Cihang Xie

11

Papers

98

Total Citations

Papers (11)

MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine

Generative Image Layer Decomposition with Visual Effects

OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning

VideoLLaMB: Long Streaming Video Understanding with Recurrent Memory Bridges

From Pixels to Objects: A Hierarchical Approach for Part and Object Segmentation Using Local and Global Aggregation

Mamba-Reg: Vision Mamba Also Needs Registers

Rejuvenating image-GPT as Strong Visual Representation Learners

Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency

L2B: Learning to Bootstrap Robust Models for Combating Label Noise

Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-training

Revisiting Adversarial Training at Scale