collaborators

11 papers

cs.CV2026

VCE: A zero-cost hallucination mitigation method of LVLMs via visual contrastive editing

Yanbin Huang, Yisen Li, Guiyao Tie +6

Large vision-language models (LVLMs) frequently suffer from Object Hallucination (OH), wherein they generate descriptions containing objects that are not actually present in the in…

cs.AI2026

HalluClear: Diagnosing, Evaluating and Mitigating Hallucinations in GUI Agents

Chao Jin, Wenkui Yang, Hao Sun +6

While progress in GUI agents has been largely driven by industrial-scale training, ungrounded hallucinations often trigger cascading failures in real-world deployments.Unlike gener…

cs.IR2026

DUET: Joint Exploration of User Item Profiles in Recommendation System

Yue Chen, Yifei Sun, Lu Wang +17

Traditional recommendation systems represent users and items as dense vectors and learn to align them in a shared latent space for relevance estimation. Recent LLM-based recommende…

cs.CV2026

Boosting Robust AIGI Detection with LoRA-based Pairwise Training

Ruiyang Xia, Qi Zhang, Yaowen Xu +4

The proliferation of highly realistic AI-Generated Image (AIGI) has necessitated the development of practical detection methods. While current AIGI detectors perform admirably on c…

cs.CV2026

NTIRE 2026 Challenge on Robust AI-Generated Image Detection in the Wild

Aleksandr Gushchin, Khaled Abud, Ekaterina Shumitskaya +51

This paper presents an overview of the NTIRE 2026 Challenge on Robust AI-Generated Image Detection in the Wild, held in conjunction with the NTIRE workshop at CVPR 2026. The goal o…

cs.AI2026

Dynamic Summary Generation for Interpretable Multimodal Depression Detection

Shiyu Teng, Jiaqing Liu, Hao Sun +6

Depression remains widely underdiagnosed and undertreated because stigma and subjective symptom ratings hinder reliable screening. To address this challenge, we propose a coarse-to…