5 papers
Accelerating Redshift-Conditioned Galaxy Image Synthesis with One-step Generative Modeling
Tianyue Yang, Sandro Tacchella, Xiao Xue
Understanding galaxy morphology evolution across cosmic time requires models that can generate realistic galaxy populations conditioned on redshift. In this work, we study efficien…
Physical Fidelity Reconstruction via Improved Consistency-Distilled Flow Matching for Dynamical Systems
Sicheng Ma, Tianyue Yang, Xiuzhe Wu +1
Reconstructing high-fidelity flow fields from low-fidelity observations is a central problem in scientific machine learning, yet recent diffusion and flow-matching models typically…
Autoregressive One-Step Generative Modeling for Dynamical System Forecasting
Tianyue Yang, Xiao Xue
Fast surrogate modeling for high-dimensional physical dynamics requires more than low short-term error: useful models must roll out efficiently while preserving the statistical str…
Revisiting Synthetic Human Trajectories: Imitative Generation and Benchmarks Beyond Datasaurus
Bangchao Deng, Xin Jing, Tianyue Yang +3
Human trajectory data, which plays a crucial role in various applications such as crowd management and epidemic prevention, is challenging to obtain due to practical constraints an…
VITA: Versatile Time Representation Learning for Temporal Hyper-Relational Knowledge Graphs
ChongIn Un, Yuhuan Lu, Tianyue Yang +1
Knowledge graphs (KGs) have become an effective paradigm for managing real-world facts, which are not only complex but also dynamically evolve over time. The temporal validity of f…