Búsqueda: diffusion models

Más de 1000 artículos coinciden: estos son los 1000 más recientes, ordenados por relevancia.

• Recursive Scaling in Masked Diffusion Models

  Alba Carballo-Castro, Julianna Piskorz, Paulius Rauba, Mihaela van der Schaar, Pascal Frossard · 17 de junio de 2026 · Generative Adversarial Networks and Image Synthesis

  Masked diffusion models (MDMs) have recently emerged as a promising paradigm for sequence generation. Scaling MDMs is conventionally achieved by increasing the parameter count or the number of denoising steps. We introduce Recursive Masked Diffusion Models (R-MDMs), which add recursive depth as a th…

• Constrained Diffusion Models with Primal-Dual Inference

  Samar Hadou, Yigit Berkay Uslu, Alejandro Ribeiro · 17 de junio de 2026 · Gaussian Processes and Bayesian Inference

  This paper develops constrained diffusion models with primal-dual inference (PDI) to sample from optimal distributions of entropy-regularized optimization problems with \emph{average} constraints. We formalize constrained sampling in the Lagrangian dual domain, where the optimal distribution takes t…

• Detail++: Training-Free Detail Enhancer for Text-to-Image Diffusion Models

  Lifeng Chen, Jiner Wang, Zihao Pan, Beier Zhu, Xiaofeng Yang, Chi Zhang · 17 de junio de 2026 · AI in cancer detection

  Recent advances in text-to-image (T2I) generation have led to impressive visual results. However, these models still face significant challenges when handling complex prompt, particularly those involving multiple subjects with distinct attributes. Inspired by the human drawing process, which first o…

• Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering

  Rohit Kundu, Arindam Dutta, Sarosij Bose, Athula Balachandran, Amit K. Roy-Chowdhury · 17 de junio de 2026 · Generative Adversarial Networks and Image Synthesis

  Open-weight video diffusion models can generate photorealistic unsafe content, from violence to misinformation, yet existing defenses either require expensive safety fine-tuning that degrades general capability, or apply external filters that are trivially bypassed by adversarial prompts. We present…

• Multi-Turn Reflective Masking Elicits Reasoning in Mask Diffusion Models

  Yanming Zhang, Yihan Bian, Jingyuan Qi, Yuguang Yao, Lifu Huang, Tianyi Zhou · 16 de junio de 2026 · Generative Adversarial Networks and Image Synthesis

  While reasoning on autoregressive (AR) models is often performed by chain-of-thought reasoning and reflection, their refinement of previous outputs still relies on fully sequential generation, even when only local edits are needed. In contrast, the masking mechanism in Mask Diffusion Models (MDMs) n…

• Structure-Semantic Co-optimized Latent Diffusion Model for Fast Visual Anagram Synthesis

  Xiang Gao, Yunpeng Jia · 16 de junio de 2026 · Generative Adversarial Networks and Image Synthesis

  Visual anagram is an intriguing form of art creation wherein a single image presents different conceptual interpretations under transformations such as flipping or rotation. Recent work has achieved visual anagram synthesis by leveraging pretrained text-to-image (T2I) diffusion models, yet still suf…

• PPDM: Pixel Puzzling Diffusion Model for Speed and Memory Efficient Volumetric Medical Image Translation

  Tianqi Chen, Jun Hou, Yinchi Zhou, James S. Duncan, Chi Liu, Bo Zhou · 16 de junio de 2026 · Generative Adversarial Networks and Image Synthesis

  Diffusion models have demonstrated superior fidelity for medical image-to-image translation, but their extension to high-resolution 3D volumes is severely constrained by prohibitive computational cost and GPU memory requirements. Existing memory-efficient strategies often compromise global volumetri…

• Diffusion Models for Adaptive Sequential Data Generation

  Haoyang Cao, Minshuo Chen, Yinbin Han, Renyuan Xu · 16 de junio de 2026 · Gaussian Processes and Bayesian Inference

  Generating realistic synthetic sequential data is critical in real-world applications across operations research, finance, healthcare, energy systems, and scientific computing, where time-indexed observations are used for prediction, simulation, risk assessment, and data-driven decision-making. Whil…

• Temporal Difference Learning for Diffusion Models

  Qizhen Ying, Yangchen Pan, Victor Adrian Prisacariu, Junfeng Wen · 16 de junio de 2026 · Generative Adversarial Networks and Image Synthesis

