activity
20122024
most citedHallucination is Inevitable: An Innate Limitation of Large Language Models

164 citations · 622 across the 69 of their papers we have counts for

collaborators
Showing 2023Show all

24 papers · 1 filter

cs.IR2023★ 2 cited

Understanding Before Recommendation: Semantic Aspect-Aware Review Exploitation via Large Language Models

Fan Liu, Yaqi Liu, Huilin Chen +3

Recommendation systems harness user-item interactions like clicks and reviews to learn their representations. Previous studies improve recommendation accuracy and interpretability…

cs.IR2023★ 17 cited

Attribute-driven Disentangled Representation Learning for Multimodal Recommendation

Zhenyang Li, Fan Liu, Yinwei Wei +3

Recommendation algorithms forecast user preferences by correlating user and item representations derived from historical interaction patterns. In pursuit of enhanced performance, m…

cs.CV2023★ 1 cited

PELA: Learning Parameter-Efficient Models with Low-Rank Approximation

Yangyang Guo, Guangzhi Wang, Mohan Kankanhalli

Applying a pre-trained large model to downstream tasks is prohibitive under resource-constrained conditions. Recent dominant approaches for addressing efficiency issues involve add…

cs.CV2023

Enhancing HOI Detection with Contextual Cues from Large Vision-Language Models

Yu-Wei Zhan, Fan Liu, Xin Luo +3

Human-Object Interaction (HOI) detection aims at detecting human-object pairs and predicting their interactions. However, conventional HOI detection methods often struggle to fully…

cs.LG2023★ 3 cited

Finetuning Text-to-Image Diffusion Models for Fairness

Xudong Shen, Chao Du, Tianyu Pang +3

The rapid adoption of text-to-image diffusion models in society underscores an urgent need to address their biases. Without interventions, these biases could propagate a skewed wor…

cs.CV2023

Prior-Free Continual Learning with Unlabeled Data in the Wild

Tao Zhuo, Zhiyong Cheng, Hehe Fan +1

Continual Learning (CL) aims to incrementally update a trained model on new tasks without forgetting the acquired knowledge of old ones. Existing CL methods usually reduce forgetti…