6 citations · 6 across the 14 of their papers we have counts for
17 papers
Rationale Distribution Distillation via Flow Matching for Distributional Continuous Latent Reasoning
Mingyeong Kim, Gyusang Cho, Juho Lee +1
Sampling multiple chain-of-thought rationales from a language model can uncover correct solutions missed by a single attempt. However, these rationales are typically lengthy, makin…
Better Slots, Better Worlds: Representation Quality & Robustness in Object-Centric World Models
Shukrullo Nazirjonov, Sai Prasanna, Anna Manasyan +1
Learning world models from offline trajectories enables agents to accomplish different tasks through planning. Object-centric (OC) representations, which decompose a scene into a s…
Shift & Drift: A Zero-Shot Benchmark for Generalizable and Robust Autonomous Driving Motion Planning
Alessandro Canevaro, Hang Yu, Julian Schmidt +5
While closed-loop motion planners trained on large-scale, object-level datasets, e.g., nuPlan, demonstrate strong in-distribution (ID) performance, their generalization to novel ur…
Scaling Laws and Tradeoffs in Recurrent Networks of Expressive Neurons
Aaron Spieler, Georg Martius, Anna Levina
Cortical neurons are complex, multi-timescale processors wired into recurrent circuits, shaped by long evolutionary pressure under stringent biological constraints. Mainstream mach…
Drifting Fields are not Conservative
Leonard T. Franz, Sebastian Hoffmann, Tim Weiland +2
Drifting models have recently gained attention for generating high-quality samples in a single forward pass. During training, they learn a push-forward map by following a vector-va…
GASP: Guided Asymmetric Self-Play For Coding LLMs
Swadesh Jana, Cansu Sancaktar, Tomáš Daniš +3
Asymmetric self-play has emerged as a promising paradigm for post-training large language models, where a teacher continually generates questions for a student to solve at the edge…
Soft Forward-Backward Representations for Zero-shot Reinforcement Learning with General Utilities
Marco Bagatella, Thomas Rupf, Georg Martius +1
Recent advancements in zero-shot reinforcement learning (RL) have facilitated the extraction of diverse behaviors from unlabeled, offline data sources. In particular, forward-backw…
Forecasting in Offline Reinforcement Learning for Non-stationary Environments
Suzan Ece Ada, Georg Martius, Emre Ugur +1
Offline Reinforcement Learning (RL) provides a promising avenue for training policies from pre-collected datasets when gathering additional interaction data is infeasible. However,…
Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies
Jiaqi Chen, Ji Shi, Cansu Sancaktar +2
Data collection is crucial for learning robust world models in model-based reinforcement learning. The most prevalent strategies are to actively collect trajectories by interacting…
Test-time Offline Reinforcement Learning on Goal-related Experience
Marco Bagatella, Mert Albaba, Jonas Hübotter +2
Foundation models compress a large amount of information in a single, large neural network, which can then be queried for individual tasks. There are strong parallels between this…
A Smooth Analytical Formulation of Collision Detection and Rigid Body Dynamics With Contact
Onur Beker, Nico Gürtler, Ji Shi +4
Generating intelligent robot behavior in contact-rich settings is a research problem where zeroth-order methods currently prevail. A major contributor to the success of such method…
SENSEI: Semantic Exploration Guided by Foundation Models to Learn Versatile World Models
Cansu Sancaktar, Christian Gumbsch, Andrii Zadaianchuk +2
Exploration is a cornerstone of reinforcement learning (RL). Intrinsic motivation attempts to decouple exploration from external, task-based rewards. However, established approache…
Advancing Out-of-Distribution Detection via Local Neuroplasticity
Alessandro Canevaro, Julian Schmidt, Mohammad Sajad Marvi +3
In the domain of machine learning, the assumption that training and test data share the same distribution is often violated in real-world scenarios, requiring effective out-of-dist…
Zero-Shot Offline Imitation Learning via Optimal Transport
Thomas Rupf, Marco Bagatella, Nico Gürtler +2
Zero-shot imitation learning algorithms hold the promise of reproducing unseen behavior from as little as a single demonstration at test time. Existing practical approaches view th…
Active Fine-Tuning of Multi-Task Policies
Marco Bagatella, Jonas Hübotter, Georg Martius +1
Pre-trained generalist policies are rapidly gaining relevance in robot learning due to their promise of fast adaptation to novel, in-domain tasks. This adaptation often relies on c…
Regularity as Intrinsic Reward for Free Play
Cansu Sancaktar, Justus Piater, Georg Martius
We propose regularity as a novel reward signal for intrinsically-motivated reinforcement learning. Taking inspiration from child development, we postulate that striving for structu…
Colored Noise in PPO: Improved Exploration and Performance through Correlated Action Sampling
Jakob Hollenstein, Georg Martius, Justus Piater
Proximal Policy Optimization (PPO), a popular on-policy deep reinforcement learning method, employs a stochastic policy for exploration. In this paper, we propose a colored noise-b…