Kaixuan Luan — accepted AI-conference papers

2026

GaussianZoom: Progressive Zoom-in Generative 3D Gaussian Splatting with Geometric and Semantic Guidance

Jiale Shi, Jiarui Hu, Zesong Yang, Kaixuan Luan, Hujun Bao, Zhaopeng Cui

CVPR 2026

We introduce GaussianZoom, a generative zoom-in 3D reconstruction system with an iterative progressive framework that combines geometry-consistent scene modeling and multi-scale semantic reasoning to enable high-fidelity extreme zoom-in rendering from low-resolution inputs. To achieve this, we devel

Cited by 0 Source ↗Scholar ↗

2025

BrainLoc: Brain Signal-Based Object Detection with Multi-modal Alignment

Jiaqi Duan, Xiaoda Yang, Kaixuan Luan, Hongshun Qiu, Weicai Yan, Xueyi Zhang +6

EMNLP 2025

Object detection is a core challenge in computer vision. Traditional methods primarily rely on intermediate modalities such as text, speech, or visual cues to interpret user intent, leading to inefficient and potentially distorted expressions of intent. Brain signals, particularly fMRI signals, emer

Cited by 0 Source ↗PDF ↗Scholar ↗