Zijian He

papers

1,115

total citations

papers (13)

FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions

CVPR 2020arXiv

321

citations

NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detection

ICCV 2023arXiv

citations

ControlRoom3D: Room Generation using Semantic Proxy Rooms

CVPR 2024arXiv

citations

Preble: Efficient Distributed Prompt Scheduling for LLM Serving

ICLR 2025arXiv

citations

Open-Set Semi-Supervised Object Detection

ECCV 2022arXiv

citations

Mask3D: Pre-Training 2D Vision Transformers by Learning Masked 3D Priors

CVPR 2023arXiv

citations

InferCept: Efficient Intercept Support for Augmented Large Language Model Inference

ICML 2024arXiv

citations

A Practical Stereo Depth System for Smart Glasses

CVPR 2023arXiv

citations

VTON 360: High-Fidelity Virtual Try-On from Any Viewing Direction

CVPR 2025arXiv

citations

Zijian He

papers (13)

FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions

Cross-Domain Adaptive Teacher for Object Detection

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

FBNetV3: Joint Architecture-Recipe Search Using Predictor Pretraining

Polyhistor: Parameter-Efficient Multi-Task Adaptation for Dense Vision Tasks

NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detection

ControlRoom3D: Room Generation using Semantic Proxy Rooms

Preble: Efficient Distributed Prompt Scheduling for LLM Serving

Open-Set Semi-Supervised Object Detection

Mask3D: Pre-Training 2D Vision Transformers by Learning Masked 3D Priors

InferCept: Efficient Intercept Support for Augmented Large Language Model Inference

A Practical Stereo Depth System for Smart Glasses

VTON 360: High-Fidelity Virtual Try-On from Any Viewing Direction

papers (13)

FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions

Cross-Domain Adaptive Teacher for Object Detection

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

FBNetV3: Joint Architecture-Recipe Search Using Predictor Pretraining

Polyhistor: Parameter-Efficient Multi-Task Adaptation for Dense Vision Tasks

NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detection

ControlRoom3D: Room Generation using Semantic Proxy Rooms

Preble: Efficient Distributed Prompt Scheduling for LLM Serving

Open-Set Semi-Supervised Object Detection

Mask3D: Pre-Training 2D Vision Transformers by Learning Masked 3D Priors

InferCept: Efficient Intercept Support for Augmented Large Language Model Inference

A Practical Stereo Depth System for Smart Glasses

VTON 360: High-Fidelity Virtual Try-On from Any Viewing Direction