2 citations · 5 across the 10 of their papers we have counts for
10 papers
ShadowPEFT: Shadow Network for Parameter-Efficient Fine-Tuning
Xianming Li, Zongxi Li, Tsz-fung Andrew Lee +3
Popular low-rank parameter-efficient fine-tuning (PEFT) methods represent adaptation as separate updates to selected backbone weights, without maintaining an explicit task-specific…
FreqEdit: Preserving High-Frequency Features for Robust Multi-Turn Image Editing
Yucheng Liao, Jiajun Liang, Kaiqian Cui +5
Instruction-based image editing through natural language has emerged as a powerful paradigm for intuitive visual manipulation. While recent models achieve impressive results on sin…
Listwise Preference Optimization with Element-wise Confusions for Aspect Sentiment Quad Prediction
Wenna Lai, Haoran Xie, Guandong Xu +2
Aspect sentiment quad prediction (ASQP) is inherently challenging to predict a structured quadruple with four core sentiment elements, including aspect term (a), aspect category (c…
When LLMs Team Up: The Emergence of Collaborative Affective Computing
Wenna Lai, Haoran Xie, Guandong Xu +2
Affective Computing (AC) is essential in bridging the gap between human emotional experiences and machine understanding. Traditionally, AC tasks in natural language processing (NLP…
ConsisLoRA: Enhancing Content and Style Consistency for LoRA-based Style Transfer
Bolin Chen, Baoquan Zhao, Haoran Xie +3
Style transfer involves transferring the style from a reference image to the content of a target image. Recent advancements in LoRA-based (Low-Rank Adaptation) methods have shown p…
STAR: Stepwise Task Augmentation with Relation Learning for Aspect Sentiment Quad Prediction
Wenna Lai, Haoran Xie, Guandong Xu +1
Aspect-based sentiment analysis (ABSA) aims to identify four sentiment elements, including aspect term, aspect category, opinion term, and sentiment polarity. These elements constr…
Multi-Task Learning with LLMs for Implicit Sentiment Analysis: Data-level and Task-level Automatic Weight Learning
Wenna Lai, Haoran Xie, Guandong Xu +1
Implicit sentiment analysis (ISA) presents significant challenges due to the absence of salient cue words. Previous methods have struggled with insufficient data and limited reason…
Self-supervised Topic Taxonomy Discovery in the Box Embedding Space
Yuyin Lu, Hegang Chen, Pengbo Mao +4
Topic taxonomy discovery aims at uncovering topics of different abstraction levels and constructing hierarchical relations between them. Unfortunately, most of prior work can hardl…
RVISA: Reasoning and Verification for Implicit Sentiment Analysis
Wenna Lai, Haoran Xie, Guandong Xu +1
With an increasing social demand for fine-grained sentiment analysis (SA), implicit sentiment analysis (ISA) poses a significant challenge with the absence of salient cue words in…
2D Matryoshka Sentence Embeddings
Xianming Li, Zongxi Li, Jing Li +2
Common approaches rely on fixed-length embedding vectors from language models as sentence embeddings for downstream tasks such as semantic textual similarity (STS). Such methods ar…