← Search

Karl Johansson

4 accepted papers

2026

Are Object-Centric Representations Better At Compositional Generalization?

ICML 2026poster

Compositional generalization, the ability to reason about novel combinations of familiar concepts, is fundamental to human cognition and a critical challenge for machine learning. Object-centric (OC) representations, which encode a scene as a set of objects, are often argued to support such generali…

Cited by 0SourceScholar
2026

Efficient Tail-Aware Generative Optimization via Flow Model Fine-Tuning

ICML 2026poster

Fine-tuning pre-trained diffusion and flow models to optimize downstream utilities is central to real-world deployment. Existing entropy-regularized methods primarily maximize expected reward, providing no mechanism to shape tail behavior. However, tail control is often essential: the lower tail det…

Cited by 0SourceScholar
2026

Noisy-Space Policy Gradient for Diffusion Policies in Offline Reinforcement Learning

ICML 2026poster

Diffusion policies offer a powerful and expressive parameterization for continuous control. Yet, their integration with reinforcement learning remains conceptually and algorithmically challenging. In this work, we address this gap by introducing a noisy-space action-value (Q-)function that assigns v…

Cited by 0SourceScholar
2021

Regret and Cumulative Constraint Violation Analysis for Online Convex Optimization with Long Term Constraints

ICML 2021oral

This paper considers online convex optimization with long term constraints, where constraints can be violated in intermediate rounds, but need to be satisfied in the long run. The cumulative constraint violation is used as the metric to measure constraint violations, which excludes the situation tha…

Cited by 52SourcePDFScholar