Denis Blessing

PhD student at Karlsruhe Institute of Technology, Germany - Working on variational inference and sampling

[Michael Albergo @msalbergo]

🌻 One final paper for 2025 :) really excited about this work with @PPotaptchik and @brianlee_lck. We show that there is an analytical ODE connecting a flow/map/diffusion model to its tilted alternative.

Allows us to turn fine-tuning into an iterative regression! Works well and has nice scaling properties :) check it out, and stay tuned for more!

[Yuanqi Du @YuanqiD]

Best paper award "Learning Boltzmann Generators via Constrained Mass Transport"

@DenBless94 and Christopher von Klitzing

https://t.co/S4NX8kzGeh

[Lorenz Richter @lorenz_richter]

Presenting our spotlight paper on trust regions for optimal control at NeurIPS, https://t.co/YS1VkDYBEB. We show that KL-equipspaced measure transport can be interpreted as geometric annealing with adaptive step sizes, leading to major performance gains on hard control problems.

[Denis Blessing @DenBless94]

If you're at NeurIPS this week and are interested in stochastic optimal control (SOC) and diffusion models come by our poster on Friday, Dec 6 • 4:30 - 7:30 PM

Joint work with, @julberner, @cdomingoenrich, @YuanqiD, @ArashVahdat and Gerhard Neumann.

[Jiajun He @JiajunHe614]

When sampling from multimodal distributions, we rely on multiple temperatures to balance exploration and exploitation.

Can we bring this idea into the world of diffusion-based neural samplers?

👉Check out our ICML paper to see how this idea can lead to significant improvements!

[Lorenz Richter @lorenz_richter]

Excited for #ICML2025 in Vancouver! On Thursday morning, I'm presenting our paper (https://t.co/8G0YZVoTz9) on a critical issue in reinforcement learning: how to correctly handle random time horizons. We've identified incorrect formulas and offer a solution. Let's chat, write me!

[Kirill Neklyudov @k_neklyudov]

1/ Where do Probabilistic Models, Sampling, Deep Learning, and Natural Sciences meet? 🤔 The workshop we’re organizing at #NeurIPS2025!

📢 FPI@NeurIPS 2025: Frontiers in Probabilistic Inference – Learning meets Sampling

Learn more and submit → https://t.co/gDt9lFzPBv

Organizers: @tara_aksa @msalbergo @bose_joey @marylougab @theh2o64 @guanhorng_liu Grant Rotskoff @EvaSmorodina @AlexanderTong7

[Onur Celik @onclk_]

I am happy to share that our work ‘DIME: Diffusion-Based Maximum Entropy Reinforcement Learning’ has been accepted to ICML 2025. Many thanks to my colleagues and collaborators @softraeh, @DenBless94, @BruceGeLi, @DPalenicek, @Jan_R_Peters, @GeorgiaChal,@geri_neumann

[Lorenz Richter @lorenz_richter]

Our new work https://t.co/WLBk0Y5KrK extends the theory of diffusion bridges to degenerate noise settings, including underdamped Langevin dynamics (with @DenBless94, @julberner). This enables more efficient diffusion-based sampling with substantially fewer discretization steps.