Hui Xiong

10

Papers

10

Total Citations

Papers (10)

UniINR: Event-guided Unified Rolling Shutter Correction, Deblurring, and Interpolation

See&Trek: Training-Free Spatial Prompting for Multimodal Large Language Model

Efficient Skill Discovery via Regret-Aware Optimization

Harnessing Multimodal Large Language Models for Multimodal Sequential Recommendation

Fusing Pruned and Backdoored Models: Optimal Transport-based Data-free Backdoor Mitigation

Temporal Graph Contrastive Learning for Sequential Recommendation

Depth Any Event Stream: Enhancing Event-based Monocular Depth Estimation via Dense-to-Sparse Distillation

Irregular Multivariate Time Series Forecasting: A Transformable Patching Graph Neural Networks Approach

MagicCity: Geometry-Aware 3D City Generation from Satellite Imagery with Multi-View Consistency

TC-LLaVA: Rethinking the Transfer of LLava from Image to Video Understanding with Temporal Considerations