Author name cluster

Zerun Li

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

2 papers

1 author row

AAAI Conference 2026 Conference Paper

Efficient Diffusion Planning with Temporal Diffusion

Jiaming Guo
Rui Zhang
Zerun Li
Yunkai Gao
Shaohui Peng
Siming Lan
Xing Hu
Zidong Du

Diffusion planning is a promising method for learning high-performance policies from offline data. To avoid the impact of discrepancies between planning and reality on performance, previous works generate new plans at each time step. However, this incurs significant computational overhead and leads to lower decision frequencies, and frequent plan switching may also affect performance. In contrast, humans might create detailed short-term plans and more general, sometimes vague, long-term plans, and adjust them over time. Inspired by this, we propose the Temporal Diffusion Planner (TDP) which improves decision efficiency by distributing the denoising steps across the time dimension. TDP begins by generating an initial plan that becomes progressively more vague over time. At each subsequent time step, rather than generating an entirely new plan, TDP updates the previous one with a small number of denoising steps. This reduces the average number of denoising steps, improving decision efficiency. Additionally, we introduce an automated replanning mechanism to prevent significant deviations between the plan and reality. Experiments on D4RL show that, compared to previous works that generate new plans every time step, TDP significantly improves the decision-making frequency by 11-24.8 times while achieving higher or comparable performance.

PDF Details DOI

EAAI Journal 2025 Journal Article

Statistical significance of cluster membership for categorical data

Lianyu Hu
Zerun Li
Junjie Dong
Mudi Jiang
Zengyou He

Clustering algorithms partition data samples into distinct groups in an unsupervised manner, which requires subsequent validation. In post-hoc cluster analysis, clustering quality is typically evaluated at the cluster level, with a focus on metrics such as intra- and inter-cluster distances. However, evaluation at the sample level (i. e. , cluster membership) is often overlooked. To assess whether a given sample is correctly assigned to its respective cluster, it is crucial to consider the inevitable effects of random assignments or noisy samples. Unfortunately, the statistical cluster membership evaluation is a largely underexplored problem, with almost no previous research efforts in this direction. In this paper, we propose a new method for assessing the statistical significance of cluster membership for categorical data. Under the null hypothesis that there is no association between one sample and a cluster, we can employ the Fisher’s exact test to derive a p -value with respect to each attribute. By combining p -values from all attributes via meta-analysis, we can obtain a consensus p -value to quantify the cluster membership, i. e. , if the sample is statistically associated with the target cluster. To show the benefit of such a cluster membership evaluation technique, we deploy our algorithm to several applications, ranging from cluster validation to cluster refinement and enhancement. Experimental results on real categorical data sets demonstrate the rationale and effectiveness of our method, including its potential to improve the overall clustering accuracy of both classical and state-of-the-art clustering algorithms.

Details DOI