WHEN IS TASK VECTOR Provably EFFECTIVE FOR MODEL EDITING? A GENERALIZATION ANALYSIS OF NONLINEAR TRANSFORMERS
- Hongkang Li
- Yihua Zhang
- et al.
- 2025
- ICLR 2025
Publications
6 results for Hongkang Li
TRAINING NONLINEAR TRANSFORMERS FOR CHAIN-OF-THOUGHT INFERENCE: A THEORETICAL GENERALIZATION ANALYSIS
- Hongkang Li
- Songtao Lu
- et al.
- 2025
- ICLR 2025
Learning on Transformers is Provable Low-Rank and Sparse: A One-layer Analysis
- Hongkang Li
- Meng Wang
- et al.
- 2024
- SAM 2024
HOW CAN PERSONALIZED CONTEXT HELP? EXPLORING JOINT RETRIEVAL OF PASSAGE AND PERSONALIZED CONTEXT
- Hui Wan
- Hongkang Li
- et al.
- 2024
- ICASSP 2024
How Does Promoting the Minority Fraction Affect Generalization? A Theoretical Study of One-Hidden-Layer Neural Network on Group Imbalance
- Hongkang Li
- Shuai Zhang
- et al.
- 2024
- Ieee Journal Of Selected Topics In Signal Processing
Generalization Guarantee of Training Graph Convolutional Networks with Graph Topology Sampling
- Hongkang Li
- Meng Wang
- et al.
- 2022
- ICML 2022