Scholar
Sebastian Cygert
Google Scholar ID: wLH9PP8AAAAJ
NASK - National Research Institute, Politechnika Gdańska
Citations & Impact
Citations
383
H-index
11
i10-index
12
Publications
20
Co-authors
12
list available
Publications
Resume (English only)
Academic Achievements
- Publications:
- - ICML 2025: No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces
- - NeurIPS 2024: Task-recency bias strikes back: Adapting covariances in Exemplar-Free Class Incremental Learning
- - BMVC 2024 & ICCV 2023 Workshop: AR-TTA: A Simple Method for Real-World Continual Test-Time Adaptation
- - ECCV 2024: MagMax: Leveraging Model Merging for Seamless Continual Learning, Revisiting Supervision for Continual Representation Learning, Category Adaptation Meets Projected Distillation in Generalized Continual Category Discovery
- - Molecular Oncology 2024: Improving platelet‐RNA‐based diagnostics: a comparative analysis of machine learning models for cancer detection and multiclass classification
- - ICLR 2024: Divide and not forget: Ensemble of selectively trained experts in Continual Learning
- - IEEE Access 2024: Looking through the past: better knowledge retention for generative replay in continual learning
- - WACV 2024: Adapt Your Teacher: Improving Knowledge Distillation for Exemplar-free Continual Learning
- Awards:
- - NCN (Sonata) funding
- - ELLIS member
- - BMVC 2024 Innovation Award at ICCV 2023 Workshop on Visual Continual Learning
Research Experience
- Currently Head of AI Safety Department at NASK - National Research Institute and Assistant Professor (part-time) at Gdańsk University of Technology. Previously, a postdoctoral researcher at IDEAS NCBR working on the Continual Learning team within the Computer Vision group. Worked at Amazon on the Amazon Scout project (Tubingen, Germany) and Alexa Text-to-speech (Gdańsk, Poland). Also worked at machine learning start-ups and enjoyed the London FinTech scene.
Education
- PhD from Gdańsk University of Technology; Master's from Warsaw University of Technology.
Background
- Research Interests: computer vision, deep learning, and generative AI. Focus: finding ways to obtain robust representations, adapt them continually, and share them across different models. Also interested in computational efficiency of ML models and physical simulations.
Miscellany
- Personal Interests: Not mentioned
