Diffusion Models

Follow this topic Ask about this topic

Diffusion models learn a data distribution by gradually corrupting examples with noise and training a denoiser to reverse that process. Major approaches include DDPMs and score-based SDEs, latent diffusion and diffusion Transformers, flow and consistency methods, and discrete masked or continuous-time Markov diffusion; conditioning and guidance adapt them to specific tasks. They are used for images, video, audio, language, molecules, and scientific forecasting, with evaluations ranging from ImageNet FID to language perplexity and domain-specific measures of accuracy and uncertainty. A central tension is how to make sampling faster and generation more controllable without sacrificing quality, calibration, or diversity, while theory and ongoing audits address generalization, memorization, and privacy.

Latest papers

1,192 papers152 papers in the last four weeks, up 77% on the four weeks before. 0.9% of all new papers.

Mar 24, 2026

Permutation-Symmetrized Diffusion for Unconditional Molecular Generation

Permutation invariance is fundamental in molecular point-cloud generation, yet most diffusion models enforce it indirectly via permutation-equivariant networks on an ordered space. We propose to model diffusion directly on the quotient manifold

\tilde{\calX}=\sR^{d\times N}/S_N

, where all atom permutations are identified. We show that the heat kernel on

\tilde{\calX}

admits an explicit expression as a sum of Euclidean heat kernels over permutations, which clarifies how diffusion on the quotient differs from ordered-particle diffusion. Training requires a permutation-symmetrized score involving an intractable sum over

S_N

; we derive an expectation form over a posterior on permutations and approximate it using MCMC in permutation space. We evaluate on unconditional 3D molecule generation on QM9 under the EQGAT-Diff protocol, using SemlaFlow-style backbone and treating all variables continuously. The results demonstrate that quotient-based permutation symmetrization is practical and yields competitive generation quality with improved efficiency.

Gyeonghoon Ko, Juho Lee

Korea Advanced Institute of Science and Technology

Molecular Generation Diffusion Models 3D Molecular Generation Permutation-Invariant Learning

Mar 24, 2026

Gimbal360: Canonicalizing Planar Diffusion for Spherical Panorama Completion

Diffusion models provide powerful priors for 2D image completion, but these priors are learned on bounded planar images and do not transfer directly to

360^\circ

panoramas. Perspective observations and spherical panoramas differ in both projective geometry and topology: viewpoint-dependent distortion complicates spatial correspondence, while Equirectangular Projection (ERP) panoramas exhibit intrinsic

S^1

periodicity that standard Euclidean architectures do not preserve. We present Gimbal360, a unified framework that adapts planar diffusion priors to spherical panoramic completion by standardizing these geometric and topological structures. Our Canonical Viewing Space expresses projective distortion as a fixed function of latitude, providing a consistent interface between perspective inputs and spherical panoramas. To map unposed in-the-wild images into this space, Differentiable Projective Canonicalization projects a dense correspondence field onto a 3-DoF rigid projection manifold without requiring camera parameters at inference. We further introduce Topologically Equivariant Generation, which enforces latent shift equivariance to preserve continuity across the periodic ERP boundary. Together, these designs allow diffusion to operate in a representation whose geometry and topology are explicitly aligned with the spherical domain. We also introduce Horizon360, a curated large-scale dataset of gravity-aligned panoramic environments. Extensive experiments show that Gimbal360 achieves state-of-the-art visual fidelity and seam continuity in

360^\circ

scene completion.

Yuqin Lu, Haofeng Liu, Yang Zhou +4

Diffusion Models Diffusion Models for Image Restoration

Mar 24, 2026

Asymptotic Learning Curves for Diffusion Models with Random Features Score and Manifold Data

We study the theoretical behavior of denoising score matching--the learning task associated to diffusion models--when the data distribution is supported on a low-dimensional manifold and the score is parameterized using a random feature neural network. We derive asymptotically exact expressions for the test, train, and score errors in the high-dimensional limit. Our analysis reveals that, for linear manifolds the sample complexity required to learn the score function scales linearly with the intrinsic dimension of the manifold, rather than with the ambient dimension. Perhaps surprisingly, the benefits of low-dimensional structure starts to diminish once we have a non-linear manifold. These results indicate that diffusion models can benefit from structured data; however, the dependence on the specific type of structure is subtle and intricate.

Anand Jerry George, Nicolas Macris

École Polytechnique Fédérale de Lausanne (EPFL), Lab for Statistical Mechanics of Inference in Large Systems (SMILS), CH-1015 Lausanne, Switzerland

Intrinsic Dimensionality Random Feature Methods Learning Curves Score-Based Generative Modeling Statistical Learning Theory Diffusion Models

Mar 23, 2026

Tiny Inference-Time Scaling with Latent Verifiers

Inference-time scaling has emerged as an effective way to improve generative models at test time by using a verifier to score and select candidate outputs. A common choice is to employ Multimodal Large Language Models (MLLMs) as verifiers, which can improve performance but introduce substantial inference-time cost. Indeed, diffusion pipelines operate in an autoencoder latent space to reduce computation, yet MLLM verifiers still require decoding candidates to pixel space and re-encoding them into the visual embedding space, leading to redundant and costly operations. In this work, we propose Verifier on Hidden States (VHS), a verifier that operates directly on intermediate hidden representations of Diffusion Transformer (DiT) single-step generators. VHS analyzes generator features without decoding to pixel space, thereby reducing the per-candidate verification cost while improving or matching the performance of MLLM-based competitors. We show that, under tiny inference budgets with only a small number of candidates per prompt, VHS enables more efficient inference-time scaling reducing joint generation-and-verification time by 63.3%, compute FLOPs by 51% and VRAM usage by 14.5% with respect to a standard MLLM verifier, achieving a +2.7% improvement on GenEval at the same inference-time budget.

