SMMD loss combines MMD with numeric distance kernels and smoothness to improve accuracy on mathematical reasoning, arithmetic, clock recognition, and chart QA across LLMs and VLMs.
naacl-main.168/
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Enhancing Numerical Prediction in LLMs via Smooth MMD Alignment
SMMD loss combines MMD with numeric distance kernels and smoothness to improve accuracy on mathematical reasoning, arithmetic, clock recognition, and chart QA across LLMs and VLMs.