Haoji Hu

9

Papers

12

Total Citations

Papers (9)

FALIP: Visual Prompt as Foveal Attention Boosts CLIP Zero-Shot Performance

Unified Medical Image Pre-training in Language-Guided Common Semantic Space

ST3: Accelerating Multimodal Large Language Model by Spatial-Temporal Visual Token Trimming

Robustness-Guided Image Synthesis for Data-Free Quantization

Collaborative Distillation for Ultra-Resolution Universal Style Transfer

Towards Calibrated Hyper-Sphere Representation via Distribution Overlap Coefficient for Long-Tailed Learning

UrbanCAD: Towards Highly Controllable and Photorealistic 3D Vehicles for Urban Scene Simulation

ReCamMaster: Camera-Controlled Generative Rendering from A Single Video

Towards Distribution-Agnostic Generalized Category Discovery