  Diffusion models are typically trained with objectives that focus on local denoising targets at individual time steps (or adjacent pairs), which do not enforce consistency between predictions along the denoising trajectory. This lack of cross-time consistency can degrade performance, especially for …

• Wasserstein Convergence of ODE-Based Samplers in Decentralized Diffusion Model via Velocity Field Decomposition

  Chencheng Tang, Xuanyu Xue, Fangyikang Wang, Chao Zhang, Hubery Yin · 16 de junio de 2026 · Stochastic Gradient Optimization Techniques

  Diffusion models have achieved impressive empirical success in generative tasks, and their convergence theory is now relatively well understood. Motivated by privacy and scalability, recent decentralized diffusion architectures replace a single global velocity field with multiple local experts and a…

• Efficient Reinforcement for Visual-Textual Thinking with Discrete Diffusion Model

  Yoonjeon Kim, Yuhta Takida, Chieh-Hsin Lai, Eunho Yang, Yuki Mitsufuji · 16 de junio de 2026 · Multimodal Machine Learning Applications

  RL-based post-training has been widely adopted to enable interleaved visual and textual reasoning in unified multimodal models capable of both text and image generation. However, most existing approaches are built upon autoregressive (AR) unified models, which require full image regeneration during …

• Divide-and-Denoise: A Game-Theoretic Method for Fairly Composing Diffusion Models

  Abhi Gupta, Polina Barabanshchikova, Vikas Garg, Samuel Kaski, Tommi Jaakkola · 16 de junio de 2026 · Generative Adversarial Networks and Image Synthesis

  The abundance of pre-trained diffusion models provides an opportunity for composition. Combining several models, however, runs the risk of one model dominating or models disagreeing with each other. Here, we propose Divide-and-Denoise, a method for coordinating multiple pre-trained diffusion models …

• Toward 360-Degree Indoor Panorama Editing via Tuning-Free Diffusion Model with Refocusing Cross-Attention

  Dinh-Khoi Vo, Nhut-Thanh Le-Hinh, Viet-Tham Huynh, Tam V. Nguyen, Minh-Triet Tran, Trung-Nghia Le · 15 de junio de 2026 · Generative Adversarial Networks and Image Synthesis

  Zero-shot text-guided diffusion has significantly advanced image editing; however, its practical usability remains constrained by three persistent challenges: prompt brittleness that requires meticulous prompt engineering, spillover edits that unintentionally affect non-target regions, and failures …

• Denoising Score Matching with Random Features: Insights on Diffusion Models from Precise Learning Curves

  Anand Jerry George, Rodrigo Veiga, Nicolas Macris · 15 de junio de 2026 · Neural Networks and Applications

  We theoretically investigate the phenomena of generalization and memorization in diffusion models. Empirical studies suggest that these phenomena are influenced by model complexity and the size of the training dataset. In our experiments, we further observe that the number of noise samples per data …

• XRDiff: Crystal Structure Prediction from Powder X-Ray Diffraction Data Using Diffusion Models

  Nofit Segal, Mingda Li, Benjamin Kurt Miller, Rafael G\'omez-Bombarelli · 15 de junio de 2026 · X-ray Diffraction in Crystallography

  Determining the crystal structure of a material from its powder X-ray diffraction (PXRD) pattern is a central challenge in materials science. PXRD is an accessible and widely used characterization technique, yet recovering the atomic structure from diffraction data requires solving an underdetermine…

• Recursively Trained Diffusion Models: Limiting Collapse Distribution and Spectral Characterization

  Na\"il B. Khelifa, Richard E. Turner, Ramji Venkataramanan · 15 de junio de 2026 · Model Reduction and Neural Networks

  Recursive training of generative models on their own outputs can lead to model collapse, a compounding drift away from the true data distribution. Existing theoretical works bound finite-round error accumulation in the context of diffusion models, but two questions remain open:~what distribution doe…

• Decoupled Latent Optimization of Diffusion Models for Full Waveform Inversion

  Chen Min, Zheng Ma · 15 de junio de 2026 · Seismic Imaging and Inversion Techniques

  Full waveform inversion (FWI) recovers subsurface velocity from seismic recordings by solving a severely ill-posed, nonconvex PDE-constrained optimization. Classical regularizers stabilize the inversion but fail to reproduce realistic geological structures; recent diffusion-prior methods improve rea…

