, Xiaodong Luo +1
Scalable high-quality MAP inference in arbitrary-order Markov Random Fields (MRFs) remains challenging. Approximate message-passing methods are often efficient but can degrade on d…
Neural Graduated Assignment for Maximum Common Edge Subgraphs
Chaolong Ying, Yingqi Ruan, Xuemin Chen +2
The Maximum Common Edge Subgraph (MCES) problem is a crucial challenge with significant implications in domains such as biology and chemistry. Traditional approaches, which include…
UM3: Unsupervised Map to Map Matching
Chaolong Ying, Yinan Zhang, Lei Zhang +3
Map-to-map matching is a critical task for aligning spatial data across heterogeneous sources, yet it remains challenging due to the lack of ground truth correspondences, sparse no…
Learning What to Trust: Bayesian Prior-Guided Optimization for Visual Generation
Ruiying Liu, Yuanzhi Liang, Haibin Huang +2
Group Relative Policy Optimization (GRPO) has emerged as an effective and lightweight framework for post-training visual generative models. However, its performance is fundamentall…
TEMPO: Temporal Multi-scale Autoregressive Generation of Protein Conformational Ensembles
Yaoyao Xu, Di Wang, Zihan Zhou +2
Understanding the dynamic behavior of proteins is critical to elucidating their functional mechanisms, yet generating realistic, temporally coherent trajectories of protein ensembl…
Secrets of GFlowNets' Learning Behavior: A Theoretical Study
Tianshu Yu
Generative Flow Networks (GFlowNets) have emerged as a powerful paradigm for generating composite structures, demonstrating considerable promise across diverse applications. While…