Cheng-Hao Tu
7 papers · 2019–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Conference Polyglot (4) π Academic Marathon (6) π Renaissance Researcher (5) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (19)
π§
Keyword Pioneer
π
Cross-Pollinator
(15)
Conferences
NIPS (3)
CVPR (2)
AAAI (1)
ICLR (1)
Top co-authors
Keywords
transfer learning
(3)
vision transformer
(2)
domain adaptation
(2)
image generation
(1)
feature extraction
(1)
knowledge distillation
(1)
image synthesis
(1)
parameter-efficient transfer learning
(1)
parameter efficient
(1)
visual recognition
(1)
gradient descent
(1)
classification accuracy
(1)
parameter learning
(1)
inverse problem
(1)
ensemble method
(1)
memory efficiency
(1)
parameter-efficient fine-tuning
(1)
feature aggregation
(1)
pretrained model
(1)
intermediate representation
(1)
Papers
Lessons and Insights from a Unifying Study of Parameter-Efficient Fine-Tuning (PEFT) in Visual Recognition
CVPR 2025
Fine-Tuning is Fine, if Calibrated
NIPS 2024
Visual Query Tuning: Towards Effective Usage of Intermediate Representations for Parameter and Memory Efficient Transfer Learning
CVPR 2023
Learning Fractals by Gradient Descent
AAAI 2023
Holistic Transfer: Towards Non-Disruptive Fine-Tuning with Partial Target Data
NIPS 2023
On the Importance and Applicability of Pre-Training for Federated Learning
ICLR 2023
Compacting, Picking and Growing for Unforgetting Continual Learning
NIPS 2019