SlotDiT: Object-Centric Representations for Diffusion Transformers

• URL: http://arxiv.org/abs/2609.17414v1
• Date: Tue, 15 Sep 2026 16:38:33 GMT
• Title: SlotDiT: Object-Centric Representations for Diffusion Transformers
• Abstract summary: SlotDiT is a text-guided Diffusion Transformer (DiT) that operates in a slot-based latent space.<n>We show that using slots as DiT latents yields competitive video generation quality while consistently improving task-completion rates.<n>Our results demonstrate that object-centric structure is a powerful inductive bias for diffusion-based generative modeling in robotic environments.
• Score: 17.4778210092639
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Text-conditioned latent diffusion models perform strongly in video generation and are promising backbones for robotic applications. However, existing approaches rely on pixel-level or VAE-based latent representations that lack explicit semantic structure, leaving the impact of the representation space largely unexplored. Slot-based object-centric representations offer a structured alternative by decomposing scenes into object-level latents, or slots. While they have shown success in dynamics modeling and planning, they have not yet been explored for diffusion-based generative modeling. We introduce SlotDiT, a text-guided Diffusion Transformer (DiT) that operates in a slot-based latent space. Given a reference image and a language instruction, SlotDiT decomposes the scene into object-centric slots representing individual entities. Conditioned on the instruction and observed scene context, the model autoregressively denoises future slot trajectories to predict scene dynamics. To systematically investigate latent-space design for diffusion transformers, we compare slot-based representations against VAE-based and semantics-aligned alternatives within a unified DiT framework. Our experiments show that using slots as DiT latents yields competitive video generation quality while consistently improving task-completion rates across four robotic datasets. Furthermore, their compact representation provides a computationally efficient alternative to VAE-based and semantics-aligned latent spaces. Overall, our results demonstrate that object-centric structure is a powerful inductive bias for diffusion-based generative modeling in robotic environments. The project page is available at https://slot-dit.github.io/.

Related papers

• Slot-RAE: Streamlining Object-Centric Learning via Direct Representation Auto-Encoders [44.055446967139424]
  Slot-RAE operates directly within the continuous semantic feature space of visual foundation models.<n>It eliminates the need for VAE bottlenecks and task-agnostic generative pre-training.<n>It delivers comparable unsupervised object discovery, higher-fidelity image reconstruction, and robust zero-shot compositionality.
  arXiv  Detail & Related papers  (2026-07-13T07:47:09Z)
• Exploring Representation-Aligned Latent Space for Better Generation [86.45670422239317]
  We introduce ReaLS, which integrates semantic priors to improve generation performance.<n>We show that fundamental DiT and SiT trained on ReaLS can achieve a 15% improvement in FID metric.<n>The enhanced semantic latent space enables more perceptual downstream tasks, such as segmentation and depth estimation.
  arXiv  Detail & Related papers  (2025-02-01T07:42:12Z)
• EnerVerse: Envisioning Embodied Future Space for Robotics Manipulation [55.26713167507132]
  We introduce a generative robotics foundation model that constructs and interprets embodied spaces.<n>EnerVerse employs an autoregressive video diffusion framework to predict future embodied spaces from instructions, enhanced by a sparse context memory for long-term reasoning.<n>We present EnerVerse-D, a data engine pipeline combining the generative model with 4D Gaussian Splatting, forming a self-reinforcing data loop to reduce the sim-to-real gap.
  arXiv  Detail & Related papers  (2025-01-03T17:00:33Z)
• LaVin-DiT: Large Vision Diffusion Transformer [99.98106406059333]
  LaVin-DiT is a scalable and unified foundation model designed to tackle over 20 computer vision tasks in a generative framework.<n>We introduce key innovations to optimize generative performance for vision tasks.<n>The model is scaled from 0.1B to 3.4B parameters, demonstrating substantial scalability and state-of-the-art performance across diverse vision tasks.
  arXiv  Detail & Related papers  (2024-11-18T12:05:27Z)
• SlotDiffusion: Object-Centric Generative Modeling with Diffusion Models [47.986381326169166]
  We introduce SlotDiffusion -- an object-centric Latent Diffusion Model (LDM) designed for both image and video data. Thanks to the powerful modeling capacity of LDMs, SlotDiffusion surpasses previous slot models in unsupervised object segmentation and visual generation. Our learned object features can be utilized by existing object-centric dynamics models, improving video prediction quality and downstream temporal reasoning tasks.
  arXiv  Detail & Related papers  (2023-05-18T19:56:20Z)
• Object-Centric Slot Diffusion [30.722428924152382]
  We introduce Latent Slot Diffusion (LSD), a novel model that serves dual purposes. We demonstrate that LSD significantly outperforms state-of-the-art transformer-based decoders. We also conduct a preliminary investigation into the integration of pre-trained diffusion models in LSD.
  arXiv  Detail & Related papers  (2023-03-20T02:40:16Z)
• PnP-DETR: Towards Efficient Visual Analysis with Transformers [146.55679348493587]
  Recently, DETR pioneered the solution vision tasks with transformers, it directly translates the image feature map into the object result. Recent transformer-based image recognition model andTT show consistent efficiency gain.
  arXiv  Detail & Related papers  (2021-09-15T01:10:30Z)
• Improve Variational Autoencoder for Text Generationwith Discrete Latent Bottleneck [52.08901549360262]
  Variational autoencoders (VAEs) are essential tools in end-to-end representation learning. VAEs tend to ignore latent variables with a strong auto-regressive decoder. We propose a principled approach to enforce an implicit latent feature matching in a more compact latent space.
  arXiv  Detail & Related papers  (2020-04-22T14:41:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.