Feng Wang

PhD student@Johns Hopkins University·美国·OpenReview

研究方向

vision-language pretraining · multi-modality learning · CLIP · self-supervised learning · representation learning · contrastive learning · semantic segmentation

5.5

UD-Mamba: A pixel-level uncertainty-driven mamba model for medical image segmentation

ICLR 2025Withdrawn

二作

4.0

M-VAR: Decoupled Scale-wise Autoregressive Modeling for High-Quality Image Generation

合作者 (20)

Feng Wang

WorldEdit: Towards Open-World Image Editing with a Knowledge-Informed Benchmark

Autoregressive Pretraining with Mamba in Vision

Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More

Causal Image Modeling for Efficient Visual Understanding

Mamba-Reg: Vision Mamba Also Needs Registers

UD-Mamba: A pixel-level uncertainty-driven mamba model for medical image segmentation

M-VAR: Decoupled Scale-wise Autoregressive Modeling for High-Quality Image Generation