activity
20242026
collaborators

9 papers

cs.LG2026

Generalized Kullback-Leibler Divergence Loss

Jiequan Cui, Beier Zhu, Qingshan Xu +5

In this paper, we delve deeper into the Kullback-Leibler (KL) Divergence loss and mathematically prove that it is equivalent to the Decoupled Kullback-Leibler (DKL) Divergence loss…

cs.CV2026

CARE Transformer: Mobile-Friendly Linear Visual Transformer via Decoupled Dual Interaction

Yuan Zhou, Qingshan Xu, Jiequan Cui +4

Recently, large efforts have been made to design efficient linear-complexity visual Transformers. However, current linear attention models are generally unsuitable to be deployed i…

cs.CV2025

Project-Probe-Aggregate: Efficient Fine-Tuning for Group Robustness

Beier Zhu, Jiequan Cui, Hanwang Zhang +1

While image-text foundation models have succeeded across diverse downstream tasks, they still face challenges in the presence of spurious correlations between the input and label.…

cs.LG2025

Generative Distribution Distillation

Jiequan Cui, Beier Zhu, Qingshan Xu +6

In this paper, we formulate the knowledge distillation (KD) as a conditional generative problem and propose the \textit{Generative Distribution Distillation (GenDD)} framework. A n…

cs.CV2024

LoRA of Change: Learning to Generate LoRA for the Editing Instruction from A Single Before-After Image Pair

Xue Song, Jiequan Cui, Hanwang Zhang +4

In this paper, we propose the LoRA of Change (LoC) framework for image editing with visual instructions, i.e., before-after image pairs. Compared to the ambiguities, insufficient s…

cs.CV2024

Pushing Rendering Boundaries: Hard Gaussian Splatting

Qingshan Xu, Jiequan Cui, Xuanyu Yi +4

3D Gaussian Splatting (3DGS) has demonstrated impressive Novel View Synthesis (NVS) results in a real-time rendering manner. During training, it relies heavily on the average magni…