Joni Pajarinen

Efficient Reinforcement Learning by Guiding World Models with Non-Curated Data

Pareto-Conditioned Diffusion Models for Offline Multi-Objective Optimization

GoalZero: Model-based Hierarchical Self-Play for Sequential Stochastic Combinatorial Optimization

Contextual Latent World Models for Offline Meta Reinforcement Learning

Cooperative Multi-Agent Planning with Adaptive Skill Synthesis

Egocentric Cross-Embodiment Video Editing via Dual Contrastive Representation Learning

Smoothing Slot Attention Iterations and Recurrences

Controllable Generative Trajectory Prediction via Weak Preference Alignment

Atrous Learning for Diffusion Models

MetaSlot: Break Through the Fixed Number of Slots in Object-Centric Learning

Monte-Carlo Tree Search with Uncertainty Propagation via Optimal Transport

Discrete Codebook World Models for Continuous Control

Multi-Scale Fusion for Object Representation

Hierarchical Reinforcement Learning with Uncertainty-Guided Diffusional Subgoals

Learning Progress Driven Multi-Agent Curriculum

Uncertainty-Regularized Diffusional Subgoals for Hierarchical Reinforcement Learning