2 papers
cs.CV2026
SlotDiT: Object-Centric Representations for Diffusion Transformers
Gjergj Plepi, Sven Behnke
Text-conditioned latent diffusion models perform strongly in video generation and are promising backbones for robotic applications. However, existing approaches rely on pixel-level…
cs.CV2025
TextOCVP: Object-Centric Video Prediction with Language Guidance
Angel Villar-Corrales, Gjergj Plepi, Sven Behnke
Understanding and forecasting future scene states is critical for autonomous agents to plan and act effectively in complex environments. Object-centric models, with structured late…