Christian Gumbsch (@cgumbsch) 's Twitter Profile
Christian Gumbsch

@cgumbsch

PhD student | @uni_tue & @MPI_IS & @tudresden_de | world models and sensorimotor abstractions for RL and cognitive modeling |👾🤖🧠

ID: 1453027334135681030

linkhttps://cgumbsch.github.io calendar_today26-10-2021 15:54:51

45 Tweet

172 Followers

143 Following

Efstratios Gavves (@egavves) 's Twitter Profile Photo

📢📢Excited to announce the 1st Causal &Object-Centric Representations for Robotics Full-day Workshop at @CVPRCall Abstracts deadline 4/28 W. amazing Francesco Locatello Roozbeh Mottaghi Andrii Zadaianchuk 🇺🇦 Phillip Lippe @Priyam8Parashar Siddharth Patki R.Desai corrworkshop.github.io/submit.html

Pietro Mazzaglia (@pietromazzaglia) 's Twitter Profile Photo

🚨Introducing GenRL! An embodied AI agent that learns multimodal foundation world models 🌍 By connecting the multimodal knowledge of foundation models with the embodied knowledge of world models for RL, GenRL enables turning vision and language prompts into actions!

Núria Armengol (@nriaarmengol2) 's Twitter Profile Photo

Tired of causally confused agents when learning from offline datasets? We propose 🚣🏼‍♀️CAIAC🚣🏼‍♀️, a method for counterfactual data augmentation to improve the robustness of offline learning agents against extreme distributional shifts at test time. 🧵

IMOL Workshop | NeurIPS 2024 (@imolneurips2024) 's Twitter Profile Photo

🚨We're back!🚨 Excited to announce The 2nd IMOL Workshop at #neurips2024! Send us your 📜newest work📜on learning & exploration in artificial and biological agents. #CFP at imol-workshop.github.io/pages/call/ 🔄Please share widely & stay tuned for more programming announcements!

🚨We're back!🚨 Excited to announce The 2nd IMOL Workshop at #neurips2024! 

Send us your 📜newest work📜on learning & exploration in artificial and biological agents. #CFP at imol-workshop.github.io/pages/call/

🔄Please share widely & stay tuned for more programming announcements!
Marin Vlastelica 🤖🎸 (@vlastelicap) 's Twitter Profile Photo

Were you ever wondering why there are little-to-no diverse offline imitation learning algorithms 🤔? Then we've got something 4 you! Our paper, "Offline Diversity Maximization under Imitation Constraints" is being presented today at RLC2024 🎇! 🧵 rlj.cs.umass.edu/2024/papers/Pa…

Were you ever wondering why there are little-to-no diverse offline imitation learning algorithms 🤔? Then we've got something 4 you! Our paper, "Offline Diversity Maximization under Imitation Constraints" is being presented today at RLC2024 🎇! 🧵

rlj.cs.umass.edu/2024/papers/Pa…
Asya Achimova (@aachimova) 's Twitter Profile Photo

#Context plays a critical role not only in interpreting language but many other cognitive processes. In a new paper, we propose that context-sensitivity is a core feature of human memory that enables flexible planning, #generalization, and decision making doi.org/10.1016/j.neub…

#Context plays a critical role not only in interpreting language but many other cognitive processes. In a new paper, we propose that context-sensitivity is a core feature of human memory that enables flexible planning, #generalization, and decision making doi.org/10.1016/j.neub…
Andrii Zadaianchuk 🇺🇦 (@zadaianchukml) 's Twitter Profile Photo

How to represent dynamic real-world data both consistently and efficiently, while reflecting the compositional object-centric structure of the world? Contrast your slots! ...with our new SlotContrast method(🚀#CVPR2025 Oral🚀)! 🌐website: slotcontrast.github.io 🧵🧵🧵 1/n

Cansu Sancaktar (@ccansusancaktar) 's Twitter Profile Photo

✨Introducing SENSEI✨ We bring semantically meaningful exploration to model-based RL using VLMs. With intrinsic rewards for novel yet useful behaviors, SENSEI showcases strong exploration in MiniHack, Pokémon Red & Robodesk. Accepted at ICML 2025🎉 Joint work with Christian Gumbsch 🧵

Marco Bagatella (@mar_baga) 's Twitter Profile Photo

When multiple tasks need improvements, fine-tuning a generalist policy becomes tricky. How do we allocate a demonstration budget across a set of tasks of varied difficulty and familiarity? We are presenting a possible solution at ICML on Wednesday! (1/3)

When multiple tasks need improvements, fine-tuning a generalist policy becomes tricky. How do we allocate a demonstration budget across a set of tasks of varied difficulty and familiarity?

We are presenting a possible solution at ICML on Wednesday!

(1/3)
Georg Martius (@gmartius) 's Twitter Profile Photo

Sergey Levine was just presenting in the Exploration in AI @ #ICML2025 and promoted that exploration needs to be grounded, and that VLMs are a good source ;-) Check our paper below 👇

<a href="/svlevine/">Sergey Levine</a> was just presenting in the Exploration in AI @ #ICML2025 and promoted that exploration needs to be grounded, and that VLMs are a good source ;-) Check our paper below
👇
Turan Orujlu (@turanorujlu) 's Twitter Profile Photo

Reframing attention as an RL problem for causal discovery AI models like GNNs & Transformers can struggle with dynamic causal reasoning. Our work introduces the Causal Process Model (CPM), which reframes attention as an RL problem. Agents dynamically build sparse causal graphs.