Zixuan Hu
14 papers · 2022–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π Cross-Pollinator (15) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (21) π§ Keyword Pioneer π Conference Polyglot (5)
β‘
Prolific Year
(6)
π
Century Club
(14)
β
The Questioner
Conferences
ICML (5)
CVPR (4)
ICCV (2)
ICLR (2)
ECCV (1)
Top co-authors
Keywords
transfer learning
(4)
knowledge distillation
(3)
model selection
(2)
data-free learning
(2)
data-free meta-learning
(2)
few-shot learning
(2)
model compression
(2)
image reconstruction
(1)
neural network optimization
(1)
zero-order optimization
(1)
pre-trained model
(1)
parameter-efficient fine-tuning
(1)
low-rank adaptation
(1)
domain shift
(1)
visual foundation model
(1)
gradient alignment
(1)
black-box model
(1)
potential energy
(1)
logit space
(1)
test time adaptation
(1)
Papers
Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent
ICML 2025
LoRA Recycle: Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs
CVPR 2025
Adaptive Dual Uncertainty Optimization: Boosting Monocular 3D Object Detection under Test-Time Shifts
ICCV 2025
Which Tasks Should Be Compressed Together? A Causal Discovery Approach for Efficient Multi-Task Representation Compression
ICLR 2025
Open-Vocabulary Customization from CLIP via Data-Free Knowledge Distillation
ICLR 2025
Beyond Entropy: Region Confidence Proxy for Wild Test-Time Adaptation
ICML 2025
Sparse Model Inversion: Efficient Inversion of Vision Transformers for Data-Free Applications
ICML 2024
Task Groupings Regularization: Data-Free Meta-Learning with Heterogeneous Pre-trained Models
ICML 2024
FREE: Faster and Better Data-Free Meta-Learning
CVPR 2024
LEAD: Exploring Logit Space Evolution for Model Selection
CVPR 2024
Exploring Model Transferability through the Lens of Potential Energy
ICCV 2023
Learning to Learn from APIs: Black-Box Data-Free Meta-Learning
ICML 2023
Architecture, Dataset and Model-Scale Agnostic Data-Free Meta-Learning
CVPR 2023
Mc-BEiT: Multi-Choice Discretization for Image BERT Pre-training
ECCV 2022