🏢 Xiamen University

UniDSeg uses Visual Foundation Models to create a unified framework for adaptable and generalizable cross-domain 3D semantic segmentation, achieving state-of-the-art results.

ReBorn revitalizes multi-agent reinforcement learning by tackling dormant neurons, boosting network expressivity and learning efficiency.

I2EBench: a new benchmark for Instruction-based Image Editing provides a comprehensive evaluation framework using 16 dimensions, aligned with human perception, to evaluate IIE models objectively.

FedGCDR, a novel federated graph learning framework, tackles cross-domain recommendation challenges by securely leveraging positive knowledge from multiple sources while mitigating negative transfer a…

Cross-Modality Perturbation Synergy (CMPS) attack: A novel universal perturbation method for cross-modality person re-identification, effectively misleading ReID models by leveraging gradients from di…

This paper introduces AAA, a novel three-stage decision-based black-box targeted attack against image-to-text models. AAA efficiently generates semantically consistent adversarial examples by asking …