Mayank Sharma
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
ML×1Vision×1
Frequent co-authors
Research Timeline
2026
Logit-Origin Centering for Singleton Test-Time Adaptation
This paper proposes Prequential Logit-Origin Centering (PLOC), a lightweight approach for fully test-time adaptation (FTTA) of deep learning models on tabular data in strict streaming regimes.
Highlighted terms show continued research focus across papers