Savas Ozkan
7 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 ↓
🌍
Conference Polyglot · Silver
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(22)
Top co-authors
Research topics
Deep Learning
(6)
Machine Learning
(5)
Application Areas
(3)
Optimization & Theory
(3)
Artificial Intelligence
(2)
Natural Language Processing
(2)
Applications
(2)
Architectures
(2)
Learning Types
(2)
Understanding
(2)
Computer Vision
(1)
Analysis
(1)
Core AI
(1)
Core Methods
(1)
Learning Paradigms
(1)
Keywords
multi-task learning
(2)
parameter-efficient fine-tuning
(2)
low-rank adaptation
(2)
named entity recognition
(2)
model merging
(1)
efficient inference
(1)
feature disentanglement
(1)
label noise
(1)
variance reduction
(1)
latent space
(1)
generative adversarial network
(1)
transformer network
(1)
parameter-efficient tuning
(1)
model scaling
(1)
parameter generation
(1)
language model fine-tuning
(1)
decentralized learning
(1)
face editing
(1)
scene text recognition
(1)
span representation
(1)
Papers
Decoding Text Spans for Efficient and Accurate Named-Entity Recognition
ACL 2026
Guided Model Merging for Hybrid Data Learning: Leveraging Centralized Data to Refine Decentralized Models
WACV 2026
Mem-MLP: Real-Time 3D Human Motion Generation from Sparse Inputs
WACV 2026
Accurate Scene Text Recognition with Efficient Model Scaling and Cloze Self-Distillation
CVPR 2025
Multi-Task Pre-Finetuning of Lightweight Transformer Encoders for Text Classification and NER
EMNLP 2025
A Study of Parameter Efficient Fine-tuning by Learning to Efficiently Fine-Tune
EMNLP 2024
Conceptual and Hierarchical Latent Space Decomposition for Face Editing
ICCV 2023