Davide Bucciarelli, Evelyn Turri, Lorenzo Baraldi +3

University of Modena and Reggio Emilia, Italy · University of Pisa, Italy

Inference-Time Scaling Diffusion Models Diffusion Model Inference Acceleration

Mar 23, 2026

Repurposing Geometric Foundation Models for Multi-view Diffusion

While recent advances in generative latent spaces have driven substantial progress in single-image generation, the optimal latent space for novel view synthesis (NVS) remains largely unexplored. In particular, NVS requires geometrically consistent generation across viewpoints, but existing approaches typically operate in a view-independent VAE latent space. In this paper, we propose Geometric Latent Diffusion (GLD), a framework that repurposes the geometrically consistent feature space of geometric foundation models as the latent space for multi-view diffusion. We show that these features not only support high-fidelity RGB reconstruction but also encode strong cross-view geometric correspondences, providing a well-suited latent space for NVS. Our experiments demonstrate that GLD outperforms both VAE and RAE on 2D image quality and 3D consistency metrics, while accelerating training by more than 4.4x compared to the VAE latent space. Notably, GLD remains competitive with state-of-the-art methods that leverage large-scale text-to-image pretraining, despite training its diffusion model from scratch without such generative pretraining.

Wooseok Jang, Seonghu Jeon, Jisang Han +5

KAIST AI · New York University · Intel Labs

Multi-View Diffusion Models Novel View Synthesis Latent Diffusion Models Diffusion Models Multi-View Consistency

Mar 23, 2026

DA-VAE: Plug-in Latent Compression for Diffusion via Detail Alignment

Reducing token count is crucial for efficient training and inference of latent diffusion models, especially at high resolution. A common strategy is to build high-compression image tokenizers with more channels per token. However, when trained only for reconstruction, high-dimensional latent spaces often lose meaningful structure, making diffusion training harder. Existing methods address this with extra objectives such as semantic alignment or selective dropout, but usually require costly diffusion retraining. Pretrained diffusion models, however, already exhibit a structured, lower-dimensional latent space; thus, a simpler idea is to expand the latent dimensionality while preserving this structure. We therefore propose Detail-Aligned VAE, which increases the compression ratio of a pretrained VAE with only lightweight adaptation of the pretrained diffusion backbone. DA-VAE uses an explicit latent layout: the first

C

channels come directly from the pretrained VAE at a base resolution, while an additional

D

channels encode higher-resolution details. A simple detail-alignment mechanism encourages the expanded latent space to retain the structure of the original one. With a warm-start fine-tuning strategy, our method enables

1024 \times 1024

image generation with Stable Diffusion 3.5 using only

32 \times 32

tokens,

4\times

fewer than the original model, within 5 H100-days. It further unlocks

2048 \times 2048

generation with SD3.5, achieving a

6\times

speedup while preserving image quality. We also validate the method and its design choices quantitatively on ImageNet.

Xin Cai, Zhiyuan You, Zhoutong Zhang +1

Multimedia Laboratory, The Chinese University of Hong Kong · Shanghai AI Laboratory · Adobe NextCam +1

Diffusion-Based Image Generation Diffusion Model Compression Diffusion Models Latent Diffusion Models Diffusion Model Inference Acceleration

Mar 23, 2026

Tuning Real-World Image Restoration at Inference: A Test-Time Scaling Paradigm for Flow Matching Models

Although diffusion-based real-world image restoration (Real-IR) has achieved remarkable progress, efficiently leveraging ultra-large-scale pre-trained text-to-image (T2I) models and fully exploiting their potential remain significant challenges. To address this issue, we propose ResFlow-Tuner, an image restoration framework based on the state-of-the-art flow matching model, FLUX.1-dev, which integrates unified multi-modal fusion (UMMF) with test-time scaling (TTS) to achieve unprecedented restoration performance. Our approach fully leverages the advantages of the Multi-Modal Diffusion Transformer (MM-DiT) architecture by encoding multi-modal conditions into a unified sequence that guides the synthesis of high-quality images. Furthermore, we introduce a training-free test-time scaling paradigm tailored for image restoration. During inference, this technique dynamically steers the denoising direction through feedback from a reward model (RM), thereby achieving significant performance gains with controllable computational overhead. Extensive experiments demonstrate that our method achieves state-of-the-art performance across multiple standard benchmarks. This work not only validates the powerful capabilities of the flow matching model in low-level vision tasks but, more importantly, proposes a novel and efficient inference-time scaling paradigm suitable for large pre-trained models.

