Pith. sign in

REVIEW 8 cited by

Dolfin: Diffusion Layout Transformers without Autoencoder

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 2310.16305 v1 pith:CQR23ZTC submitted 2023-10-25 cs.CV cs.LG

classification cs.CVcs.LG
keywords dolfinlayoutdiffusionmodelalignmentautoencodergenerationgenerative
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

In this paper, we introduce a novel generative model, Diffusion Layout Transformers without Autoencoder (Dolfin), which significantly improves the modeling capability with reduced complexity compared to existing methods. Dolfin employs a Transformer-based diffusion process to model layout generation. In addition to an efficient bi-directional (non-causal joint) sequence representation, we further propose an autoregressive diffusion model (Dolfin-AR) that is especially adept at capturing rich semantic correlations for the neighboring objects, such as alignment, size, and overlap. When evaluated against standard generative layout benchmarks, Dolfin notably improves performance across various metrics (fid, alignment, overlap, MaxIoU and DocSim scores), enhancing transparency and interoperability in the process. Moreover, Dolfin's applications extend beyond layout generation, making it suitable for modeling geometric structures, such as line segments. Our experiments present both qualitative and quantitative results to demonstrate the advantages of Dolfin.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 8 Pith papers

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

  1. T2VTextBench: A Human Evaluation Benchmark for Textual Control in Video Generation Models

    cs.CV 2025-05 conditional novelty 6.0 of 10

    T2VTextBench is a new 73-prompt human benchmark showing that ten leading text-to-video models score below 0.44/1.0 on on-screen text fidelity, exposing a consistent weakness in current generators.

  2. LazyDiT: Lazy Learning for the Acceleration of Diffusion Transformers

    cs.LG 2024-12 conditional novelty 5.0 of 10

    LazyDiT learns small gates that decide when to reuse cached layer outputs, cutting diffusion transformer compute by up to half while matching or beating DDIM quality.

  3. Force Matching with Relativistic Constraints: A Physics-Inspired Approach to Stable and Efficient Generative Modeling

    cs.LG 2025-02 reject novelty 4.0 of 10

    Force Matching replaces velocity matching in flow-based generative models with a relativistic force objective, but the toy experiments are designed so the model class matches the data generator exactly.

  4. Universal Approximation of Visual Autoregressive Transformers

    cs.LG 2025-02 reject novelty 4.0 of 10

    The paper's headline claim that VAR transformers universally approximate all Lipschitz image maps is not supported, because the theorem restricts the target class and its key lemma has an invalid linearity step.

  5. Dissecting Submission Limit in Desk-Rejections: A Mathematical Analysis of Fairness in AI Conference Policies

    cs.LG 2025-02 reject novelty 4.0 of 10

    A proposed LP-based fair desk-rejection system is presented, but its central claims about linear-programming equivalence, NP-hardness, and expected fairness contain invalid steps.

  6. High-Order Matching for One-Step Shortcut Diffusion Models

    cs.CV 2025-02 reject novelty 4.0 of 10

    HOMO extends shortcut diffusion with acceleration and jerk supervision, but the proof of superior approximation is not supported and experiments lack error bars.

  7. On Computational Limits and Provably Efficient Criteria of Visual Autoregressive Models: A Fine-Grained Complexity Analysis

    cs.LG 2025-01 reject novelty 4.0 of 10

    Under SETH, the paper claims VAR models cannot be approximated faster than O(n^4) when attention entries are Theta(sqrt(log n)), but can be approximated in O(n^{2+o(1)}) when entries are o(sqrt(log n)).

  8. Circuit Complexity Bounds for Visual Autoregressive Model

    stat.ML 2025-01 reject novelty 4.0 of 10

    The authors show that a simplified formalization of the VAR image generation model lies in DLOGTIME-uniform TC0, meaning it can be simulated by constant-depth threshold circuits with polynomial size and precision.

Pith tools