Pith. sign in

REVIEW 22 cited by

Unified Multimodal Discrete Diffusion

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 2503.20853 v1 pith:5QW57EG2 submitted 2025-03-26 cs.CV cs.AIcs.LGcs.RO

classification cs.CVcs.AIcs.LGcs.RO
keywords modelsmultimodaltextdiffusiondiscretegenerationimageunidisc
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Multimodal generative models that can understand and generate across multiple modalities are dominated by autoregressive (AR) approaches, which process tokens sequentially from left to right, or top to bottom. These models jointly handle images, text, video, and audio for various tasks such as image captioning, question answering, and image generation. In this work, we explore discrete diffusion models as a unified generative formulation in the joint text and image domain, building upon their recent success in text generation. Discrete diffusion models offer several advantages over AR models, including improved control over quality versus diversity of generated samples, the ability to perform joint multimodal inpainting (across both text and image domains), and greater controllability in generation through guidance. Leveraging these benefits, we present the first Unified Multimodal Discrete Diffusion (UniDisc) model which is capable of jointly understanding and generating text and images for a variety of downstream tasks. We compare UniDisc to multimodal AR models, performing a scaling analysis and demonstrating that UniDisc outperforms them in terms of both performance and inference-time compute, enhanced controllability, editability, inpainting, and flexible trade-off between inference time and generation quality. Code and additional visualizations are available at https://unidisc.github.io.

Discussion (0). Sign in to comment.

Forward citations

Cited by 22 Pith papers

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

  1. AsyncPatch Diffusion: spatially-flexible image generation

    cs.CV 2026-06 unverdicted novelty 7.0 of 10

    AsyncPatch Diffusion introduces asynchronous per-region noise levels in diffusion models, proves a valid ELBO, and uses a controlled sampler to support spatially adaptive generation and native inpainting.

  2. Language Generation as Optimal Control: Closed-Loop Diffusion in Latent Control Space

    cs.CL 2026-05 unverdicted novelty 7.0 of 10

    The paper introduces Manta-LM, which approximates the Hamilton-Jacobi-Bellman optimal policy via Flow Matching in a rectified latent control space to enable high-fidelity parallel language generation.

  3. Discrete Guidance Matching: Exact Guidance for Discrete Flow Matching

    cs.LG 2025-09 conditional novelty 7.0 of 10

    Derives exact guidance transition rates for discrete flow matching models that require only one model evaluation per sampling step and unify prior approximation-based methods.

  4. Hierarchical Domain Generalization

    cs.LG 2026-07 conditional novelty 6.0 of 10

    Over infinite domains, hierarchy-uniform domain generalization is impossible for every nontrivial hypothesis class; a length-generalization bound is a property of the length hierarchy, not a hierarchy-free guarantee.

  5. Language Generation as Optimal Control: Closed-Loop Diffusion in Latent Control Space

    cs.CL 2026-05 unverdicted novelty 6.0 of 10

    Language generation is recast as optimal control and solved approximately with flow matching in rectified latent control space to enable high-fidelity parallel text generation.

  6. Language Generation as Optimal Control: Closed-Loop Diffusion in Latent Control Space

    cs.CL 2026-05 unverdicted novelty 6.0 of 10

    Manta-LM approximates the HJB equation via flow matching in latent control space to realize closed-loop optimal control for language generation.

  7. dFlowGRPO: Rate-Aware Policy Optimization for Discrete Flow Models

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    dFlowGRPO is a new rate-aware RL method for discrete flow models that outperforms prior GRPO approaches on image generation and matches continuous flow models while supporting broad probability paths.

  8. DVD: Discrete Voxel Diffusion for 3D Generation and Editing

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    DVD treats voxel occupancy as a discrete variable in a diffusion framework to generate, assess, and edit sparse 3D voxels without continuous thresholding.

  9. DVD: Discrete Voxel Diffusion for 3D Generation and Editing

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    DVD applies discrete diffusion directly to voxel occupancy for 3D generation, uncertainty estimation via entropy, and single-round editing via block perturbation fine-tuning.

