Autonomous Learning Robots Lab

🧠 Onur Celik (@onclk_ ) presents his ICML publication “Acquiring Diverse Skills using Curriculum RL with Mixture of Experts” at the ARLET workshop.

🔍 Philipp Becker (@philippb06) will also be at ARLET, presenting “Combining Reconstruction and Contrastive Methods for Multimodal Representations in RL” and his preliminary work on “KalMamba: Towards Efficient Probabilistic State Space Models for RL under Uncertainty.”

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

Having great pleasure from presenting our work in temporally correlated RL (github.com/BruceGeLi/TCE_…) in #ICLR2024 and enjoying a lot of fun in #Vienna

🧩 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 arxiv.org/abs/2306.12306

📢Interested in 6D pose estimation of novel objects w/o mesh models and gt-masks from clutter scenes? 🤖Check out our #CORL2023 paper "SA6D: Self-Adaptive Few-Shot 6D Pose Estimator for Novel and Occluded Objects"🎉 🌐sites.google.com/view/sa6d @Bosch_AI @alr_lab_kit @corl_conf

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.🎧📊 arxiv.org/abs/2304.00818 github.com/NiklasFreymuth… Catch us at #NeurIPS2023!

Excited to share 4 accepted NeurIPS papers from our team. Amazing work and congratz to the team! Looking forward to seeing everyone in New Orleans :)

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)

I am happy to share our recent work, “On Uncertainty in Deep State Space Models for Model-Based Reinforcement Learning”, ( openreview.net/pdf?id=UQXdQyo… ) published at TMLR. With @geri_neumann Let me summarize our key contributions in a short thread:

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. arxiv.org/abs/2010.10201

Our work ‚Specializing Versatile Skill Libraries using Local Mixture of Experts‘ is accepted at #CoRL2021 🙂. openreview.net/forum?id=j3Rgu… Thanks to Prof. Neumann(@alr_kit), Zhou, Ge Li and Philipp Becker (@philippb06).

Our work 'What Matters for Meta-Learning Vision Regression Tasks?' is accepted at #CVPR2022. Check it out if you are interested :) Codes and datasets will be available soon. Thanks to professor @geri_neumann and our collaborators Hanna Ziesche, @VienNgo4, @volppmichael.

Onur's recent work on Versatile Skill Learning, published at @corl_conf 2021. Congrats! 🎉