From the 1 of 9 linked papers with an AI index.
9 papers
Slot-RAE: Streamlining Object-Centric Learning via Direct Representation Auto-Encoders
Alexandre Chapin, Emmanuel Dellandrea, Liming Chen
Slot-RAE is an object‑centric model that learns to decompose and reconstruct scenes directly in the feature space of frozen visual foundation models using a diffusion transformer d…
More Structure, Not More Capacity: Object-Centric Representations for Visuomotor Imitation Learning
Yi Li, Alexandre Chapin, Liming Chen +2
Robotic manipulation policies rely on pre-trained vision models that give either a global scene embedding or a dense patch grid. Both mix task-relevant and task-irrelevant features…
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…
Spotlighting Task-Relevant Features: Object-Centric Representations for Better Generalization in Robotic Manipulation
Alexandre Chapin, Bruno Machado, Emmanuel Dellandréa +1
The generalization capabilities of robotic manipulation policies are heavily influenced by the choice of visual representations. Existing approaches typically rely on representatio…
Flowing With Purpose: Latent Action Guided Flow Matching Policies For Robotic Manipulation
Bruno Machado, Alexandre Chapin, Emmanuel Dellandrea +1
Flow matching has recently become a new standard for behavior cloning in robotic manipulation. However, state-of-the-art flow matching policies suffer from a systematic structural…
Warm-Starting Collision-Free Model Predictive Control With Object-Centric Diffusion
Arthur Haffemayer, Alexandre Chapin, Armand Jordana +4
Acting in cluttered environments requires predicting and avoiding collisions while still achieving precise control. Conventional optimization-based controllers can enforce physical…