5 papers
REKI: Registering Knowledge in VLAs
Juliette Marrie, Paul Pacaud, Adrien Ramanana Rahary +2
We introduce REKI, a 2.4B vision-language-action model (VLA) pretrained exclusively on public data that sets a new Pareto frontier between performance and model size: on LIBERO-Plu…
Diffusable Latents from Structure-Agnostic Distillation
Adrien Ramanana Rahary, Nicolas Dufour, Patrick Pérez +1
Distilling pretrained foundation models into an autoencoder bottleneck improves latent diffusability, enabling diffusion models to converge faster and reach higher sample quality.…
Multiplayer Interactive World Models with Representation Autoencoders
Anthony Hu, Václav Volhejn, Adrien Ramanana Rahary +24
We introduce the first multiplayer world model for highly dynamic environments governed by complex physical interactions. Whereas single-player world models treat the other agents…
One View Is Enough: In-the-Wild Monocular Pretraining for Novel View Generation
Adrien Ramanana Rahary, Nicolas Dufour, Patrick Perez +1
Monocular novel-view synthesis has long required multi-view image pairs for supervision, limiting training to a narrow set of purpose-built datasets. We propose in-the-wild monocul…
LACONIC: A 3D Layout Adapter for Controllable Image Creation
Léopold Maillard, Tom Durand, Adrien Ramanana Rahary +1
Existing generative approaches for guided image synthesis of multi-object scenes typically rely on 2D controls in the image or text space. As a result, these methods struggle to ma…