Haoji Hu
16 papers · 2020–2026 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π Cross-Pollinator (14) π Conference Polyglot (7) π Academic Marathon (5) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (30)
π§
Keyword Pioneer
π
Renaissance Researcher
(5)
π₯
Unstoppable
(5)
ποΈ
Keyword Collector
(58)
π
Century Club
(15)
Conferences
AAAI (5)
ECCV (3)
CVPR (2)
ICLR (2)
MIDL (2)
ICCV (1)
NIPS (1)
Top co-authors
Keywords
model compression
(2)
multimodal large language model
(2)
knowledge distillation
(2)
attention mechanism
(2)
image segmentation
(1)
metric learning
(1)
3d reconstruction
(1)
style transfer
(1)
semantic segmentation
(1)
open-set classification
(1)
video generation
(1)
unsupervised pretraining
(1)
person re-identification
(1)
autonomous driving
(1)
image synthesis
(1)
feature learning
(1)
computer graphics
(1)
feature representation
(1)
generative model
(1)
contrastive learning
(1)
Papers
Q Cache: Visual Attention Is Valuable in Less than Half of Decode Layers for Multimodal Large Language Model
AAAI 2026
ReCamMaster: Camera-Controlled Generative Rendering from A Single Video
ICCV 2025
UrbanCAD: Towards Highly Controllable and Photorealistic 3D Vehicles for Urban Scene Simulation
CVPR 2025
SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints
ICLR 2025
ST3: Accelerating Multimodal Large Language Model by Spatial-Temporal Visual Token Trimming
AAAI 2025
FALIP: Visual Prompt as Foveal Attention Boosts CLIP Zero-Shot Performance
ECCV 2024
Robustness-Guided Image Synthesis for Data-Free Quantization
AAAI 2024
Unified Medical Image Pre-training in Language-Guided Common Semantic Space
ECCV 2024
On the Effectiveness of Out-of-Distribution Data in Self-Supervised Long-Tail Learning.
ICLR 2023
Towards Distribution-Agnostic Generalized Category Discovery
NIPS 2023
Towards Calibrated Hyper-Sphere Representation via Distribution Overlap Coefficient for Long-Tailed Learning
ECCV 2022
Unsupervised Pre-training Improves Tooth Segmentation in 3-Dimensional Intraoral Mesh Scans
MIDL 2022
Region Aware Transformer for Automatic Breast Ultrasound Tumor Segmentation
MIDL 2022
Renovate Yourself: Calibrating Feature Representation of Misclassified Pixels for Semantic Segmentation
AAAI 2022
Collaborative Distillation for Ultra-Resolution Universal Style Transfer
CVPR 2020
Appearance and Motion Enhancement for Video-Based Person Re-Identification
AAAI 2020