3 papers
cs.LG2026
Learning to Order: Task Sequencing as In-Context Optimization
Jan Kobiolka, Christian Frey, Arlind Kadra +2
Task sequencing (TS) is one of the core open problems in Deep Learning, arising in a plethora of real-world domains, from robotic assembly lines to autonomous driving. Unfortunatel…
cs.LG2026
POP: Prior-Fitted First-Order Optimization Policies
Jan Kobiolka, Christian Frey, Gresa Shala +3
Gradient-based optimizers are highly sensitive to design choices in their adaptive learning rate mechanisms. To address this limitation, we introduce POP, a meta-learned Reinforcem…
cs.LG2026
End-to-End Compression for Tabular Foundation Models
Guri Zabërgja, Rafiq Kamel, Arlind Kadra +2
The long-standing dominance of gradient-boosted decision trees for tabular data has recently been challenged by in-context learning tabular foundation models. In-context learning m…