Purui Bai, Junxian Duan, Pin Wang +4

MAIS & NLPR, Institute of Automation, Chinese Academy of Sciences, China · Kuaishou Tech, China

Image Restoration Diffusion Models

Mar 23, 2026

IPSL-AID: Generative Diffusion Models for Climate Downscaling from Global to Regional Scales

Effective adaptation and mitigation strategies for climate change require high-resolution projections to inform strategic decision-making. Conventional global climate models, which typically operate at resolutions of 150 to 200 kilometers, lack the capacity to represent essential regional processes. IPSL-AID is a global to regional downscaling tool based on a denoising diffusion probabilistic model designed to address this limitation. Trained on ERA5 reanalysis data, it generates 0.25 degree resolution fields for temperature, wind, and precipitation using coarse inputs and their spatiotemporal context. It also models probability distributions of fine-scale features to produce plausible scenarios for uncertainty quantification. The model accurately reconstructs statistical distributions, including extreme events, power spectra, and spatial structures. This work highlights the potential of generative diffusion models for efficient climate downscaling with uncertainty

Kishanthan Kingston, Olivier Boucher, Freddy Bouchet +5

Climate Modeling Center, Sorbonne University, CNRS, IPSL, Paris, France · LMD, CNRS, ENS/PSL, Sorbonne University, IPSL, Paris, France · Climate Modeling and Analysis, LLC, Superior, CO, USA +1

Climate Downscaling Precipitation Downscaling Diffusion Models

Mar 23, 2026

SHARP: Spectrum-aware Highly-dynamic Adaptation for Resolution Promotion in Remote Sensing Synthesis

Text-to-image synthesis for remote sensing (RS) lacks an accessible, high-performance generative foundation, as directly training diffusion models at large, high resolutions is computationally prohibitive. Training-free resolution promotion via Rotary Position Embedding (RoPE) extrapolation offers an efficient alternative, but existing algorithms apply static scaling rules tailored to natural scenes, whereas RS imagery is dominated by dense, minute instances that hinge on high-frequency structural integrity. We present a comprehensive framework for large-scale RS synthesis. First, we curate over 100{,}000 image-text pairs to train RS-FLUX, a domain-specialized generative prior. Second, we propose SHARP, a training-free extrapolation algorithm that introduces a Rational Decay Scheduler to modulate RoPE frequencies throughout denoising: strong positional extrapolation early on enforces coherent global layouts, and progressive relaxation later recovers dense high-frequency details. Extensive experiments show that SHARP consistently achieves state-of-the-art performance across multiple promoted resolutions with negligible (

<

4%) overhead, offering an efficient and structurally faithful solution for large-scale RS generation.

Bingxuan Zhao, Qing Zhou, Chuang Yang +2

Northwestern Polytechnical University, Xi’an, China · The Hong Kong Polytechnic University, Hong Kong, China

Rotary Positional Embeddings Diffusion Transformer Remote Sensing Diffusion-Based Image Generation Diffusion Models

Mar 22, 2026

Generalized Discrete Diffusion from Snapshots

We introduce Generalized Discrete Diffusion from Snapshots (GDDS), a unified framework for discrete diffusion modeling that supports arbitrary noising processes over large discrete state spaces. Our formulation encompasses all existing discrete diffusion approaches, while allowing significantly greater flexibility in the choice of corruption dynamics. The forward noising process relies on uniformization and enables fast arbitrary corruption. For the reverse process, we derive a simple evidence lower bound (ELBO) based on snapshot latents, instead of the entire noising path, that allows efficient training of standard generative modeling architectures with clear probabilistic interpretation. Our experiments on large-vocabulary discrete generation tasks suggest that the proposed framework outperforms existing discrete diffusion methods in terms of training efficiency and generation quality, and beats autoregressive models for the first time at this scale. We provide the code along with a blog post on the project page : https://oussamazekri.fr/gdds.

Oussama Zekri, Théo Uscidda, Nicolas Boullé +1

CREST, ENSAE, Institut Polytechnique de Paris, Paris, France · Department of Mathematics, Imperial College London, London, SW7 2AZ, UK

Diffusion Models Diffusion Language Models

Mar 22, 2026

ReDiffuse: Rotation Equivariant Diffusion Model for Multi-focus Image Fusion

Diffusion models have achieved impressive performance on multi-focus image fusion (MFIF). However, a key challenge in applying diffusion models to the ill-posed MFIF problem is that defocus blur can make common symmetric geometric structures (e.g., textures and edges) appear warped and deformed, often leading to unexpected artifacts in the fused images. Therefore, embedding rotation equivariance into diffusion networks is essential, as it enables the fusion results to faithfully preserve the original orientation and structural consistency of geometric patterns underlying the input images. Motivated by this, we propose ReDiffuse, a rotation-equivariant diffusion model for MFIF. Specifically, we carefully construct the basic diffusion architectures to achieve end-to-end rotation equivariance. We also provide a rigorous theoretical analysis to evaluate its intrinsic equivariance error, demonstrating the validity of embedding equivariance structures. ReDiffuse is comprehensively evaluated against various MFIF methods across four datasets (Lytro, MFFW, MFI-WHU, and Road-MF). Results demonstrate that ReDiffuse achieves competitive performance, with improvements of 0.28-6.64% across six evaluation metrics. The code is available at https://github.com/MorvanLi/ReDiffuse.

