1 citations · 1 across the 6 of their papers we have counts for
6 papers
Slot-RAE: Streamlining Object-Centric Learning via Direct Representation Auto-Encoders
Alexandre Chapin, Emmanuel Dellandrea, Liming Chen
Deploying object-centric models for real-world scene understanding typically requires complex pipelines to achieve both robust scene decomposition and high-fidelity generation. Rec…
Spotlighting Task-Relevant Features: Object-Centric Representations for Better Generalization in Robotic Manipulation
Alexandre Chapin, Bruno Machado, Emmanuel Dellandrea +2
The generalization capabilities of robotic manipulation policies are heavily influenced by the choice of visual representations. Existing approaches typically rely on representatio…
STORM: Slot-based Task-aware Object-centric Representation for robotic Manipulation
Alexandre Chapin, Emmanuel Dellandréa, Liming Chen
Visual foundation models provide strong perceptual features for robotics, but their dense representations lack explicit object-level structure, limiting robustness and controllabil…
Jack of All Trades, Master of Some, a Multi-Purpose Transformer Agent
Quentin Gallouédec, Edward Beeching, Clément Romac +1
The search for a general model that can operate seamlessly across multiple domains remains a key goal in machine learning research. The prevailing methodology in Reinforcement Lear…
Learning Less Generalizable Patterns with an Asymmetrically Trained Double Classifier for Better Test-Time Adaptation
Thomas Duboudin, Emmanuel Dellandréa, Corentin Abgrall +2
Deep neural networks often fail to generalize outside of their training distribution, in particular when only a single data domain is available during training. While test-time ada…
Cell-Free Latent Go-Explore
Quentin Gallouédec, Emmanuel Dellandréa
In this paper, we introduce Latent Go-Explore (LGE), a simple and general approach based on the Go-Explore paradigm for exploration in reinforcement learning (RL). Go-Explore was i…