PhD student, University of Science and Technology of China
2 papers at NeurIPS 2025
We boost masked graph autoencoders for molecules by introducing DyCC, a dynamic, chemistry-aware training framework with adaptive masking (GIBMS) and soft label reconstruction (SLG).
We enhance long-term time series forecasting by proposing MEW, a new metric, and two modules (IBF and HTM) that help Transformers better use historical data.
