StruMPL is a multi-task dense regression model that jointly addresses disjoint partial supervision, MNAR labels, and inter-task physical constraints for improved forest biomass estimation from Earth observation.
International conference on machine learning , pages=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
GST uses gradient-based affinity metrics to form dataset groups and applies progressive scheduling, achieving 30-40% faster convergence than uniform mixture training on 14 AudioQA datasets while matching or exceeding performance.
citing papers explorer
-
StruMPL: Multi-task Dense Regression under Disjoint Partial Supervision and MNAR Labels
StruMPL is a multi-task dense regression model that jointly addresses disjoint partial supervision, MNAR labels, and inter-task physical constraints for improved forest biomass estimation from Earth observation.
-
Heterogeneity-Aware Dataset Scheduling for Efficient Audio Large Language Model Training
GST uses gradient-based affinity metrics to form dataset groups and applies progressive scheduling, achieving 30-40% faster convergence than uniform mixture training on 14 AudioQA datasets while matching or exceeding performance.
- Multi-task Linear Regression without Eigenvalue Lower Bounds: Adaptivity, Robustness, and Safety