Bartłomiej Twardowski
9 papers · 2020–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
🗺️ Taxonomy Completionist (20) 🌍 Conference Polyglot (5) 🏃 Academic Marathon (5) 🐝 Cross-Pollinator (8) 🌈 Renaissance Researcher (6)
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
📈
Trend Setter
Conferences
NIPS (3)
ICLR (2)
ICML (2)
CVPR (1)
WACV (1)
Top co-authors
Keywords
continual learning
(4)
class incremental learning
(2)
catastrophic forgetting
(2)
knowledge distillation
(2)
image captioning
(1)
class-incremental learning
(1)
covariance matrix
(1)
psychophysical experiment
(1)
diffusion model
(1)
gaussian distribution
(1)
recurrent neural network
(1)
latent space
(1)
feature extractor
(1)
anti-collapse regularization
(1)
representation shift
(1)
prototypical network
(1)
teacher adaptation
(1)
neural network
(1)
recurrent attention
(1)
visual illusion
(1)
Papers
No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces
ICML 2025
Improving Continual Learning Performance and Efficiency with Auxiliary Classifiers
ICML 2025
The Art of Deception: Color Visual Illusions and Diffusion Models
CVPR 2025
Task-recency bias strikes back: Adapting covariances in Exemplar-Free Class Incremental Learning
NIPS 2024
Adapt Your Teacher: Improving Knowledge Distillation for Exemplar-Free Continual Learning
WACV 2024
Divide and not forget: Ensemble of selectively trained experts in Continual Learning
ICLR 2024
Planckian Jitter: countering the color-crippling effects of color jitter on self-supervised training
ICLR 2023
FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning
NIPS 2023
RATT: Recurrent Attention to Transient Tasks for Continual Image Captioning
NIPS 2020