Búsqueda: diffusion models

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

• Efficient bias mitigation in T2I diffusion models using Concept Graphs

  Mansi, Avinash Kori, Francesco Leofante · 7 de julio de 2026 · Generative Adversarial Networks and Image Synthesis

  Text-to-Image diffusion models often propagate harmful bias inherited from the training data. Existing bias mitigation techniques typically intervene only at the text encoder or provide inference-time guidance, often leading to generations that collapse into semantically incoherent outputs. To addre…

• Flex-Forcing: Towards a Unified Autoregressive and Bidirectional Video Diffusion Model

  Xinyin Ma, Julius Berner, Chao Liu, Arash Vahdat, Weili Nie, Xinchao Wang · 6 de julio de 2026 · Generative Adversarial Networks and Image Synthesis

  Recent progress in large-scale generative models has substantially advanced video generation, yet existing methods remain constrained by a rigid inference paradigm. Bidirectional diffusion models excel at global coherence and visual fidelity but suffer from slow inference, while autoregressive model…

• Handwriting Trajectory Recovery with Diffusion Models

  Hiroki Nagamatsu, Shoji Toyota, Seiichi Uchida · 6 de julio de 2026 · Handwritten Text Recognition Techniques

  Recovering online pen trajectories from offline handwriting images, often referred to as handwriting trajectory recovery (stroke recovery), is an offline-to-online conversion task with applications in stroke-level editing and forensic analysis. We propose, to the best of our knowledge, the first dif…

• A Decomposable Probe for Few-Step Diffusion Models: Prompt, Latent, and Score Selectivity across Backbone Families and Distillation Paradigms

  Patrick Mu Haojie · 6 de julio de 2026 · Advanced Neuroimaging Techniques and Applications

  Few-step distilled diffusion students cut text-to-image inference from ~50 to 1-8 network evaluations, but the quality gap is usually summarised by a single FID/CLIP scalar that cannot say which axis of the conditioning response changed, nor whether a behaviour comes from the architecture, the disti…

• BiSLW: Bi-Spectral Latent Watermarking for Generative Diffusion Models

  Aryan Pandit · 3 de julio de 2026 · Generative Adversarial Networks and Image Synthesis

  Diffusion-based generative models have transformed visual content synthesis, yet they remain vulnerable to unauthorized usage and lack reliable attribution methods. Existing watermarking techniques often treat latent tensors as static spatial feature maps or depend on pixel-domain modification, and …

• Hierarchical Anti-Aesthetics: Protecting Facial Privacy against Customized Diffusion Models

  Songping Wang, Yueming Lyu, Shiqi Liu, Chen Zhao, Ziyuan Chen, Ning Li, Jing Dong, Caifeng Shan · 3 de julio de 2026 · Aesthetic Perception and Analysis

  The rise of customized diffusion models has fueled a boom in personalized visual content creation, but it also introduces serious risks of malicious misuse, thereby posing threats to personal privacy. Image aesthetics are strongly correlated with human perception of image quality. Motivated by this …

• ProSAC-CT: Progressive Spectral-Anatomical Co-Guided Multi-Stage Diffusion Model for Low-Dose CT Denoising

  Xuepeng Liu, Zetong Liu, Renyiming Li, Yan Li, Ruiyu Li, Ruili Li, Jiayi Ding, Eichi Takaya · 3 de julio de 2026 · Medical Imaging Techniques and Applications

  Low-dose computed tomography (LDCT) reduces radiation exposure but introduces stronger quantum noise, streak artifacts, and local texture degradation, which can obscure anatomical boundaries and weaken low-contrast structures. Diffusion models are promising for LDCT denoising by progressively recove…

• ICDepth: Taming Video Diffusion Models for Video Depth Estimation via In-Context Conditioning

  Xuanhua He, Jiaxin Xie, Mingzhe Zheng, Qifeng Chen · 3 de julio de 2026 · Advanced Vision and Imaging

  Monocular video depth estimation requires temporal consistency, geometric accuracy, and generalization across diverse scenarios, yet existing methods struggle to achieve all three simultaneously. Discriminative models excel at per-frame accuracy but suffer from temporal drift due to limited context …

• A Mathematical Introduction to Diffusion Models

  Jianfeng Lu · 3 de julio de 2026 · Markov Chains and Monte Carlo Methods

  These notes give a proof-oriented introduction to diffusion models from the viewpoint of sampling, tracing a single arc from classical sampling dynamics to modern diffusion samplers, their error analysis, and inference-time control. Throughout, the material is layered into core definitions and ident…

