Zhijian Liu

Affiliations

Massachusetts Institute of Technology

papers

2,401

total citations

papers (16)

SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformer

CVPR 2023arXiv

citations

StreamDiffusion: A Pipeline-level Solution for Real-Time Interactive Generation

ICCV 2025arXiv

citations

DataMix: Efficient Privacy-Preserving Edge-Cloud Inference

ECCV 2020

citations

VILA-M3: Enhancing Vision-Language Models with Medical Expert Knowledge

CVPR 2025arXiv

citations

MapPrior: Bird's-Eye View Map Layout Estimation with Generative Models

ICCV 2023arXiv

citations

LocTex: Learning Data-Efficient Visual Representations From Localized Textual Supervision

ICCV 2021arXiv

citations

KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems

NEURIPS 2025arXiv

citations

GAN Compression: Efficient Architectures for Interactive Conditional GANs

CVPR 2020arXiv

citations

SparseVILA: Decoupling Visual Sparsity for Efficient VLM Inference

ICCV 2025arXiv

citations

Point Transformer V3: Simpler Faster Stronger

CVPR 2024

citations

Zhijian Liu

Affiliations

papers (16)

Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution

Differentiable Augmentation for Data-Efficient GAN Training

LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models

APQ: Joint Search for Network Architecture, Pruning and Quantization Policy

NVILA: Efficient Frontier Visual Language Models

FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer

SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformer

StreamDiffusion: A Pipeline-level Solution for Real-Time Interactive Generation

DataMix: Efficient Privacy-Preserving Edge-Cloud Inference

VILA-M3: Enhancing Vision-Language Models with Medical Expert Knowledge

MapPrior: Bird's-Eye View Map Layout Estimation with Generative Models

LocTex: Learning Data-Efficient Visual Representations From Localized Textual Supervision

KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems

GAN Compression: Efficient Architectures for Interactive Conditional GANs

SparseVILA: Decoupling Visual Sparsity for Efficient VLM Inference

Point Transformer V3: Simpler Faster Stronger

papers (16)

Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution

Differentiable Augmentation for Data-Efficient GAN Training

LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models

APQ: Joint Search for Network Architecture, Pruning and Quantization Policy

NVILA: Efficient Frontier Visual Language Models

FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer

SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformer

StreamDiffusion: A Pipeline-level Solution for Real-Time Interactive Generation

DataMix: Efficient Privacy-Preserving Edge-Cloud Inference

VILA-M3: Enhancing Vision-Language Models with Medical Expert Knowledge

MapPrior: Bird's-Eye View Map Layout Estimation with Generative Models

LocTex: Learning Data-Efficient Visual Representations From Localized Textual Supervision

KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems

GAN Compression: Efficient Architectures for Interactive Conditional GANs

SparseVILA: Decoupling Visual Sparsity for Efficient VLM Inference

Point Transformer V3: Simpler Faster Stronger