• Towards More General Control of Diffusion Models Using Jeffrey Guidance

  Rapha\"el Razafindralambo, R\'emy Sun, Fr\'ed\'eric Precioso, Jes Frellsen, Pierre-Alexandre Mattei · 12 de junio de 2026 · Generative Adversarial Networks and Image Synthesis

  A key strength of diffusion models lies in their flexibility, since their outputs can be controlled at sampling time through guidance. However, beyond simple cases such as conditional sampling, the target distribution is often left implicit, defined only through a sampling rule or a heuristic energy…

• Efficient, Robust, and Anti-Collusion Fingerprinting of Image Diffusion Models

  Jianwei Fei, Yunshu Dai, Zhihua Xia, Xiaochun Cao, Jiantao Zhou, Alessandro Piva, Benedetta Tondi · 12 de junio de 2026 · Adversarial Robustness in Machine Learning

  Model fingerprinting, embedding user-specific identifiers (fingerprints) into generated outputs, has recently emerged as a popular solution to protect the intellectual property rights (IPR) of generative text-to-image (T2I) models and prevent unauthorized redistribution. In this work, we reveal a pr…

• VOID: Defeating Unauthorized Mimicry in Latent Diffusion Models

  Chunlin Qiu, Ang Li, Tianxiao Huang, Ruilin Gan, Yunjie Ge, Shenyi Zhang, Huayi Duan, Lingchen Zhao, Chao Shen, Qian Wang · 11 de junio de 2026 · Adversarial Robustness in Machine Learning

  While Latent Diffusion Models (LDMs) have revolutionized visual synthesis, they are increasingly exploited for unauthorized mimicry of individuals. Existing defenses inject deceptive perturbations to steer the generated images toward irrelevant targets. However, this approach hinges on an ungrounded…

• STEDiff: Strengthening Text Embedding for Text-to-Image Alignment in Diffusion Model

  Hailan Zhang, Haipeng Liu, Bo Fu, Yang Wang · 10 de junio de 2026 · Generative Adversarial Networks and Image Synthesis

  Although pretrained text-to-image (T2I) generation models can produce high-quality images, they often fail to faithfully reflect the semantic intent of complex prompts due to stochastic noise and inherent model limitations. This issue frequently manifests as the model overlooking specific objects or…

• SSR-Merge: Subspace Signal Routing for Training-Free LoRA Merging in Diffusion Models

  Zhengxuan Wei, Yi Dong, Zonghui Li, Xianhui Lin, Xing Liu, Hong Gu, Shaofeng Zhang, Wenbin Li, Qi Fan · 10 de junio de 2026 · Generative Adversarial Networks and Image Synthesis

  Low-Rank Adaptation (LoRA) merging can efficiently combine diverse generative capabilities from multiple trained LoRAs for a diffusion model. However, existing LoRA merging techniques often suffer from severe parameter interference, causing destructive collisions in the shared parameter space. To ad…

• Breaking the Curse of Dimensionality: Diffusion Models Efficiently Learn Low-Dimensional Distributions

  Peng Wang, Huijie Zhang, Zekai Zhang, Siyi Chen, Yi Ma, Qing Qu · 10 de junio de 2026 · Neural Networks and Applications

  Despite their empirical success across a wide range of generative tasks, the fundamental principles underlying the ability of diffusion models to learn data distributions are poorly understood. In this work, we develop a new mathematical framework that explains how diffusion models can effectively l…

• The Emergence of Reproducibility and Generalizability in Diffusion Models

  Huijie Zhang, Jinfan Zhou, Yifu Lu, Minzhe Guo, Peng Wang, Liyue Shen, Qing Qu · 10 de junio de 2026 · Generative Adversarial Networks and Image Synthesis

  In this work, we investigate an intriguing and prevalent phenomenon of diffusion models which we term as "consistent model reproducibility": given the same starting noise input and a deterministic sampler, different diffusion models often yield remarkably similar outputs. We confirm this phenomenon …

• MMD Guidance: Training-Free Distribution Adaptation for Diffusion Models via Maximum Mean Discrepancy Guidance

  Matina Mahdizadeh Sani, Nima Jamali, Mohammad Jalali, Farzan Farnia · 10 de junio de 2026 · Generative Adversarial Networks and Image Synthesis

  Pre-trained diffusion models have emerged as powerful generative priors for both unconditional and conditional sample generation, yet their outputs often deviate from the characteristics of user-specific target data. Such mismatches are especially problematic in domain adaptation tasks, where only a…