Sjoerd van Steenkiste
21 papers · 2017–2025 · 6 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 ↓+13 more ↓ Show less ↑
🗺️ Taxonomy Completionist (46) 🌍 Conference Polyglot · Silver 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Gold 🐣 Hot Topic Early Bird
🏆
Grand Slam
🤝
Dynamic Duo
(10)
🧬
Topic Evolution
🏆
Keyword Champion
👥
Mega-Team · Squad
🚀
Conference Pioneer
🔥
Unstoppable · Bronze
❓
The Questioner
(2)
⚡
Prolific Year · Productive
💎
Century Club · Bronze
🌈
Renaissance Researcher
(5)
📈
Trend Setter
🗃️
Keyword Collector
(104)
Top co-authors
Research topics
Deep Learning
(14)
Artificial Intelligence
(13)
Computer Vision
(12)
Machine Learning
(11)
Core AI
(11)
Analysis
(8)
Learning Types · Machine Learning
(8)
Learning Types · Deep Learning
(7)
Generation
(5)
Models
(5)
Processing
(4)
Architectures
(3)
Core Methods
(3)
Knowledge & Reasoning
(2)
Reinforcement Learning
(2)
Keywords
unsupervised learning
(5)
self-supervised learning
(4)
slot attention
(3)
representation learning
(3)
novel view synthesis
(3)
object-centric learning
(3)
neural network
(3)
physical reasoning
(2)
diffusion model
(2)
object-centric representation
(2)
scene understanding
(2)
human evaluation
(2)
vision-language model
(2)
expectation maximization
(2)
text-to-image generation
(2)
3d scene representation
(2)
object discovery
(2)
prompt engineering
(1)
vision transformer
(1)
interpretability
(1)
Papers
CulturalFrames: Assessing Cultural Expectation Alignment in Text-to-Image Models and Evaluation Metrics
EMNLP 2025
Direct Motion Models for Assessing Generated Videos
ICML 2025
DreamSync: Aligning Text-to-Image Generation with Image Understanding Feedback
NAACL 2025
Benchmarking Vision Language Models for Cultural Understanding
EMNLP 2024
DORSal: Diffusion for Object-centric Representations of Scenes et al.
ICLR 2024
DyST: Towards Dynamic Neural Scene Representations on Real-World Videos
ICLR 2024
Moving Off-the-Grid: Scene-Grounded Video Representations
NeurIPS 2024
Neural Assets: 3D-Aware Multi-Object Scene Synthesis with Image Diffusion Models
NeurIPS 2024
Invariant Slot Attention: Object Discovery with Slot-Centric Reference Frames
ICML 2023
Scaling Vision Transformers to 22 Billion Parameters
ICML 2023
Test-time Adaptation with Slot-Centric Models
ICML 2023
Exploring through Random Curiosity with General Value Functions
NeurIPS 2022
Object Scene Representation Transformer
NeurIPS 2022
SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videos
NeurIPS 2022
Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks
ICLR 2021
Hierarchical Relational Inference
AAAI 2021
Unsupervised Object Keypoint Learning using Local Spatial Predictability
ICLR 2021
Improving Generalization in Meta Reinforcement Learning using Learned Objectives
ICLR 2020
Are Disentangled Representations Helpful for Abstract Visual Reasoning?
NeurIPS 2019
Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions
ICLR 2018
Neural Expectation Maximization
NeurIPS 2017