Philipp Becker

PhD student at the Autonomous Learning Robots lab at KIT. Working with probabilistic models for modeling time series and multi-modality.

[Autonomous Learning Robots Lab @alr_lab_kit]

Excited to announce that today we will present four papers at the ICML workshops :

📐 @NiklasFreymuth will showcase “Iterative Sizing Field Prediction for Adaptive Mesh Generation From Expert Demonstrations” @ the AI for Science Workshop.

Stay tuned! #ICML2024 #MachineLearning

[Philipp Becker @philippb06]

@sai_prasanna @artemZholus @apsarathchandar @danijarh Thanks for tagging me. I think @artemZholus makes a good point in that the graphical model induces an inductive bias and thus it depends on the problem. In my experience, using tighter lower bounds is more important when there is a lot of uncertainty in the system.

[Philipp Becker @philippb06]

🧩 How does #BayesianDeepLearning handle the wild terrain of real-world o.o.d. data? Novel work from our student Florian Seligmann with the #WILDS 🐾 datasets: Exploring transformers, finetuning and last-layer methods while ensembling it all! #NeurIPS2023 https://t.co/WmFQjTff8F

[Niklas Freymuth @NiklasFreymuth]

Feeling the stress of slow simulations?⏰Let Adaptive Swarm Mesh Refinement (ASMR) soothe your computational woes! Our method produces high-quality mesh refinements that offer up to 100x speedup.🎧📊
https://t.co/nfxW1qd3Zm
https://t.co/s13qaa4wps
Catch us at #NeurIPS2023!

[Vaisakh Shaj🏳️‍🌈 @vaisakhsshaj]

I'm super excited about this PhD work of mine, "Multi Time Scale World Models", which has been accepted to Neurips 2023 as a spotlight (Top 3% of all submitted papers). Details are in the thread below. (1/6)

[Philipp Becker @philippb06]

For more details, check out our paper: https://t.co/Bz9nCYEXy1 , Code available at https://t.co/4gJ4V8BdX6 .

Many thanks also to the reviewers, action editor, and organizers of @TmlrOrg . We really like the new format!

[Philipp Becker @philippb06]

I am happy to share our recent work, “On Uncertainty in Deep State Space Models for Model-Based Reinforcement Learning”, ( https://t.co/PWazDxVfBg ) published at TMLR. With @geri_neumann

Let me summarize our key contributions in a short thread:

[Philipp Becker @philippb06]

As a more principled alternative, we propose the VRKN. It uses a smoothing approach for an inference that considers future observations and explicitly models epistemic uncertainty. Thus, it gives correct aleatoric uncertainty estimates and improves performance in many cases.

[Vaisakh Shaj🏳️‍🌈 @vaisakhsshaj]

Excited to present our work on "Hidden Parameter RSSMs for Changing Dynamics Scenarios" at ICLR 2022 on 27 April. 🙂 We learn a deep multi-task Kalman Filter than can adapt to non-stationary environments. https://t.co/0Jw2Df8FDn

@geri_neumann @dtrbchlr @philippb06 @alr_lab_kit

[Onur Celik @onclk_]

Our work ‚Specializing Versatile Skill Libraries using Local Mixture of Experts‘ is accepted at #CoRL2021 🙂.
https://t.co/Vmw8CRhjJL
Thanks to Prof. Neumann(@alr_kit), Zhou, Ge Li and Philipp Becker (@philippb06).

[Vaisakh Shaj🏳️‍🌈 @vaisakhsshaj]

Our work 'Action Conditional Recurrent Kalman Network' is accepted at #CoRL2020. Excited to share more details at the virtual conf. :)

Thanks to Prof Gerhard Neuman(@alr_kit) and our collaborators @philippb06, @dtrbchlr, @MarcHanheide, @LCAS_UoL.

https://t.co/pyAdnQwymy

[Philipp Becker @philippb06]

@MLSS_Tuebingen @MPI_IS Is Maximum Likelihood the right objective for multi-modal data? Especially versatile behavior? And how can we efficiently use alternative objectives?
https://t.co/DkfxEowbUa