Pith. sign in

REVIEW 7 cited by

Causal Diffusion Transformers for Generative Modeling

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2412.12095 v2 pith:L4UQ4RCN submitted 2024-12-16 cs.CV

Causal Diffusion Transformers for Generative Modeling

classification cs.CV
keywords diffusionmodelscausalfusiongenerationcausalcontinuousdatadiscrete
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We introduce Causal Diffusion as the autoregressive (AR) counterpart of Diffusion models. It is a next-token(s) forecasting framework that is friendly to both discrete and continuous modalities and compatible with existing next-token prediction models like LLaMA and GPT. While recent works attempt to combine diffusion with AR models, we show that introducing sequential factorization to a diffusion model can substantially improve its performance and enables a smooth transition between AR and diffusion generation modes. Hence, we propose CausalFusion - a decoder-only transformer that dual-factorizes data across sequential tokens and diffusion noise levels, leading to state-of-the-art results on the ImageNet generation benchmark while also enjoying the AR advantage of generating an arbitrary number of tokens for in-context reasoning. We further demonstrate CausalFusion's multimodal capabilities through a joint image generation and captioning model, and showcase CausalFusion's ability for zero-shot in-context image manipulations. We hope that this work could provide the community with a fresh perspective on training multimodal models over discrete and continuous data.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. OmniMem: Scalable and Adaptive Memory Retrieval for Long Video Generation

    cs.CV 2026-05 unverdicted novelty 6.0

    OmniMem enables scalable long video generation via adaptive sparse KV retrieval that addresses local bias and union explosion while preserving explicit historical access.

  2. Rethinking Cross-Layer Information Routing in Diffusion Transformers

    cs.CV 2026-05 unverdicted novelty 6.0

    DAR replaces residual addition in DiTs with learnable, timestep-adaptive aggregation of sublayer outputs, yielding 2.11 FID improvement on SiT-XL/2 and 8.75x faster convergence on ImageNet 256x256.

  3. Rethinking Cross-Layer Information Routing in Diffusion Transformers

    cs.CV 2026-05 conditional novelty 6.0

    DAR replaces residual addition in DiTs with learnable timestep-adaptive non-incremental aggregation of sublayer outputs, improving FID by 2.11 on ImageNet 256x256 and accelerating convergence by 8.75x.

  4. INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modeling

    cs.CV 2026-04 unverdicted novelty 6.0

    INSPATIO-WORLD is a real-time framework for high-fidelity 4D scene generation and navigation from monocular videos via STAR architecture with implicit caching, explicit geometric constraints, and distribution-matching...

  5. Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion

    cs.CV 2025-06 unverdicted novelty 6.0

    Self Forcing trains autoregressive video diffusion models by performing autoregressive rollout with KV caching during training to close the exposure bias gap, using a holistic video-level loss and few-step diffusion f...

  6. RepFlow: Representation Enhanced Flow Matching for Causal Effect Estimation

    cs.LG 2026-05 unverdicted novelty 5.0

    RepFlow combines representation learning and conditional flow matching to estimate both point and distributional causal effects while mitigating selection bias via entropically regularized Wasserstein distance on norm...

  7. Emerging Properties in Unified Multimodal Pretraining

    cs.CV 2025-05 unverdicted novelty 5.0

    BAGEL is a unified decoder-only model that develops emerging complex multimodal reasoning abilities after pretraining on large-scale interleaved data and outperforms prior open-source unified models.