8 citations · 26 across the 12 of their papers we have counts for
13 papers
Narrative Paradoxes in LLM Inference: Shaping Reasoning Trajectories toward Misalignment
Haoming Yang, Ke Ma, Yangbangyan Jiang +6
Explicit reasoning in large language models (LLMs) is often associated with reliability, yet it can still pose risks when a model infers harmful goals under a benign context. We id…
The Price of Consistency: Exploiting Visual Anchors for Multimodal Jailbreaking in Video Generation
Peng Li, Qianqian Xu, Yangbangyan Jiang +2
The rapid evolution of video generation has shifted the paradigm from pure text-driven to multi-conditional controllable generation, with reference images now widely adopted as con…
UniTraffic-Agent: Unified Traffic Video Reasoning for AI City Challenge 2026 Track 3 with Two Out-of-Domain Evaluations
Peng Li, Qianqian Xu, Shilong Bao +2
Traffic video understanding has become an important problem in intelligent transportation, as road videos provide direct evidence for accidents, violations, and interactions betwee…
Localize and Neutralize: Gradient-guided Token Suppression against Visual Prompt Injection Attack
Dongpeng Zhang, Ke Ma, Yangbangyan Jiang +4
Adversarial images pose a severe security threat to multimodal large language models through prompt injection. Existing defenses largely lack a principled understanding of the unde…
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…
Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection
Zhipeng Yu, Qianqian Xu, Yangbangyan Jiang +2
The existence of noisy labels in real-world data negatively impacts the performance of deep learning models. Although much research effort has been devoted to improving the robustn…
AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmentation
Boyu Han, Qianqian Xu, Zhiyong Yang +4
The Area Under the ROC Curve (AUC) is a well-known metric for evaluating instance-level long-tail learning problems. In the past two decades, many AUC optimization methods have bee…
Regularized Contrastive Partial Multi-view Outlier Detection
Yijia Wang, Qianqian Xu, Yangbangyan Jiang +2
In recent years, multi-view outlier detection (MVOD) methods have advanced significantly, aiming to identify outliers within multi-view datasets. A key point is to better detect cl…
HGOE: Hybrid External and Internal Graph Outlier Exposure for Graph Out-of-Distribution Detection
Junwei He, Qianqian Xu, Yangbangyan Jiang +3
With the progressive advancements in deep graph learning, out-of-distribution (OOD) detection for graph data has emerged as a critical challenge. While the efficacy of auxiliary da…
ADA-GAD: Anomaly-Denoised Autoencoders for Graph Anomaly Detection
Junwei He, Qianqian Xu, Yangbangyan Jiang +2
Graph anomaly detection is crucial for identifying nodes that deviate from regular behavior within graphs, benefiting various domains such as fraud detection and social network. Al…
Dist-PU: Positive-Unlabeled Learning from a Label Distribution Perspective
Yunrui Zhao, Qianqian Xu, Yangbangyan Jiang +2
Positive-Unlabeled (PU) learning tries to learn binary classifiers from a few labeled positive examples with many unlabeled ones. Compared with ordinary semi-supervised learning, t…
Seeking the Shape of Sound: An Adaptive Framework for Learning Voice-Face Association
Peisong Wen, Qianqian Xu, Yangbangyan Jiang +3
Nowadays, we have witnessed the early progress on learning the association between voice and face automatically, which brings a new wave of studies to the computer vision community…
Deep Robust Subjective Visual Property Prediction in Crowdsourcing
Qianqian Xu, Zhiyong Yang, Yangbangyan Jiang +3
The problem of estimating subjective visual properties (SVP) of images (e.g., Shoes A is more comfortable than B) is gaining rising attention. Due to its highly subjective nature,…