collaborators

24 papers

cs.CV2025

Closing the Approximation Gap of Partial AUC Optimization: A Tale of Two Formulations

Yangbangyan Jiang, Qianqian Xu, Huiyang Shao +4

As a variant of the Area Under the ROC Curve (AUC), the partial AUC (PAUC) focuses on a specific range of false positive rate (FPR) and/or true positive rate (TPR) in the ROC curve…

cs.CV2025

HiGFA: Hierarchical Guidance for Fine-grained Data Augmentation with Diffusion Models

Zhiguang Lu, Qianqian Xu, Peisong Wen +2

Generative diffusion models show promise for data augmentation. However, applying them to fine-grained tasks presents a significant challenge: ensuring synthetic images accurately…

cs.SI2025

Quantifying the Potential to Escape Filter Bubbles: A Behavior-Aware Measure via Contrastive Simulation

Difu Feng, Qianqian Xu, Zitai Wang +3

Nowadays, recommendation systems have become crucial to online platforms, shaping user exposure by accurate preference modeling. However, such an exposure strategy can also reinfor…

cs.CV2025

Bootstrapping Physics-Grounded Video Generation through VLM-Guided Iterative Self-Refinement

Yang Liu, Xilin Zhao, Peisong Wen +2

Recent progress in video generation has led to impressive visual quality, yet current models still struggle to produce results that align with real-world physical principles. To th…

cs.LG2025

TuckA: Hierarchical Compact Tensor Experts for Efficient Fine-Tuning

Qifeng Lei, Zhiyong Yang, Qianqian Xu +3

Efficiently fine-tuning pre-trained models for downstream tasks is a key challenge in the era of foundation models. Parameter-efficient fine-tuning (PEFT) presents a promising solu…

cs.CV2025

Exploring Structural Degradation in Dense Representations for Self-supervised Learning

Siran Dai, Qianqian Xu, Peisong Wen +2

In this work, we observe a counterintuitive phenomenon in self-supervised learning (SSL): longer training may impair the performance of dense prediction tasks (e.g., semantic segme…