Marin Vlastelica
9 papers · 2020–2025 · 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 🏃 Academic Marathon · Sprint 🗺️ Taxonomy Completionist (21) 🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Silver
🔥
Unstoppable · Bronze
🗃️
Keyword Collector
(58)
Top co-authors
Research topics
Keywords
image retrieval
(2)
robustness
(1)
entropy maximization
(1)
graph matching
(1)
epistemic uncertainty
(1)
object detection
(1)
model-based learning
(1)
task-oriented dialogue
(1)
symmetry
(1)
model predictive control
(1)
gradient descent
(1)
trajectory optimization
(1)
model-based reinforcement learning
(1)
convergence
(1)
variational inference
(1)
mirror descent
(1)
zero-order optimization
(1)
amortized inference
(1)
score function
(1)
deep reinforcement learning
(1)
Papers
Divide, Discover, Deploy: Factorized Skill Learning with Symmetry and Style Priors
CoRL 2025
Provable Maximum Entropy Manifold Exploration via Diffusion Models
ICML 2025
Causal Action Influence Aware Counterfactual Data Augmentation
ICML 2024
Backpropagation through Combinatorial Algorithms: Identity with Projection Works
ICLR 2023
Taming Continuous Posteriors for Latent Variational Dialogue Policies
AAAI 2023
Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations
CoRL 2022
Neuro-algorithmic Policies Enable Fast Combinatorial Generalization
ICML 2021
Risk-Averse Zero-Order Trajectory Optimization
CoRL 2021
Optimizing Rank-Based Metrics With Blackbox Differentiation
CVPR 2020