Denis Blessing

I am a third year PhD student in the Autonomous Learning Robots (ALR) Lab at the Karlsruhe Institute of Technology (KIT), supervised by Gerhard Neumann. My research focuses on variational inference and sampling methods, with a focus on diffusion models. Prior to this, I completed my Master's Degree in Computer Science at KIT, where my thesis focused on imitation learning of diverse skills.

Contact: denis.blessing@kit.edu

List of selected publications (* denotes equal contribution)

2025

ICML

DIME: Diffusion-Based Maximum Entropy Reinforcement Learning

Onur Celik, Zechu Li, Denis Blessing, Ge Li, Daniel Palenicek, Jan Peters, Georgia Chalvatzaki, and Gerhard Neumann

42st International Conference on Machine Learning, 2025

PDF

.
ICLR

Underdamped Diffusion Bridges with Applications to Sampling

Denis Blessing^*, Julius Berner^*, Lorenz Richter^*, and Gerhard Neumann

13th International Conference on Learning Representations, 2025

PDF

.
ICLR

End-to-end Learning of Gaussian Mixture Priors for Diffusion Sampler

Denis Blessing, Xiaogang Jia, and Gerhard Neumann

13th International Conference on Learning Representations, 2025

PDF

.
ICLR

Sequential Controlled Langevin Diffusions

Junhua Chen^*, Lorenz Richter^*, Julius Berner^*, Denis Blessing^*, Gerhard Neumann, and Anima Anandkumar

13th International Conference on Learning Representations, 2025

PDF

.

2024

NeurIPS

Variational Distillation of Diffusion Policies into Mixture of Experts

Hongyi Zhou, Denis Blessing, Ge Li, Onur Celik, Xiaogang Jia, Gerhard Neumann, and Rudolf Lioutikov

38th Conference on Neural Information Processing Systems, 2024

PDF CODE

.
ICML

Beyond ELBOs: A Large-Scale Evaluation of Variational Methods for Sampling

Denis Blessing, Xiaogang Jia, Johannes Esslinger, Francisco Vargas and Gerhard Neumann

41st International Conference on Machine Learning, 2024

PDF CODE

Monte Carlo methods, Variational Inference, and their combinations play a pivotal role in sampling from intractable probability distributions. However, current studies lack a unified evaluation framework, relying on disparate performance measures and limited method comparisons across diverse tasks, complicating the assessment of progress and hindering the decision-making of practitioners. In response to these challenges, our work introduces a benchmark that evaluates sampling methods using a standardized task suite and a broad range of performance criteria. Moreover, we study existing metrics for quantifying mode collapse and introduce novel metrics for this purpose. Our findings provide insights into strengths and weaknesses of existing sampling methods, serving as a valuable reference for future developments. The code is publicly available here.
ICLR

Transport meets Variational Inference: Controlled Monte Carlo Diffusions

Francisco Vargas, Shreyas Padhy, Denis Blessing and Nikolas Nüsken

12th International Conference on Learning Representations, 2024

PDF CODE

Connecting optimal transport and variational inference, we present a principled and systematic framework for sampling and generative modelling centred around divergences on path space. Our work culminates in the development of the \emph{Controlled Monte Carlo Diffusion} sampler (CMCD) for Bayesian computation, a score-based annealing technique that crucially adapts both forward and backward dynamics in a diffusion model. On the way, we clarify the relationship between the EM-algorithm and iterative proportional fitting (IPF) for Schr{ö}dinger bridges, deriving as well a regularised objective that bypasses the iterative bottleneck of standard IPF-updates. Finally, we show that CMCD has a strong foundation in the Jarzinsky and Crooks identities from statistical physics, and that it convincingly outperforms competing approaches across a wide array of experiments.
ICLR

Towards Diverse Behaviors: A Benchmark for Imitation Learning with Human Demonstrations

Xiaogang Jia, Denis Blessing, Xinkai Jiang, Moritz Reuss, Atalay Donat, Rudolf Lioutikov, and Gerhard Neumann

12th International Conference on Learning Representations, 2024

PDF CODE

Imitation learning with human data has demonstrated remarkable success in teaching robots in a wide range of skills. However, the inherent diversity in human behavior leads to the emergence of multi-modal data distributions, thereby presenting a formidable challenge for existing imitation learning algorithms. Quantifying a model's capacity to capture and replicate this diversity effectively is still an open problem. In this work, we introduce simulation benchmark environments and the corresponding Datasets with Diverse human Demonstrations for Imitation Learning (D3IL), designed explicitly to evaluate a model's ability to learn multi-modal behavior. Our environments are designed to involve multiple sub-tasks that need to be solved, consider manipulation of multiple objects which increases the diversity of the behavior and can only be solved by policies that rely on closed loop sensory feedback. Other available datasets are missing at least one of these challenging properties. To address the challenge of diversity quantification, we introduce tractable metrics that provide valuable insights into a model's ability to acquire and reproduce diverse behaviors. These metrics offer a practical means to assess the robustness and versatility of imitation learning algorithms. Furthermore, we conduct a thorough evaluation of state-of-the-art methods on the proposed task suite. This evaluation serves as a benchmark for assessing their capability to learn diverse behaviors. Our findings shed light on the effectiveness of these methods in tackling the intricate problem of capturing and generalizing multi-modal human behaviors, offering a valuable reference for the design of future imitation learning algorithms.

2023

NeurIPS

Information Maximizing Curriculum: A Curriculum-Based Approach for Imitating Diverse Skills

Denis Blessing, Onur Celik, Xiaogang Jia, Moritz Reuss, Maximilian Xiling, Rudolf Lioutikov, and Gerhard Neumann

37th Conference on Neural Information Processing Systems, 2023

PDF CODE

Imitation learning uses data for training policies to solve complex tasks. However, when the training data is collected from human demonstrators, it often leads to multimodal distributions because of the variability in human actions. Most imitation learning methods rely on a maximum likelihood (ML) objective to learn a parameterized policy, but this can result in suboptimal or unsafe behavior due to the mode-averaging property of the ML objective. In this work, we propose Information Maximizing Curriculum, a curriculum-based approach that assigns a weight to each data point and encourages the model to specialize in the data it can represent, effectively mitigating the mode-averaging problem by allowing the model to ignore data from modes it cannot represent. To cover all modes and thus, enable diverse behavior, we extend our approach to a mixture of experts (MoE) policy, where each mixture component selects its own subset of the training data for learning. A novel, maximum entropy-based objective is proposed to achieve full coverage of the dataset, thereby enabling the policy to encompass all modes within the data distribution. We demonstrate the effectiveness of our approach on complex simulated control tasks using diverse human demonstrations, achieving superior performance compared to state-of-the-art methods.