Bo Li, Tingting Bao, Lingling Zhang +3

School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, Shaanxi, China · School of Information Engineering, Chang’an University, Xi’an, Shaanxi, China

Multi-Source Image Fusion Diffusion Models Equivariant Neural Networks

Mar 22, 2026

LPNSR: Learnable Noise Prediction for Diffusion-Based Image Super-Resolution

Diffusion-based image super-resolution (SR) aims to reconstruct high-resolution (HR) images from low-resolution (LR) observations. A key property of diffusion models is that, once the starting point of the reverse chain and the denoising network are fixed, the quality of the generated image is dictated by the noise maps sampled at the intermediate steps, which are drawn from an unconstrained standard Gaussian distribution in conventional pipelines. This property raises a natural question: does there exist a noise sampling distribution better than the standard Gaussian that improves the quality of the generated images? To this end, we use a parameterized deep neural network to predict the mean and the variance of the Gaussian noise sampling distribution at each intermediate step, and design two training schemes, one supervised by the quality of the final generated image and the other by aligning each reverse step with the forward posterior. Experiments show that, compared with the standard Gaussian distribution, the learnable noise sampling distribution improves the quality of the generated images. The source code of our method can be found at https://github.com/Faze-Hsw/LPNSR.

Shuwei Huang, Shizhuo Liu, Zijun Wei

Huazhong University of Science and Technology

Image Super-Resolution Diffusion Models Diffusion Sampling

Mar 22, 2026

Interpreting the Synchronization Gap: The Hidden Mechanism Inside Diffusion Transformers

Recent theoretical models of diffusion processes, conceptualized as coupled Ornstein-Uhlenbeck systems, predict a hierarchy of interaction timescales, and consequently, the existence of a synchronization gap between modes that commit at different stages of the reverse process. However, because these predictions rely on continuous time and analytically tractable score functions, it remains unclear how this phenomenology manifests in the deep, discrete architectures deployed in practice. In this work, we investigate how the synchronization gap is mechanistically realized within pretrained Diffusion Transformers (DiTs). We construct an explicit architectural realization of replica coupling by embedding two generative trajectories into a joint token sequence, modulated by a symmetric cross attention gate with variable coupling strength g. Through a linearized analysis of the attention difference, we show that the replica interaction decomposes mechanistically. We empirically validate our theoretical framework on a pretrained DiT-XL/2 model by tracking commitment and per layer internal mode energies. Our results reveal that: (1) the synchronization gap is an intrinsic architectural property of DiTs that persists even when external coupling is turned off; (2) as predicted by our spatial routing bounds, the gap completely collapses under strong coupling; (3) the gap is strictly depth localized, emerging sharply only within the final layers of the Transformer; and (4) global, low frequency structures consistently commit before local, high frequency details. Ultimately, our findings provide a mechanistic interpretation of how Diffusion Transformers resolve generative ambiguity, isolating speciation transitions to the terminal layers of the network.

Emil Albrychiewicz, Andrés Franco Valiente, Li-Ching Chen +1

Leinweber Institute for Theoretical Physics and Department of Physics, University of California, Berkeley, CA, 94720-7300, USA · Theoretical Physics Group, Lawrence Berkeley National Laboratory, Berkeley, CA 94720-8162, USA · Department of Radiation Oncology, University of California, San Francisco +2

Diffusion Models Diffusion Transformer Transformer Interpretability

Mar 21, 2026

Diffusion Model for Manifold Data: Score Decomposition, Curvature, and Statistical Complexity

Diffusion models have become a leading framework in generative modeling, yet their theoretical understanding -- especially for high-dimensional data concentrated on low-dimensional structures -- remains incomplete. This paper investigates how diffusion models learn such structured data, focusing on two key aspects: statistical complexity and influence of data geometric properties. By modeling data as samples from a smooth Riemannian manifold, our analysis reveals crucial decompositions of score functions in diffusion models under different levels of injected noise. We also highlight the interplay of manifold curvature with the structures in the score function. These analyses enable an efficient neural network approximation to the score function, built upon which we further provide statistical rates for score estimation and distribution learning. Remarkably, the obtained statistical rates are governed by the intrinsic dimension of data and the manifold curvature. These results advance the statistical foundations of diffusion models, bridging theory and practice for generative modeling on manifolds.

Zixuan Zhang, Kaixuan Huang, Tuo Zhao +2

Georgia Tech · Princeton University · Northwestern University

Diffusion Models Statistical Learning Theory

Mar 21, 2026

Generating from Discrete Distributions Using Diffusions: Insights from Random Constraint Satisfaction Problems

Generating data from discrete distributions is important for a number of application domains including text, tabular data, and genomic data. Several groups have recently used random

k

-satisfiability (

k

-SAT) as a synthetic benchmark for new generative techniques. In this paper, we show that fundamental insights from the theory of random constraint satisfaction problems have observable implications (sometime contradicting intuition) on the behavior of generative techniques on such benchmarks. More precisely, we study the problem of generating a uniformly random solution of a given (random)

k

-SAT or

k

-XORSAT formula. Among other findings, we observe that:

(i)

~Continuous diffusions outperform masked discrete diffusions;

(ii)

~Learned diffusions can match the theoretical `ideal' accuracy;

(iii)

~Smart ordering of the variables can significantly improve accuracy, although not following popular heuristics.

