← Search

Jiayu Bai

2 accepted papers

2026

Diving into Kronecker Adapters: Component Design Matters

ICML 2026poster

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 largely treats the component structure as a fixed or heuristic design choice, leaving the dimensions and number of Krone…

Cited by 0Source ↗Scholar ↗
2025

Adaptive Discretization for Consistency Models

NeurIPS 2025poster

Consistency Models (CMs) have shown promise for efficient one-step generation. However, most existing CMs rely on manually designed discretization schemes, which can cause repeated adjustments for different noise schedules and datasets. To address this, we propose a unified framework for the automat…

Cited by 0Source ↗code ↗Scholar ↗