Yi-Lin Sung
11 papers · 2021–2025 · 6 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 ↓+4 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (28) 🧭 Keyword Pioneer
🤝
Dynamic Duo
(10)
🗃️
Keyword Collector
(64)
💎
Century Club · Bronze
🔥
Unstoppable · Bronze
Top co-authors
Research topics
Machine Learning
(11)
Deep Learning
(9)
Application Areas
(9)
Artificial Intelligence
(6)
Learning Types · Deep Learning
(6)
Core AI · Artificial Intelligence
(5)
Learning Types · Machine Learning
(4)
Computer Vision
(3)
Techniques
(3)
Architectures
(2)
Core AI · Computer Vision
(2)
Core Methods
(2)
Generation
(1)
Learning Paradigms
(1)
Models
(1)
Keywords
model merging
(3)
expert merging
(2)
vision-language model
(2)
transfer learning
(2)
parameter-efficient transfer learning
(2)
multimodal learning
(2)
mixture of expert
(2)
knowledge distillation
(1)
semantic alignment
(1)
catastrophic forgetting
(1)
cross-modal retrieval
(1)
text-to-image generation
(1)
parameter-efficient learning
(1)
multi-task learning
(1)
fisher information
(1)
audio-visual learning
(1)
parameter efficient
(1)
model pruning
(1)
weight sparsification
(1)
instruction tuning
(1)
Papers
DAM: Dynamic Adapter Merging for Continual Video QA Learning
WACV 2025
Glider: Global and Local Instruction-Driven Expert Router
EMNLP 2025
ECoFLaP: Efficient Coarse-to-Fine Layer-Wise Pruning for Vision-Language Models
ICLR 2024
Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy
ICLR 2024
SELMA: Learning and Merging Skill-Specific Text-to-Image Experts with Auto-Generated Data
NeurIPS 2024
An Empirical Study of Multimodal Model Merging
EMNLP 2023
Unified Coarse-to-Fine Alignment for Video-Text Retrieval
ICCV 2023
Vision Transformers Are Parameter-Efficient Audio-Visual Learners
CVPR 2023
LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learning
NeurIPS 2022
VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks
CVPR 2022
Training Neural Networks with Fixed Sparse Masks
NeurIPS 2021