Michał Stypułkowski
5 papers · 2021–2026 · 3 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 · Bronze
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Gold
🗺️
Taxonomy Completionist
(12)
🌈
Renaissance Researcher
(6)
Venues
Top co-authors
Research topics
Computer Vision
(3)
Generation
(3)
Deep Learning
(2)
Machine Learning
(2)
Learning Types · Machine Learning
(2)
Artificial Intelligence
(1)
Computer Science
(1)
Interdisciplinary
(1)
Natural Language Processing
(1)
Speech & Audio
(1)
Analysis
(1)
Applications · Computer Science
(1)
Applications · Natural Language Processing
(1)
Core AI
(1)
Learning Types · Deep Learning
(1)
Keywords
contrastive predictive coding
(2)
self-supervised learning
(2)
diffusion model
(2)
video generation
(1)
talking face generation
(1)
information retrieval
(1)
facial animation
(1)
image synthesis
(1)
flow matching
(1)
latent representation
(1)
unsupervised representation
(1)
lip synchronization
(1)
facial expression
(1)
speech representation
(1)
speech segmentation
(1)
speech coding
(1)
pattern matching
(1)
talking face
(1)
keyframe interpolation
(1)
latent space editing
(1)
Papers
FlashLips: 100-FPS Mask-Free Latent Lip-Sync using Reconstruction Instead of Diffusion or GANs
CVPR 2026
KeyFace: Expressive Audio-Driven Facial Animation for Long Sequences via KeyFrame Interpolation
CVPR 2025
Diffused Heads: Diffusion Models Beat GANs on Talking-Face Generation
WACV 2024
Aligned Contrastive Predictive Coding
Interspeech 2021
Information Retrieval for ZeroSpeech 2021: The Submission by University of Wroclaw
Interspeech 2021