12 papers
Disentangling Generation and Regression in Stochastic Interpolants for Controllable Image Restoration
Yi Liu, Jia Ma, Wengen Li +3
Recent advances in Image Restoration (IR) have been largely driven by generative methods such as Diffusion Models and Flow Matching, which excel in synthesizing realistic textures…
SSDA: Bridging Spectral and Structural Gaps via Dual Adaptation for Vision-Based Time Series Forecasting
Mingrui Zhang, Hanchen Yang, Wengen Li +4
Large vision models (LVMs) have recently proven to be surprisingly effective time series forecasters, simply by rendering temporal data as images. This success, how ever, rests on…
AdaMamba: Adaptive Frequency-Gated Mamba for Long-Term Time Series Forecasting
Xudong Jiang, Mingshan Loo, Hanchen Yang +5
Accurate long-term time series forecasting (LTSF) requires the capture of complex long-range dependencies and dynamic periodic patterns. Recent advances in frequency-domain analysi…
An Adaptive Spatiotemporal Clustering Framework for 3D Ocean Subsurface Temperature Reconstruction
Ming Shan Loo, Wengen Li, Xudong Jiang +4
The reconstruction of ocean subsurface temperature (OST) using satellite remote sensing data holds significant scientific value for advancing the understanding of ocean dynamics an…
One Pass for All: A Discrete Diffusion Model for Knowledge Graph Triple Set Prediction
Jihong Guan, Jiaqi Wang, Wengen Li +3
Knowledge Graphs (KGs) are composed of triples, and the goal of Knowledge Graph Completion (KGC) is to infer the missing factual triples. Traditional KGC tasks predict missing elem…
BioBridge: Bridging Proteins and Language for Enhanced Biological Reasoning with LLMs
Yujia Wang, Jihong Guan, Wengen Li +2
Existing Protein Language Models (PLMs) often suffer from limited adaptability to multiple tasks and exhibit poor generalization across diverse biological contexts. In contrast, ge…