Michal Rolinek
12 papers · 2018–2021 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (25) π Interdisciplinary Bridge π Conference Polyglot (7) π Renaissance Researcher (8) π§ Keyword Pioneer
π
Interdisciplinary Bridge
π§
Keyword Pioneer
π€
Dynamic Duo
(10)
π
Trend Setter
ποΈ
Keyword Collector
(57)
π
Century Club
(12)
β‘
Prolific Year
(5)
Conferences
CVPR (3)
ICML (3)
NIPS (2)
CORL (1)
ECCV (1)
ICCV (1)
ICLR (1)
Top co-authors
Keywords
model-based reinforcement learning
(2)
disentangled representation
(2)
variational autoencoder
(2)
combinatorial optimization
(2)
average precision
(2)
principal component analysis
(1)
feature extraction
(1)
representation learning
(1)
information retrieval
(1)
model-based learning
(1)
deep learning
(1)
message passing
(1)
gradient descent
(1)
trajectory optimization
(1)
stochastic gradient descent
(1)
multiple object tracking
(1)
integer programming
(1)
object detection
(1)
sampling efficiency
(1)
learning to rank
(1)
Papers
Planning from Pixels in Environments with Combinatorially Hard Search Spaces
NIPS 2021
CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraints
ICML 2021
Making Higher Order MOT Scalable: An Efficient Approximate Solver for Lifted Disjoint Paths
ICCV 2021
Demystifying Inductive Biases for (Beta-)VAE Based Architectures
ICML 2021
Neuro-algorithmic Policies Enable Fast Combinatorial Generalization
ICML 2021
Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers
ECCV 2020
Sample-efficient Cross-Entropy Method for Real-time Planning
CORL 2020
Optimizing Rank-Based Metrics With Blackbox Differentiation
CVPR 2020
Differentiation of Blackbox Combinatorial Solvers
ICLR 2020
Variational Autoencoders Pursue PCA Directions (by Accident)
CVPR 2019
L4: Practical loss-based stepsize adaptation for deep learning
NIPS 2018
Efficient Optimization for Rank-Based Loss Functions
CVPR 2018