Papers by Hyunkuk Lim
REZE: Representation Regularization for Domain-adaptive Text Embedding Pre-finetuning (2026.acl-long)
Copied to clipboard
| Challenge: | Recent text embedding models often introduce task-induced bias alongside domain knowledge, leading to performance degradation. |
| Approach: | They propose a representation regularization framework that explicitly controls representation shift during embedding pre-finetuning. |
| Outcome: | The proposed framework outperforms standard pre-finetuning and isotropy-oriented post-hoc regularization in most settings. |
TelME: Teacher-leading Multimodal Fusion Network for Emotion Recognition in Conversation (2024.naacl-long)
Copied to clipboard
| Challenge: | Emotion Recognition in Conversation (ERC) aims to identify emotions expressed by participants at each turn within a conversation. |
| Approach: | They propose a Teacher-leading Multimodal fusion network for ERC that integrates cross-modal knowledge distillation to transfer information from a lan- guage model acting as the teacher to non- verbal students. |
| Outcome: | The proposed model achieves state-of-the-art in a multi-speaker conversation dataset for ERC. |