Bartłomiej Twardowski
10 papers · 2020–2026 · 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 ↓+2 more ↓ Show less ↑
🌉 Interdisciplinary Bridge · Silver 🌍 Conference Polyglot · Silver 🏃 Academic Marathon · Sprint 🗺️ Taxonomy Completionist (28) 🐣 Hot Topic Early Bird
💎
Century Club · Bronze
📈
Trend Setter
Venues
Top co-authors
Research topics
Machine Learning
(9)
Deep Learning
(8)
Learning Types · Machine Learning
(7)
Core Methods
(5)
Learning Types · Deep Learning
(5)
Artificial Intelligence
(4)
Application Areas
(3)
Core AI
(3)
Computer Vision
(2)
Models
(2)
Interdisciplinary
(1)
Natural Language Processing
(1)
Applications · Computer Vision
(1)
Applications · Natural Language Processing
(1)
Bayesian & Probabilistic
(1)
Keywords
continual learning
(6)
catastrophic forgetting
(4)
class-incremental learning
(4)
gaussian distribution
(2)
knowledge distillation
(2)
self-supervised learning
(1)
model merging
(1)
feature distribution
(1)
image captioning
(1)
data augmentation
(1)
image retrieval
(1)
expert selection
(1)
illumination invariance
(1)
feature representation
(1)
spectral analysis
(1)
covariance matrix
(1)
attention mechanism
(1)
psychophysical experiment
(1)
diffusion model
(1)
feature extraction
(1)
Papers
IsoCLIP: Decomposing CLIP Projectors for Efficient Intra-modal Alignment
CVPR 2026
Improving Continual Learning Performance and Efficiency with Auxiliary Classifiers
ICML 2025
No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces
ICML 2025
The Art of Deception: Color Visual Illusions and Diffusion Models
CVPR 2025
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
Task-recency bias strikes back: Adapting covariances in Exemplar-Free Class Incremental Learning
NeurIPS 2024
FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning
NeurIPS 2023
Planckian Jitter: countering the color-crippling effects of color jitter on self-supervised training
ICLR 2023
RATT: Recurrent Attention to Transient Tasks for Continual Image Captioning
NeurIPS 2020