collaborators

6 papers

cs.LG2025

Efficient Image Restoration with State-Dependent Forward Diffusion

Ziwei Luo, Fredrik K. Gustafsson, Jens Sjölund +3

This paper proposes to perform image restoration through a state-dependent mean-reverting forward diffusion (FoD) process. In contrast to traditional diffusion-based approaches tha…

eess.SY2025

Minimal positive Markov realizations

Hamed Taghavian, Jens Sjölund

Finding a positive state-space realization with the minimum dimension for a given transfer function is an open problem in control theory. In this paper, we focus on positive realiz…

cs.LG2025

Exploring Modularity of Agentic Systems for Drug Discovery

Laura van Weesep, Samuel Genheden, Ola Engkvist +1

Large-language models (LLMs) and agentic systems present exciting opportunities to accelerate drug discovery. In this study, we examine the modularity of LLM-based agentic systems…

math.OC2025

Symmetrizable systems

Hamed Taghavian, Jens Sjölund

Transforming an asymmetric system into a symmetric system makes it possible to exploit the simplifying properties of symmetry in control problems. We define and characterize the fa…

cs.AI2025

Real-Time Diffusion Policies for Games: Enhancing Consistency Policies with Q-Ensembles

Ruoqi Zhang, Ziwei Luo, Jens Sjölund +3

Diffusion models have shown impressive performance in capturing complex and multi-modal action distributions for game agents, but their slow inference speed prevents practical depl…

cs.LG2025

Improving Sample Efficiency in Multi-Agent Reinforcement Learning for Simulated Football Games via Exploration

Amir Baghi, Jens Sjölund, Jens Sjölund +4

Multi-agent reinforcement learning has shown promise in learning cooperative behaviors in team-based environments. However, such methods often demand extensive training time, which…