Jihao Liu

10

Papers

60

Total Citations

Papers (10)

Learning Where to Focus for Efficient Video Object Detection

EasyDrag: Efficient Point-based Manipulation on Diffusion Models

DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning

Rotate-and-Render: Unsupervised Photorealistic Face Rotation From Single-View Images

MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers

Differentiable Kernel Evolution

GeoMIM: Towards Better 3D Knowledge Transfer via Masked Image Modeling for Multi-view 3D Understanding

"UniNet: Unified Architecture Search with Convolution, Transformer, and MLP"

GLID: Pre-training a Generalist Encoder-Decoder Vision Model

TokenMix: Rethinking Image Mixing for Data Augmentation in Vision Transformers