Alankrita Bhatt, Mukur Gupta, Germain Kolossov +1

Granica Computing Inc. – granica.ai · Stanford University

Diffusion Sampling Diffusion Models Constraint Satisfaction

Mar 21, 2026

Improving Diffusion Generalization with Weak-to-Strong Segmented Guidance

Diffusion models generate synthetic images through an iterative refinement process. However, the misalignment between the simulation-free objective and the iterative process often causes accumulated gradient error along the sampling trajectory, which leads to unsatisfactory results and a failure to generalize. Guidance techniques like Classifier Free Guidance (CFG) and AutoGuidance (AG) alleviate this by extrapolating between the main and inferior signal for stronger generalization. Despite empirical success, the effective operational regimes of prevalent guidance methods are still under-explored, leading to ambiguity when selecting the appropriate guidance method given a precondition. In this work, we first conduct synthetic comparisons to isolate and demonstrate the effective regime of guidance methods represented by CFG and AG from the perspective of weak-to-strong principle. Based on this, we propose a hybrid instantiation called SGG under the principle, taking the benefits of both. Furthermore, we demonstrate that the W2S principle along with SGG can be migrated into the training objective, improving the generalization ability of unguided diffusion models. We validate our approach with comprehensive experiments. At inference time, evaluations on SD3 and SD3.5 confirm that SGG outperforms existing training-free guidance variants. Training-time experiments on transformer architectures demonstrate the effective migration and performance gains in both conditional and unconditional settings. Code is available at https://github.com/851695e35/SGG.

Liangyu Yuan, Yufei Huang, Mingkun Lei +5

Westlake University · Tongji University · Zhejiang University +1

Diffusion Model Guidance Diffusion Models Diffusion Guidance Classifier-Free Guidance

Mar 20, 2026

Beyond Single Tokens: Distilling Discrete Diffusion Models via Discrete MMD

It is currently difficult to distill discrete diffusion models. In contrast, continuous diffusion literature has many distillation approaches methods that can reduce sampling steps to a handful. Our method, Discrete Moment Matching Distillation (D-MMD), leverages ideas that have been highly successful in the continuous domain. Whereas previous discrete distillation methods collapse, D-MMD maintains high quality and diversity (given sufficient sampling steps). This is demonstrated on both text and image datasets. Moreover, the newly distilled generators can outperform their teachers.

Emiel Hoogeboom, David Ruhe, Jonathan Heek +2

Google DeepMind Amsterdam

Diffusion Model Distillation Diffusion Models Diffusion Language Model Distillation

Mar 20, 2026

How Out-of-Equilibrium Phase Transitions can Seed Pattern Formation in Trained Diffusion Models

Diffusion models generate structure by progressively transforming noise into data, yet the mechanisms underlying this transition remain poorly understood. In this work, we show that pattern formation in trained diffusion models can be explained as an out-of-equilibrium phase transition driven by instabilities in the denoising dynamics. We develop a theoretical framework linking data symmetries and architectural constraints, such as locality and translation equivariance, to the emergence of collective spatial modes. In this view, structure arises when low-frequency modes become unstable, triggering a rapid growth of spatial correlations that organizes noise into coherent patterns. We validate this theory through a combination of analytical models and experiments. In a controlled patch-based model, we observe a sharp softening of low-frequency modes in the theoretically predicted critical regime. Similar signatures are found in trained convolutional diffusion models on Fashion-MNIST and in large-scale ImageNet models, where pattern formation coincides with a pronounced weakening of spatial modes. Finally, intervention experiments show that applying guidance precisely at this critical stage improves class alignment compared to applying it at random times, demonstrating that this regime is not only descriptive but functionally important.

Luca Ambrogioni

Radboud University, Donders Institute for Brain, Cognition, and Behaviour

Diffusion Models

Mar 20, 2026

On the role of memorization in learned priors for geophysical inverse problems

Learned priors based on deep generative models offer data-driven regularization for seismic inversion, but training them requires a dataset of representative subsurface models -- a resource that is inherently scarce in geoscience applications. Since the training objective of most generative models can be cast as maximum likelihood on a finite dataset, any such model risks converging to the empirical distribution -- effectively memorizing the training examples rather than learning the underlying geological distribution. We show that the posterior under such a memorized prior reduces to a reweighted empirical distribution -- i.e., a likelihood-weighted lookup among the stored training examples. For diffusion models specifically, memorization yields a Gaussian mixture prior in closed form, and linearizing the forward operator around each training example gives a Gaussian mixture posterior whose components have widths and shifts governed by the local Jacobian. We validate these predictions on a stylized inverse problem and demonstrate the consequences of memorization through diffusion posterior sampling for full waveform inversion.