• Look But Don't Touch with Sparse Autoencoders for Unlearning in Diffusion Models

  Enrico Cassano, Riccardo Renzulli, Rayyan Ahmed, Marco Grangetto, Stephan Alaniz · 3 de julio de 2026 · Generative Adversarial Networks and Image Synthesis

  Sparse autoencoders (SAEs) have recently been proposed as interpretable tools for concept-level manipulation, under the assumption that isolated features can serve as controllable intervention points. In this work, we systematically evaluate this assumption in the context of object erasure and steer…

• Locality-Aware Continual Unlearning for Diffusion Models

  Naveen George, Naoki Murata, Yuhta Takida, Konda Reddy Mopuri, Yuki Mitsufuji · 3 de julio de 2026 · Generative Adversarial Networks and Image Synthesis

  Real-world deployment of text-to-image diffusion models requires continual concept removal as new privacy, copyright, or safety obligations arise over time. Existing unlearning methods, however, are designed for single-step deletion and collapse after only 3-5 sequential applications. We trace this …

• ADMC: Attention-based Diffusion Model for Missing Modalities Feature Completion

  Yuhan Li, Wei Zhang, Juan Chen, Jiangjia Yan, Peng Xiangli, Liangze Yin · 3 de julio de 2026 · Emotion and Mood Recognition

  Multimodal emotion and intent recognition is essential for automated human-computer interaction, It aims to analyze users' speech, text, and visual information to predict their emotions or intent. One of the significant challenges is that missing modalities due to sensor malfunctions or incomplete d…

• Subliminal Clocks: Latent Time Modelling in Diffusion Language Models

  Maximo Rulli (Sapienza University of Rome), Thomas Fontanari (Sapienza University of Rome), Simone Petruzzi (Sapienza University of Rome), Federico Alvetreti (Sapienza University of Rome), Giorgio Strano (Sapienza University of Rome), Donato Crisostomi (Sapienza University of Rome), Giorgos Nikolaou (EPFL), Tommaso Mencattini (EPFL), Andrea Santilli (Independent researcher), Emanuele Rodol\`a (Sapienza University of Rome), Simone Scardapane (Sapienza University of Rome), Alessio Devoto (Independent researcher) · 3 de julio de 2026 · Large Language Models

  Diffusion Language Models (DLMs) have recently emerged as a promising alternative to autoregressive models. Unlike standard diffusion-based approaches, DLMs are not explicitly conditioned on a timestep, raising a natural question: do these models internally represent denoising progress, and how is s…

• Training-Free Debiasing of Diffusion Models via CLIP-Guided Denoising Optimization

  Dain Kim, Jinseo Kim, Sungyong Baik · 2 de julio de 2026 · Generative Adversarial Networks and Image Synthesis

  Text-to-image diffusion models achieve impressive visual quality, yet demographic bias remains a challenge, as neutral prompts consistently produce stereotypical representations across gender and race. Existing approaches remain limited by costly retraining or by inference-time interventions that of…

• DriftScope: Measuring The Hidden Effects of Diffusion Model Adaptation

  Héctor Laria, Yiping Han, Julian D. Santamaria, Kai Wang, Bogdan Raducanu, Joost van de Weijer, Alexandra Gomez-Villa · 2 de julio de 2026 · Domain Adaptation and Few-Shot Learning

  Adapting pre-trained text-to-image diffusion models, whether to learn new visual concepts or erase unwanted ones, is routinely evaluated on its intended effects alone. We argue this framing is incomplete. Through sparse autoencoder analysis and zero-shot classification, we demonstrate that adaptatio…

• Accelerating Discrete Diffusion Models with Parallel-In-Time Sampling

  Yu Yao, Huanjian Zhou, Andi Han, Wei Huang, Masashi Sugiyama · 2 de julio de 2026 · Generative Adversarial Networks and Image Synthesis

  Discrete diffusion models are widely used for learning and generating discrete distributions. As the generation process is inherently sequential, the acceleration of sampling is of significant importance. In this work, we parallelize the mainstream $\tau$-leaping algorithm for absorbing discrete dif…

• The Illusion of High Utility in Safety Alignment of Text-to-Image Diffusion Models

  Adeel Yousaf, Soumik Ghosh, James Beetham, Amrit Singh Bedi, Mubarak Shah · 2 de julio de 2026 · Adversarial Robustness in Machine Learning

  Safety alignment of text-to-image (T2I) diffusion models aims to suppress harmful generations while preserving utility on benign prompts. Recent methods often appear to deliver high safety with high utility, but this conclusion rests largely on coarse global utility metrics (e.g., FID, CLIPScore) th…

