2 papers
cs.LG2026
Reformulating Neural Operators in Dimensions for Embedding Evolution
Haoze Song, Zhihao Li, Xiaobo Zhang +3
Neural Operators (NOs) are powerful architectures for learning mappings between function spaces. While most advances focus on refining kernel parameterizations over the -dimensi…
cs.CV2025
Diffusion Reconstruction-based Data Likelihood Estimation for Core-Set Selection
Mingyang Chen, Jiawei Du, Bo Huang +3
Existing core-set selection methods predominantly rely on heuristic scoring signals such as training dynamics or model uncertainty, lacking explicit modeling of data likelihood. Th…