Zizheng Pan

papers

1,131

total citations

papers (13)

Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation

CVPR 2025arXiv

293

citations

JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation

CVPR 2025arXiv

citations

The Road To Know-Where: An Object-and-Room Informed Sequential BERT for Indoor Vision-Language Navigation

ICCV 2021arXiv

citations

Stitchable Neural Networks

CVPR 2023arXiv

citations

EcoFormer: Energy-Saving Attention with Linear Complexity

NEURIPS 2022arXiv

citations

An Efficient Spatio-Temporal Pyramid Transformer for Action Detection

ECCV 2022arXiv

citations

Dynamic Focus-Aware Positional Queries for Semantic Segmentation

CVPR 2023arXiv

citations

Efficient Stitchable Task Adaptation

CVPR 2024arXiv

citations

PaRa: Personalizing Text-to-Image Diffusion via Parameter Rank Reduction

ICLR 2025arXiv

citations

Stitched ViTs are Flexible Vision Backbones

ECCV 2024arXiv

citations

Zizheng Pan

papers (13)

Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation

Fast Vision Transformers with HiLo Attention

Scalable Vision Transformers With Hierarchical Pooling

Object-and-Action Aware Model for Visual Language Navigation

JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation

The Road To Know-Where: An Object-and-Room Informed Sequential BERT for Indoor Vision-Language Navigation

Stitchable Neural Networks

EcoFormer: Energy-Saving Attention with Linear Complexity

An Efficient Spatio-Temporal Pyramid Transformer for Action Detection

Dynamic Focus-Aware Positional Queries for Semantic Segmentation

Efficient Stitchable Task Adaptation

PaRa: Personalizing Text-to-Image Diffusion via Parameter Rank Reduction

Stitched ViTs are Flexible Vision Backbones

papers (13)

Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation

Fast Vision Transformers with HiLo Attention

Scalable Vision Transformers With Hierarchical Pooling

Object-and-Action Aware Model for Visual Language Navigation

JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation

The Road To Know-Where: An Object-and-Room Informed Sequential BERT for Indoor Vision-Language Navigation

Stitchable Neural Networks

EcoFormer: Energy-Saving Attention with Linear Complexity

An Efficient Spatio-Temporal Pyramid Transformer for Action Detection

Dynamic Focus-Aware Positional Queries for Semantic Segmentation

Efficient Stitchable Task Adaptation

PaRa: Personalizing Text-to-Image Diffusion via Parameter Rank Reduction

Stitched ViTs are Flexible Vision Backbones