5 papers
GenSpan: Generation-Calibrated Motion Span Priors for Multi-Verb Video Corpus Moment Retrieval
Yunzhuo Sun, Xinyue Liu, Yanyang Li +4
Video Corpus Moment Retrieval (VCMR) aims to retrieve both the correct video and its temporal segment corresponding to a natural-language query, a task that is especially challengi…
Meta Additive Model: Interpretable Sparse Learning With Auto Weighting
Xuelin Zhang, Xinyue Liu, Lingjuan Wu +1
Sparse additive models have attracted much attention in high-dimensional data analysis due to their flexible representation and strong interpretability. However, most existing mode…
Alignment Whack-a-Mole : Finetuning Activates Verbatim Recall of Copyrighted Books in Large Language Models
Xinyue Liu, Niloofar Mireshghallah, Jane C. Ginsburg +1
Frontier LLM companies have repeatedly assured courts and regulators that their models do not store copies of training data. They further rely on safety alignment strategies via RL…
Boosting Meta-Learning for Few-Shot Text Classification via Label-guided Distance Scaling
Yunlong Gao, Xinyue Liu, Yingbo Wang +2
Few-shot text classification aims to recognize unseen classes with limited labeled text samples. Existing approaches focus on boosting meta-learners by developing complex algorithm…
Hawkes based Representation Learning for Reasoning over Scale-free Community-structured Temporal Knowledge Graphs
Yuwei Du, Xinyue Liu, Wenxin Liang +2
Temporal knowledge graph (TKG) reasoning has become a hot topic due to its great value in many practical tasks. The key to TKG reasoning is modeling the structural information and…