Ali Siahkoohi, Davide Sabeddu

University of Central Florida

Memorization in Generative Models Inverse Problems Diffusion Models Diffusion Posterior Sampling

Mar 20, 2026

SeeClear: Reliable Transparent Object Depth Estimation via Generative Opacification

Monocular depth estimation remains challenging for transparent objects, where refraction and transmission are difficult to model and break the appearance assumptions used by depth networks. As a result, state-of-the-art estimators often produce unstable or incorrect depth predictions for transparent materials. We propose SeeClear, a novel framework that converts transparent objects into generative opaque images, enabling stable monocular depth estimation for transparent objects. Given an input image, we first localize transparent regions and transform their refractive appearance into geometrically consistent opaque shapes using a diffusion-based generative opacification module. The processed image is then fed into an off-the-shelf monocular depth estimator without retraining or architectural changes. To train the opacification model, we construct SeeClear-396k, a synthetic dataset containing 396k paired transparent-opaque renderings. Experiments on both synthetic and real-world datasets show that SeeClear significantly improves depth estimation for transparent objects. Project page: https://heyumeng.com/SeeClear-web/

Xiaoying Wang, Yumeng He, Jingkai Shi +4

University of California, Los Angeles. · University of Southern California. · University of Utah.

Depth Estimation Monocular Depth Estimation Diffusion Models

Mar 19, 2026

TRACE: Trajectory Recovery with State Propagation Diffusion for Urban Mobility

High-quality GPS trajectories are essential for location-based web services and smart city applications, including navigation, ride-sharing and delivery. However, due to low sampling rates and limited infrastructure coverage during data collection, real-world trajectories are often sparse and feature unevenly distributed location points. Recovering these trajectories into dense and continuous forms is essential but challenging, given their complex and irregular spatio-temporal patterns. In this paper, we introduce a novel diffusion model for trajectory recovery named TRACE, which reconstruct dense and continuous trajectories from sparse and incomplete inputs. At the core of TRACE, we propose a State Propagation Diffusion Model (SPDM), which integrates a novel memory mechanism, so that during the denoising process, TRACE can retain and leverage intermediate results from previous steps to effectively reconstruct those hard-to-recover trajectory segments. Extensive experiments on multiple real-world datasets show that TRACE outperforms the state-of-the-art, offering

>

26% accuracy improvement without significant inference overhead. Our work strengthens the foundation for mobile and web-connected location services, advancing the quality and fairness of data-driven urban applications. Code is available at: https://github.com/JinmingWang/TRACE

Jinming Wang, Hai Wang, Hongkai Wen +2

University of Exeter Department of Computer Science Exeter, United Kingdom · Jingdong Logistics Beijing, China · University of Warwick Department of Computer Science Coventry, United Kingdom

Trajectory Reconstruction Diffusion Models Intelligent Transportation Systems

Mar 19, 2026

Cubic Discrete Diffusion: Discrete Visual Generation on High-Dimensional Representation Tokens

Visual generation with discrete tokens has gained significant attention as it enables a unified token prediction paradigm shared with language models, promising seamless multimodal architectures. However, current discrete generation methods remain limited to low-dimensional latent tokens (typically 8-32 dims), sacrificing the semantic richness essential for understanding. While high-dimensional pretrained representations (768-1024 dims) could bridge this gap, their discrete generation poses fundamental challenges. In this paper, we present Cubic Discrete Diffusion (CubiD), the first discrete generation model for high-dimensional representations. CubiD performs fine-grained masking throughout the high-dimensional discrete representation -- any dimension at any position can be masked and predicted from partial observations. This enables the model to learn rich correlations both within and across spatial positions, with the number of generation steps fixed at

T

regardless of feature dimensionality, where

T \ll hwd

. On ImageNet-256, CubiD achieves state-of-the-art discrete generation with strong scaling behavior from 900M to 3.7B parameters. Crucially, we validate that these discretized tokens preserve original representation capabilities, demonstrating that the same discrete tokens can effectively serve both understanding and generation tasks. We hope this work will inspire future research toward unified multimodal architectures. Code is available at: https://github.com/YuqingWang1029/CubiD.

Yuqing Wang, Chuofan Ma, Zhijie Lin +7

University of Hong Kong · ByteDance Seed · Carnegie Mellon University +2

Image Generation Diffusion-Based Image Generation Diffusion Models Masked Diffusion Models

Mar 19, 2026

Rethinking Vector Field Learning for Generative Segmentation

Taming diffusion models for generative segmentation has attracted increasing attention. While existing approaches primarily focus on architectural tweaks or training heuristics, there remains a limited understanding of the intrinsic mismatch between continuous flow matching objectives and discrete perception tasks. In this work, we revisit diffusion segmentation from the perspective of vector field learning. We identify two key limitations of the commonly used flow matching objective: gradient vanishing and trajectory traversing, which result in slow convergence and poor class separation. To tackle these issues, we propose a principled vector field reshaping strategy that augments the learned velocity field with a detached distance-aware correction term. This correction introduces both attractive and repulsive interactions, enhancing gradient magnitudes near centroids while preserving the original diffusion training framework. Furthermore, we design a computationally efficient, quasi-random category encoding scheme inspired by Kronecker sequences, which integrates seamlessly with an end-to-end pixel neural field framework for pixel-level semantic alignment. Extensive experiments consistently demonstrate significant improvements over vanilla flow matching approaches, substantially narrowing the performance gap between generative segmentation and strong discriminative specialists.

