Zhijian Liu

19

Papers

71

Total Citations

Papers (19)

DataMix: Efficient Privacy-Preserving Edge-Cloud Inference

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

SparseVILA: Decoupling Visual Sparsity for Efficient VLM Inference

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

NeurIPS 2025arXiv

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

GAN Compression: Efficient Architectures for Interactive Conditional GANs

FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer

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

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

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

Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution

NVILA: Efficient Frontier Visual Language Models

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

Point Transformer V3: Simpler Faster Stronger

HAQ: Hardware-Aware Automated Quantization With Mixed Precision

Learning to Exploit Stability for 3D Scene Parsing

Point-Voxel CNN for Efficient 3D Deep Learning

Deep Leakage from Gradients

Differentiable Augmentation for Data-Efficient GAN Training