Dandan Liang — accepted AI-conference papers

2025

NarGINA: Towards Accurate and Interpretable Children’s Narrative Ability Assessment via Narrative Graphs

Jun Zhong, Longwei Xu, Li Kong, Xianzhuo Li, Dandan Liang, Junsheng Zhou

ACL 2025finding

The assessment of children’s narrative ability is crucial for diagnosing language disorders and planning interventions. Distinct from the typical automated essay scoring, this task focuses primarily on evaluating the completeness of narrative content and the coherence of expression, as well as the i…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2025

Towards Straggler-Resilient Split Federated Learning: An Unbalanced Update Approach

Dandan Liang, Jianing Zhang, Evan Chen, Zhe Li, Rui Li, Haibo Yang

NeurIPS 2025poster

Split Federated Learning (SFL) enables scalable training on edge devices by combining the parallelism of Federated Learning (FL) with the computational offloading of Split Learning (SL). Despite its great success, SFL suffers significantly from the well-known straggler issue in distributed learning…

Cited by 0 Source ↗Scholar ↗