Chaoyang Wang, Yaobo Liang, Boci Peng +3

Peking University · Baidu

Semantic Segmentation Diffusion Models Flow Matching

Mar 19, 2026

DreamPartGen: Semantically Grounded Part-Level 3D Generation via Collaborative Latent Denoising

Understanding and generating 3D objects as compositions of meaningful parts is fundamental to human perception and reasoning. However, most text-to-3D methods overlook the semantic and functional structure of parts. While recent part-aware approaches introduce decomposition, they remain largely geometry-focused, lacking semantic grounding and failing to model how parts align with textual descriptions or their inter-part relations. We propose DreamPartGen, a framework for semantically grounded, part-aware text-to-3D generation. DreamPartGen introduces Duplex Part Latents (DPLs) that jointly model each part's geometry and appearance, and Relational Semantic Latents (RSLs) that capture inter-part dependencies derived from language. A synchronized co-denoising process enforces mutual geometric and semantic consistency, enabling coherent, interpretable, and text-aligned 3D synthesis. Across multiple benchmarks, DreamPartGen delivers state-of-the-art performance in geometric fidelity and text-shape alignment.

Tianjiao Yu, Xinzhuo Li, Muntasir Wahed +4

University of Illinois Urbana-Champaign

Part-Level 3D Generation 3D Shape Generation Text-to-3D Generation Diffusion Models

Mar 19, 2026

RPiAE: A Representation-Pivoted Autoencoder Enhancing Both Image Generation and Editing

Diffusion models have become the dominant paradigm for image generation and editing, with latent diffusion models shifting denoising to a compact latent space for efficiency and scalability. Recent attempts to leverage pretrained visual representation models as tokenizer priors either align diffusion features to representation features or directly reuse representation encoders as frozen tokenizers. Although such approaches can improve generation metrics, they often suffer from limited reconstruction fidelity due to frozen encoders, which in turn degrades editing quality, as well as overly high-dimensional latents that make diffusion modeling difficult. To address these limitations, We propose Representation-Pivoted AutoEncoder, a representation-based tokenizer that improves both generation and editing. We introduce Representation-Pivot Regularization, a training strategy that enables a representation-initialized encoder to be fine-tuned for reconstruction while preserving the semantic structure of the pretrained representation space, followed by a variational bridge which compress latent space into a compact one for better diffusion modeling. We adopt an objective-decoupled stage-wise training strategy that sequentially optimizes generative tractability and reconstruction-fidelity objectives. Together, these components yield a tokenizer that preserves strong semantics, reconstructs faithfully, and produces latents with reduced diffusion modeling complexity. Experiments demonstrate that RPiAE outperforms other visual tokenizers on text-to-image generation and image editing, while delivering the best reconstruction fidelity among representation-based tokenizers.

Yue Gong, Hongyu Li, Shanyuan Liu +8

Beihang University · AI Research · The Chinese University of Hong Kong

T2I Diffusion Models Diffusion-Based Image Generation Diffusion-Based Image Editing Diffusion Models Latent Diffusion Models

Mar 18, 2026

Towards Infinitely Long Neural Simulations: Self-Refining Neural Surrogate Models for Dynamical Systems

Recent advances in autoregressive neural surrogate models have enabled orders-of-magnitude speedups in simulating dynamical systems. However, autoregressive models are generally prone to distribution drift: compounding errors in autoregressive rollouts that severely degrade generation quality over long time horizons. Existing work attempts to address this issue by implicitly leveraging the inherent trade-off between short-time accuracy and long-time consistency through hyperparameter tuning. In this work, we introduce a unifying mathematical framework that makes this tradeoff explicit, formalizing and generalizing hyperparameter-based strategies in existing approaches. Within this framework, we propose a robust, hyperparameter-free model implemented as a conditional diffusion model that balances short-time fidelity with long-time consistency by construction. Our model, Self-refining Neural Surrogate model (SNS), can be implemented as a standalone model that refines its own autoregressive outputs or as a complementary model to existing neural surrogates to ensure long-time consistency. We also demonstrate the numerical feasibility of SNS through high-fidelity simulations of complex dynamical systems over arbitrarily long time horizons.

Qi Liu, Laure Zanna, Joan Bruna

Courant Institute School of Mathematics, Computing, and Data Science, New York University, USA.

Neural Surrogate Modeling Autoregressive Modeling Dynamical Systems Diffusion Models

Mar 18, 2026

FrescoDiffusion: 4K Image-to-Video with Prior-Regularized Tiled Diffusion

Diffusion-based image-to-video (I2V) models are increasingly effective, yet they struggle to scale to ultra-high-resolution inputs (e.g., 4K). Generating videos at the model's native resolution often loses fine-grained structure, whereas high-resolution tiled denoising preserves local detail but breaks global layout consistency. This failure mode is particularly severe in the fresco animation setting: monumental artworks containing many distinct characters, objects, and semantically different sub-scenes that must remain spatially coherent over time. We introduce FrescoDiffusion, a training-free method for coherent large-format I2V generation from a single complex image. The key idea is to augment tiled denoising with a precomputed latent prior: we first generate a low-resolution video at the underlying model resolution and upsample its latent trajectory to obtain a global reference that captures long-range temporal and spatial structure. For 4K generation, we compute per-tile noise predictions and fuse them with this reference at every diffusion timestep by minimizing a single weighted least-squares objective in model-output space. The objective combines a standard tile-merging criterion with our regularization term, yielding a closed-form fusion update that strengthens global coherence while retaining fine detail. We additionally provide a spatial regularization variable that enables region-level control over where motion is allowed. Experiments on the VBench-I2V dataset and our proposed fresco I2V dataset show improved global consistency and fidelity over tiled baselines, while being computationally efficient. Our regularization enables explicit controllability of the trade-off between creativity and consistency.

