Shiyu Xia
10 papers · 2023–2026 · 5 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 ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (24) 💎 Century Club · Bronze ❓ The Questioner
⚡
Prolific Year · Productive
Venues
Top co-authors
Research topics
Deep Learning
(8)
Machine Learning
(8)
Architectures
(6)
Learning Types · Deep Learning
(6)
Application Areas
(5)
Computer Vision
(4)
Learning Types · Machine Learning
(4)
Artificial Intelligence
(3)
Core AI · Computer Vision
(2)
Core AI · Artificial Intelligence
(2)
Core Methods
(2)
Optimization & Theory
(2)
Techniques
(2)
Analysis
(1)
Learning Paradigms
(1)
Keywords
model compression
(5)
transfer learning
(4)
knowledge distillation
(4)
representation learning
(3)
partial label learning
(2)
model initialization
(2)
variable-sized model
(2)
image classification
(2)
parameter initialization
(2)
vision transformer
(1)
multimodal learning
(1)
contrastive learning
(1)
label disambiguation
(1)
transformer architecture
(1)
knowledge transfer
(1)
vision-language model
(1)
self-supervised learning
(1)
weight initialization
(1)
convolutional neural network
(1)
multi-class classification
(1)
Papers
Extracting Multimodal Learngene in CLIP: Unveiling the Multimodal Generalizable Knowledge
AAAI 2026
Unlocking Pre-trained Weights: Parameter Inheritance for Zero-Shot Initialization
CVPR 2026
Inheriting Generalized Learngene for Efficient Knowledge Transfer across Multiple Tasks
AAAI 2025
Learngene Tells You How to Customize: Task-Aware Parameter Initialization at Flexible Scales
ICML 2025
Building Variable-Sized Models via Learngene Pool
AAAI 2024
Initializing Variable-sized Vision Transformers from Learngene with Learnable Transformation
NeurIPS 2024
Transformer as Linear Expansion of Learngene
AAAI 2024
Vision Language Models for Spreadsheet Understanding: Challenges and Opportunities
ACL 2024
What Makes Partial-Label Learning Algorithms Effective?
NeurIPS 2024
Towards Effective Visual Representations for Partial-Label Learning
CVPR 2023