42 papers
Momba: Network Modernization Improves Multi-Objective Reinforcement Learning
Adam Štafa, Santeri Heiskanen, Petr Novotný +1
Recent advances in deep reinforcement learning (RL) have shown that improving neural network architectures can yield substantial gains in sample efficiency and asymptotic performan…
Embodied Active Learning under Limited Annotation and Navigation Budget for Object Detection
Hadrien Crassous, Mohamed Yassine Kabouri, Minahil Raza +2
This paper studies how to adapt a computer vision object detector to an unknown environment under both a robot navigation time and annotation budget constraint. Our approach select…
HSA: Hierarchical Slot Attention for Multi-granularity Scene-Decomposition
Neelu Madan, Rongzhen Zhao, Andreas Mogelmose +4
Slot attention is a powerful framework for object-centric learning, decomposing visual scenes into latent slots through iterative competitive attention. However, existing methods s…
Efficient Reinforcement Learning by Guiding World Models with Non-Curated Data
Yi Zhao, Aidan Scannell, Wenshuai Zhao +7
Leveraging offline data is a promising way to improve the sample efficiency of online reinforcement learning (RL). This paper expands the pool of usable data for offline-to-online…
ReMoBot: Retrieval-Based Few-Shot Imitation Learning for Mobile Manipulation with Vision Foundation Models
Yuying Zhang, Wenyan Yang, Francesco Verdoja +2
Imitation learning (IL) algorithms typically distill demonstrations into parametric policies to mimic expert behavior. However, with limited data and partial observability, such as…
Internalizing Temporal Consistency in Video Object-Centric Learning without Explicit Regularization
Rongzhen Zhao, Zhiyuan Li, Juho Kannala +1
Video Object-Centric Learning (OCL) aims to represent objects as \textit{slot} vectors and maintain their consistency across frames. Slot-Slot Contrastive (SSC) loss has become the…