Hugo Caselles-Dupré, Mathis Koroglu, Guillaume Jeanneret +2

Obvious Research, Paris, France · Sorbonne Université, CNRS, ISIR, F-75005 Paris, France · Valeo.ai, France

High-Resolution Video Generation Image-to-Video Generation Video Generation Diffusion Models Temporal Consistency in Video Generation Controllable Video Generation

Mar 18, 2026

Learning Permutation Distributions via Reflected Diffusion on Ranks

The finite symmetric group S_n provides a natural domain for permutations, yet learning probability distributions on S_n is challenging due to its factorially growing size and discrete, non-Euclidean structure. Recent permutation diffusion methods define forward noising via shuffle-based random walks (e.g., riffle shuffles) and learn reverse transitions with Plackett-Luce (PL) variants, but the resulting trajectories can be abrupt and increasingly hard to denoise as n grows. We propose Soft-Rank Diffusion, a discrete diffusion framework that replaces shuffle-based corruption with a structured soft-rank forward process: we lift permutations to a continuous latent representation of order by relaxing discrete ranks into soft ranks, yielding smoother and more tractable trajectories. For the reverse process, we introduce contextualized generalized Plackett-Luce (cGPL) denoisers that generalize prior PL-style parameterizations and improve expressivity for sequential decision structures. Experiments on sorting and combinatorial optimization benchmarks show that Soft-Rank Diffusion consistently outperforms prior diffusion baselines, with particularly strong gains in long-sequence and intrinsically sequential settings.

Sizhuang He, Yangtian Zhang, Shiyang Zhang +1

Department of Computer Science, Yale University, New Haven, CT, USA.

Diffusion Models

Mar 17, 2026

V-Co: A Closer Look at Visual Representation Alignment via Co-Denoising

Pixel-space diffusion has recently re-emerged as a strong alternative to latent diffusion, enabling high-quality generation without pretrained autoencoders. However, standard pixel-space diffusion models receive relatively weak semantic supervision and are not explicitly designed to capture high-level visual structure. Recent representation-alignment methods (e.g., REPA) suggest that pretrained visual features can substantially improve diffusion training, and visual co-denoising has emerged as a promising direction for incorporating such features into the generative process. However, existing co-denoising approaches often entangle multiple design choices, making it unclear which are truly essential. We therefore present V-Co, a systematic study of visual co-denoising in a unified JiT-based framework. This controlled setting allows us to isolate the ingredients that make visual co-denoising effective. Our study reveals two main ingredients. First, co-denoising benefits from preserving feature-specific computation while enabling flexible cross-stream interaction, which leads to a fully dual-stream architecture together with a structurally defined unconditional prediction for classifier-free guidance. Second, it requires both stronger semantic supervision and proper cross-stream calibration, which we realize through a perceptual-drifting hybrid loss and RMS-based feature rescaling. Together, these findings yield a simple recipe for visual co-denoising. Experiments on ImageNet-256 show that, at comparable model sizes, V-Co outperforms the underlying pixel-space diffusion baseline and strong prior pixel-diffusion methods while using fewer training epochs, offering practical guidance for future representation-aligned generative models.

Han Lin, Xichen Pan, Zun Wang +4

1UNC Chapel Hill · 2NYU · 3Meta +1

Diffusion Model Alignment Pixel-Space Diffusion Models Diffusion-Based Image Generation Diffusion Models Image Denoising

Mar 17, 2026

Iris: Bringing Real-World Priors into Diffusion Model for Monocular Depth Estimation

In this paper, we propose Iris, a deterministic framework for Monocular Depth Estimation (MDE) that integrates real-world priors into the diffusion model. Conventional feed-forward methods rely on massive training data, yet still miss details. Previous diffusion-based methods leverage rich generative priors yet struggle with synthetic-to-real domain transfer. Iris, in contrast, preserves fine details, generalizes strongly from synthetic to real scenes, and remains efficient with limited training data. To this end, we introduce a two-stage Priors-to-Geometry Deterministic (PGD) schedule: the prior stage uses Spectral-Gated Distillation (SGD) to transfer low-frequency real priors while leaving high-frequency details unconstrained, and the geometry stage applies Spectral-Gated Consistency (SGC) to enforce high-frequency fidelity while refining with synthetic ground truth. The two stages share weights and are executed with a high-to-low timestep schedule. Extensive experimental results confirm that Iris achieves significant improvements in MDE performance with strong in-the-wild generalization.

Xinhao Cai, Gensheng Pei, Zeren Sun +3

Nanjing University of Science and Technology · State Key Laboratory of Intelligent Manufacturing of Advanced Construction Machinery · Department of Electrical and Computer Engineering, Sungkyunkwan University +2

Monocular Depth Estimation Diffusion Models Diffusion Model Guidance