• Wavelet-Optimized Pseudo-3D Accelerated Diffusion Model for Truncated Computed Laminography

  Genyuan Zhang, Junyao Wang, Chuandong Tan, Fenglin Liu, Yongning Zhou · 1 de julio de 2026 · Optical measurement and interference techniques

  Computed Laminography (CL) is a key technology for the nondestructive testing of large plate-shaped objects. However, field-of-view (FOV) limitations inevitably lead to truncation of projected data, an ill-posed inverse problem that causes severe reconstruction artifacts. Existing deep learning meth…

• Look But Don't Touch with Sparse Autoencoders for Unlearning in Diffusion Models

  Enrico Cassano, Riccardo Renzulli, Rayyan Ahmed, Marco Grangetto, Stephan Alaniz · 1 de julio de 2026 · Generative Adversarial Networks and Image Synthesis

  Sparse autoencoders (SAEs) have recently been proposed as interpretable tools for concept-level manipulation, under the assumption that isolated features can serve as controllable intervention points. In this work, we systematically evaluate this assumption in the context of object erasure and steer…

• Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models

  Nikolai R\"ohrich, Julian Glei{\ss}ner, Ahmed H. A. Ibrahim, Silvan Mertes, Tobias Huber · 1 de julio de 2026 · Advanced Neural Network Applications

  Semantic segmentation models struggle with data sparsity and rare or visually diverse regions, e.g., dense regions or small objects in aerial or autonomous mobility data. While synthetic augmentation is an appealing solution, directly generating new labeled data risks misalignment of labels and gene…

• TDGT: A Tabular Data Generation Toolkit supporting adaptive GPU-accelerated Bayesian mixture models, diffusion-based models, and latent-space generative modeling

  Vasileios C. Pezoulas, Nikolaos S. Tachos, Eleni Georga, Kostas Marias, Manolis Tsiknakis, Dimitrios I. Fotiadis · 1 de julio de 2026 · Privacy-Preserving Technologies in Data

  The growing demand for privacy-preserving data sharing has positioned synthetic data generation as a critical component of responsible AI workflows. Despite notable advances in generative modeling, existing solutions often lack integration of adaptive generation strategies, multi-metric evaluation, …

• OTCache: Optimal Transport for Geometry-Aware Caching in Diffusion Models

  Huanlin Gao, Fang Zhao, Qiang Hui, Fuyuan Shi, Shaoan Zhao, Yantao Li, Chao Tan, Ting Lu, Yuren You, Kai Wang, Shiguo Lian · 1 de julio de 2026 · Advanced Neuroimaging Techniques and Applications

  We propose OTCache, a training-free framework for accelerating diffusion sampling via caching schedule prediction. Existing graph-based caching methods reduce redundant computation by optimizing shortest-path objectives, but rely on an additive independence assumption, which often breaks down in the…

• DSIP: A Dynamic Coordination Planner for Signal-Free Intersections using Diffusion-Model-Based Multi-Agent Motion Planning

  Qian Hu, Haoyang Peng, Songan Zhang, Ming Yang, Hongtei Eric Tseng · 1 de julio de 2026 · Traffic control and management

  Traffic signal control at urban intersections inherently introduces stop-and-go behavior, resulting in increased delays and reduced traffic efficiency, especially under high traffic demand. With the emergence of connected and automated vehicles (CAVs), trajectory-level coordination has emerged as a …

• Unsupervised Thermodynamics of Molecular Diffusion Models: Action-Operator Semantics and Auditable Free-Energy Readout

  Wenjie Xi · 1 de julio de 2026 · Protein Structure and Dynamics

  Diffusion models are increasingly utilized for modeling molecular structures and conformational ensembles, yet the thermodynamic meaning of their learned representations and scores remains elusive. To resolve this ambiguity, we introduce a mathematically consistent action-operator framework natively…

• Beyond Point Estimates for Glaucoma Visual Field Forecasting with Diffusion Models

  Marta Colmenar Herrera, Pablo Márquez Neila, Şerife Seda Kucur Ergünay, Martin S. Zinkernagel, Raphael Sznitman · 30 de junio de 2026 · Ophthalmology and Visual Impairment Studies

  Forecasting visual fields (VFs) is critical for personalized monitoring and treatment planning in glaucoma. This is inherently uncertain due to heterogeneous disease progression and measurement variability, yet most existing methods produce single deterministic predictions that fail to represent thi…