Yongxian Wei
9 papers · 2024–2026 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🗺️
Taxonomy Completionist
(26)
Top co-authors
Research topics
Machine Learning
(8)
Artificial Intelligence
(7)
Deep Learning
(7)
Application Areas
(6)
Core AI
(4)
Learning Paradigms · Artificial Intelligence
(4)
Architectures
(3)
Learning Types · Deep Learning
(3)
Optimization & Theory
(3)
Models
(2)
Techniques
(2)
Learning Paradigms · Machine Learning
(1)
Learning Types · Machine Learning
(1)
Keywords
model compression
(3)
task vector
(2)
image reconstruction
(2)
transfer learning
(2)
pre-trained model
(2)
knowledge distillation
(2)
knowledge extraction
(1)
data-free learning
(1)
semantic segmentation
(1)
model merging
(1)
low-rank adaptation
(1)
data-free distillation
(1)
vector quantization
(1)
gradient descent
(1)
few-shot learning
(1)
parameter-efficient fine-tuning
(1)
hidden state
(1)
shared representation
(1)
test-time adaptation
(1)
vision transformer
(1)
Papers
Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation
AAAI 2026
VQRAE: Representation Quantization Autoencoders for Multimodal Understanding, Generation and Reconstruction
CVPR 2026
LoRA Recycle: Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs
CVPR 2025
Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent
ICML 2025
Open-Vocabulary Customization from CLIP via Data-Free Knowledge Distillation
ICLR 2025
Whoever Started the interference Should End It: Guiding Data-Free Model Merging via Task Vectors
ICML 2025
FREE: Faster and Better Data-Free Meta-Learning
CVPR 2024
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