  10. AsyncVLA: Asynchronous Flow Matching for Vision-Language-Action Models

    cs.RO 2025-11 unverdicted novelty 6.0 of 10

    AsyncVLA adds asynchronous flow matching and a confidence rater to VLA models so they can generate actions on flexible schedules and selectively refine low-confidence tokens before execution.

  11. Any-Order Flexible Length Masked Diffusion

    cs.LG 2025-08 conditional novelty 6.0 of 10

    FlexMDM is a discrete diffusion model that provably supports any-order generation over variable-length sequences by learning an insertion expectation alongside the unmasking posterior, validated by length-fidelity, ma...

  12. Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model

    cs.LG 2025-05 unverdicted novelty 6.0 of 10

    Muddit is a unified discrete diffusion transformer that integrates strong visual priors from a pretrained text-to-image model with a lightweight text decoder to enable fast parallel generation across text and image mo...

  13. LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning

    cs.LG 2025-05 conditional novelty 6.0 of 10

    LLaDA-V is a diffusion-based multimodal large language model that reaches competitive or state-of-the-art results on visual instruction tasks while using a non-autoregressive architecture.

  14. Mask-Aware Policy Gradients for Diffusion Language Models

    cs.CL 2026-07 conditional novelty 5.0 of 10

    Optimizing both token predictions and unmasking-position probabilities in MDLM policy gradients improves RL fine-tuning, reaching 87.1% GSM8K and 53.4% MBPP.

  15. Bridging Video Understanding and Generation in a Unified Framework

    cs.CV 2026-06 unverdicted novelty 5.0 of 10

    Vega unifies video understanding and generation via shared vocabulary and hybrid autoregressive-diffusion architecture, reporting strong results on VBench and VideoMME.

  16. TBD-VLA: Temporal Block Diffusion Vision Language Action Model

    cs.CV 2026-06 unverdicted novelty 5.0 of 10

    TBD-VLA partitions action sequences into temporal blocks, performs masked discrete diffusion within blocks, and autoregressive generation across blocks to unify parallel decoding with temporal coherence in discrete VL...

  17. MONET: A Massive, Open, Non-redundant and Enriched Text-to-image dataset

    cs.CV 2026-05 unverdicted novelty 5.0 of 10

    MONET is an open 104.9M image-text pair dataset created via safety filtering, deduplication, and multi-VLM recaptioning from 2.9B raw pairs, validated by training a competitive 4B-parameter latent diffusion model.

  18. Discrete Diffusion Models: A Unified Framework from Tokenization to Generation

    cs.LG 2026-07 unverdicted novelty 4.0 of 10

    Discrete diffusion models are re-framed as instances of a tokenization-centric, four-component design space (corruption, denoiser, objective, sampler) in a broad survey with no new experimental or theoretical results.

  19. UniTranslator: A Unified Multi-modal Framework for End-to-end In-Image Machine Translation

    cs.CV 2026-06 unverdicted novelty 4.0 of 10

    UniTranslator adds an Understand-Generation Alignment Module and Spatial Mask Decoder to a unified multimodal model to fix translation inconsistency and spatial misalignment in in-image machine translation, reporting ...

  20. Show-o2: Improved Native Unified Multimodal Models

    cs.CV 2025-06 unverdicted novelty 4.0 of 10

    Show-o2 unifies text, image, and video understanding and generation in a single autoregressive-plus-flow-matching model built on 3D causal VAE representations.

  21. Generative AI Meets 6G and Beyond: Diffusion Models for Semantic Communications

    eess.SP 2025-11 unverdicted novelty 3.0 of 10

    The tutorial synthesizes diffusion model techniques for generative semantic communications to achieve high compression while preserving meaning in wireless transmission.

  22. A Survey on Diffusion Language Models

    cs.CL 2025-08 unverdicted novelty 3.0 of 10

    A comprehensive survey of diffusion language models covering taxonomy, training and inference techniques, and comparisons with autoregressive models.

Pith tools