Kamil Deja
8 papers · 2022–2026 · 7 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
(13)
❓
The Questioner
Top co-authors
Research topics
Deep Learning
(5)
Models
(5)
Machine Learning
(4)
Computer Vision
(3)
Generation
(3)
Speech & Audio
(2)
Architectures
(2)
Learning Types · Machine Learning
(2)
Synthesis
(2)
Artificial Intelligence
(1)
Analysis
(1)
Application Areas
(1)
Core AI
(1)
Core Methods
(1)
Learning Types · Deep Learning
(1)
Keywords
diffusion model
(6)
generative model
(2)
continual learning
(2)
catastrophic forgetting
(2)
image generation
(2)
text generation
(1)
text-to-image generation
(1)
speaker embedding
(1)
model interpretability
(1)
adversarial attack
(1)
variational autoencoder
(1)
lora fine-tuning
(1)
sparse autoencoder
(1)
deep generative model
(1)
knowledge consolidation
(1)
latent space alignment
(1)
generative continual learning
(1)
reverse diffusion
(1)
concept unlearning
(1)
speaker similarity
(1)
Papers
Attention, May I Have Your Decision? Localizing Generative Choices in Diffusion Models
CVPR 2026
Joint Diffusion Models in Continual Learning
ICCV 2025
Precise Parameter Localization for Textual Generation in Diffusion Models
ICLR 2025
SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders
ICML 2025
Diffusion-based accent modelling in speech synthesis
Interspeech 2023
Automatic Evaluation of Speaker Similarity
Interspeech 2022
Multiband VAE: Latent Space Alignment for Knowledge Consolidation in Continual Learning
IJCAI 2022
On Analyzing Generative and Denoising Capabilities of Diffusion-based Deep Generative Models
NeurIPS 2022