XCTFormer is a channel-dependent transformer that uses token-to-token cross-relational attention and an optional compression plugin to capture cross-channel and cross-time dependencies, reporting SOTA imputation results on three benchmarks.
Forty-first International Conference on Machine Learning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
TabPFN-TS captures simple target-covariate relationships more effectively than Chronos-2 in controlled experiments, especially for short horizons.
citing papers explorer
-
XCTFormer: Leveraging Cross-Channel and Cross-Time Dependencies for Enhanced Time-Series Analysis
XCTFormer is a channel-dependent transformer that uses token-to-token cross-relational attention and an optional compression plugin to capture cross-channel and cross-time dependencies, reporting SOTA imputation results on three benchmarks.
-
Investigating simple target-covariate relationships for Chronos-2 and TabPFN-TS
TabPFN-TS captures simple target-covariate relationships more effectively than Chronos-2 in controlled experiments, especially for short horizons.