Skip to content

Hongkang Li

Publication record assembled from the DBLP archive of ranked conferences.

Papers indexed

9

Venues

4

Active years

2022–2025

Best venue rank

A*

Where they publish

Papers

9 indexed papers, newest first.

YearVenueTitleAuthors
2025ICLRTraining Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization Analysis.Hongkang Li, Songtao Lu, Pin-Yu Chen, Xiaodong Cui, Meng Wang
2025ICLRWhen is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers.Hongkang Li, Yihua Zhang, Shuai Zhang, Pin-Yu Chen, Sijia Liu, Meng Wang
2025ICLRNode Identifiers: Compact, Discrete Representations for Efficient Graph Learning.Yuankai Luo, Hongkang Li, Qijiong Liu, Lei Shi, Xiao-Ming Wu
2024ICASSPHow Can Personalized Context Help? Exploring Joint Retrieval of Passage and Personalized Context.Hui Wan, Hongkang Li, Songtao Lu, Xiaodong Cui, Marina Danilevsky
2024ICMLHow Do Nonlinear Transformers Learn and Generalize in In-Context Learning?Hongkang Li, Meng Wang, Songtao Lu, Xiaodong Cui, Pin-Yu Chen
2024ICMLWhat Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding.Hongkang Li, Meng Wang, Tengfei Ma, Sijia Liu, Zaixi Zhang, Pin-Yu Chen
2023ICLRA Theoretical Understanding of Shallow Vision Transformers: Learning, Generalization, and Sample Complexity.Hongkang Li, Meng Wang, Sijia Liu, Pin-Yu Chen
2022CISSLearning and generalization of one-hidden-layer neural networks, going beyond standard Gaussian data.Hongkang Li, Shuai Zhang, Meng Wang
2022ICMLGeneralization Guarantee of Training Graph Convolutional Networks with Graph Topology Sampling.Hongkang Li, Meng Wang, Sijia Liu, Pin-Yu Chen, Jinjun Xiong