Peizhao Zhang

papers

1,419

total citations

papers (14)

Open-Vocabulary Semantic Segmentation With Mask-Adapted CLIP

CVPR 2023arXiv

630

citations

FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions

CVPR 2020arXiv

321

citations

Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference

CVPR 2023arXiv

citations

LinGen: Towards High-Resolution Minute-Length Text-to-Video Generation with Linear Computational Complexity

CVPR 2025arXiv

citations

FP-NAS: Fast Probabilistic Neural Architecture Search

CVPR 2021arXiv

citations

Movie Weaver: Tuning-Free Multi-Concept Video Personalization with Anchored Prompts

CVPR 2025arXiv

citations

Geometric Correspondence Fields: Learned Differentiable Rendering for 3D Pose Refinement in the Wild

ECCV 2020arXiv

citations

Auto-CARD: Efficient and Robust Codec Avatar Driving for Real-Time Mobile Telepresence

CVPR 2023arXiv

citations

Visual Transformers: Where Do Transformers Really Belong in Vision Models?

ICCV 2021

citations

DIME-FM : DIstilling Multimodal and Efficient Foundation Models

ICCV 2023

citations

Peizhao Zhang

papers (14)

Open-Vocabulary Semantic Segmentation With Mask-Adapted CLIP

FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions

Cache Me if You Can: Accelerating Diffusion Models through Block Caching

FBNetV3: Joint Architecture-Recipe Search Using Predictor Pretraining

FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis

ControlRoom3D: Room Generation using Semantic Proxy Rooms

Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference

LinGen: Towards High-Resolution Minute-Length Text-to-Video Generation with Linear Computational Complexity

FP-NAS: Fast Probabilistic Neural Architecture Search

Movie Weaver: Tuning-Free Multi-Concept Video Personalization with Anchored Prompts

Geometric Correspondence Fields: Learned Differentiable Rendering for 3D Pose Refinement in the Wild

Auto-CARD: Efficient and Robust Codec Avatar Driving for Real-Time Mobile Telepresence

Visual Transformers: Where Do Transformers Really Belong in Vision Models?

DIME-FM : DIstilling Multimodal and Efficient Foundation Models

papers (14)

Open-Vocabulary Semantic Segmentation With Mask-Adapted CLIP

FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions

Cache Me if You Can: Accelerating Diffusion Models through Block Caching

FBNetV3: Joint Architecture-Recipe Search Using Predictor Pretraining

FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis

ControlRoom3D: Room Generation using Semantic Proxy Rooms

Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference

LinGen: Towards High-Resolution Minute-Length Text-to-Video Generation with Linear Computational Complexity

FP-NAS: Fast Probabilistic Neural Architecture Search

Movie Weaver: Tuning-Free Multi-Concept Video Personalization with Anchored Prompts

Geometric Correspondence Fields: Learned Differentiable Rendering for 3D Pose Refinement in the Wild

Auto-CARD: Efficient and Robust Codec Avatar Driving for Real-Time Mobile Telepresence

Visual Transformers: Where Do Transformers Really Belong in Vision Models?

DIME-FM : DIstilling Multimodal and Efficient Foundation Models