Kuang-Ming Chen — accepted AI-conference papers

2025

ToSA: Token Merging with Spatial Awareness

Hsiang-Wei Huang, Wenhao Chai, Kuang-Ming Chen, Cheng-Yen Yang, Jenq-Neng Hwang

IROS 2025

Token merging has emerged as an effective strategy to accelerate Vision Transformers (ViT) by reducing computational costs. However, existing methods primarily rely on the visual token’s feature similarity for token merging, overlooking the potential of integrating spatial information, which can ser

Cited by 5 Source ↗code ↗Scholar ↗

2024

Chat Vector: A Simple Approach to Equip LLMs with Instruction Following and Model Alignment in New Languages

Shih-Cheng Huang, Pin-Zu Li, Yu-chi Hsu, Kuang-Ming Chen, Yu Tung Lin, Shih-Kai Hsiao +2

ACL 2024long

Recently, the development of open-source large language models (LLMs) has advanced rapidly. Nevertheless, due to data constraints, the capabilities of most open-source LLMs are primarily focused on English. To address this issue, we introduce the concept of chat vector to equip pre-trained language…

Cited by 9 Source ↗PDF ↗code ↗Scholar ↗