Chunked attention, with no retraining, makes TabPFN v2 handle long tabular contexts exactly and shows accuracy keeps improving past the old 10K limit.
Flashattention: Fast and memory-efficient exact attention with IO-awareness
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 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.