Chunked attention, with no retraining, makes TabPFN v2 handle long tabular contexts exactly and shows accuracy keeps improving past the old 10K limit.
Revisiting deep learning models for tabular data.Advances in neural information processing systems, 34:18932–18943, 2021
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Chunked TabPFN: Exact Training-Free In-Context Learning for Long-Context Tabular Data
Chunked attention, with no retraining, makes TabPFN v2 handle long tabular contexts exactly and shows accuracy keeps improving past the old 10K limit.