Yongxian Wei
8 papers · 2024–2026 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
π
Conference Polyglot
(3)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(12)
π§
Keyword Pioneer
π
Cross-Pollinator
(15)
Conferences
ICML (4)
CVPR (2)
AAAI (1)
ICLR (1)
Top co-authors
Keywords
model compression
(2)
few-shot learning
(1)
transfer learning
(1)
knowledge extraction
(1)
knowledge distillation
(1)
image reconstruction
(1)
data-free learning
(1)
hidden state
(1)
pre-trained model
(1)
parameter-efficient fine-tuning
(1)
low-rank adaptation
(1)
visual foundation model
(1)
gradient alignment
(1)
layer pruning
(1)
iterative pruning
(1)
data-free meta-learning
(1)
magnitude compensation
(1)
Papers
Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation
AAAI 2026
Whoever Started the interference Should End It: Guiding Data-Free Model Merging via Task Vectors
ICML 2025
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
Open-Vocabulary Customization from CLIP via Data-Free Knowledge Distillation
ICLR 2025
Task Groupings Regularization: Data-Free Meta-Learning with Heterogeneous Pre-trained Models
ICML 2024
Sparse Model Inversion: Efficient Inversion of Vision Transformers for Data-Free Applications
ICML 2024
FREE: Faster and Better Data-Free Meta-Learning
CVPR 2024