3 papers
cs.LG2026
Diving into Kronecker Adapters: Component Design Matters
Jiayu Bai, Danchen Yu, Zhenyu Liao +4
Kronecker adapters have emerged as a promising approach for fine-tuning large-scale models, enabling high-rank updates through tunable component structures. However, existing work…
stat.ML2026
On the Interpolation Error of Nonlinear Attention versus Linear Regression
Zhenyu Liao, Jiaqing Liu, TianQi Hou +2
Attention has become the core building block of modern machine learning (ML) by efficiently capturing the long-range dependencies among input tokens. Its inherently parallelizable…
cs.LG2026
Latent Iterative Refinement Flow: A Geometric Constrained Approach for Few-Shot Generation
Songtao Li, Tianqi Hou, Zhenyu Liao +1
Diffusion and flow-matching models trained with limited data often tend to memorize the training data instead of generalization, leading to severely reduced diversity. In this pape…