6 papers
ROAR: Retrieval Opportunity-Aware Refinement for Zero-Shot Time Series Forecasting
Jinjin Chi, Lei Feng, Lulu Zhang +7
Retrieval augmentation provides time series forecasters with historical continuations, yet even candidates that outperform the base forecast may fail to improve the final predictio…
Decomposing the Basic Abilities of Large Language Models: Mitigating Cross-Task Interference in Multi-Task Instruct-Tuning
Bing Wang, Ximing Li, Changchun Li +3
Recently, the prominent performance of large language models (LLMs) has been largely driven by multi-task instruct-tuning. Unfortunately, this training paradigm suffers from a key…
Harmful Visual Content Manipulation Matters in Misinformation Detection Under Multimedia Scenarios
Bing Wang, Ximing Li, Changchun Li +4
Nowadays, the widespread dissemination of misinformation across numerous social media platforms has led to severe negative effects on society. To address this challenge, the automa…
Disentangled Representation Learning via Flow Matching
Jinjin Chi, Taoping Liu, Mengtao Yin +5
Disentangled representation learning aims to capture the underlying explanatory factors of observed data, enabling a principled understanding of the data-generating process. Recent…
Variational Wasserstein Barycenters with c-Cyclical Monotonicity
Jinjin Chi, Zhiyao Yang, Jihong Ouyang +1
Wasserstein barycenter, built on the theory of optimal transport, provides a powerful framework to aggregate probability distributions, and it has increasingly attracted great atte…
Topic representation: finding more representative words in topic models
Jinjin Chi, Jihong Ouyang, Changchun Li +3
The top word list, i.e., the top-M words with highest marginal probability in a given topic, is the standard topic representation in topic models. Most of recent automatical topic…