Latent Diffusion Models

Follow this topic Ask about this topic

Momentum

9 papers in the last four weeks, up 13% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 143

All topics

Slot-RAE: Streamlining Object-Centric Learning via Direct Representation Auto-Encoders
Jul 13, 2026Alexandre Chapin, Emmanuel Dellandrea, Liming ChenLatent Diffusion Models Image Generation
LIRIS, imagine
Autoregressive latent diffusion for 3D molecule generation
Jul 10, 2026Federico Ottomano, Gaopeng Ren, Yingzhen Li +2Latent Diffusion Models Molecular Graph Generation
Department of Chemistry Imperial College London · Department of Computing Imperial College London
ReGen: Hierarchical Multi-Prompt Representation Generation for Efficient Waveform Diffusion Models
Jul 10, 2026Sang-Hoon Lee, Ha-Yeong ChoiAudio Representation Learning Latent Diffusion Models
Department of Artificial Intelligence, Ajou University, Suwon, Korea · KT Corp., Seoul, Korea
An Hybrid Quantum-Classical Diffusion Model for Image Generation
Jul 8, 2026Qipeng Qian, Keli Deng, Yuntao QianLatent Diffusion Models Quantum Generative Modeling
Program of Applied Mathematics, Department of Mathematics, University of Arizona, Tucson, USA · College of Computer Science and Technology, Zhejiang University, Hangzhou, China
Tuning-Free Latent Diffusion Models for Ultrahigh-Resolution Image Editing
Jul 7, 2026Wanglong Lu, Lingming Su, Kaijie Shi +4Latent Diffusion Models Diffusion Sampling
College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou 325035, China · Department of Computer Science, Memorial University of Newfoundland, St. John’s, NL A1B 3X5, Canada · AI Analytics Team, Nasdaq, St. John’s, NL A1A 0L9, Canada +2
AI for Cultural Heritage Textiles: Fine-Tuned Latent Diffusion for Novel Ulos Motif Synthesis
Jul 6, 2026Humasak Tommy Argo Simanjuntak, Jesika Purba, Sitogab Girsang +4Latent Diffusion Models Image Generation
Information Systems Study Program, Faculty of Informatics and Electrical Engineering, Institut Teknologi Del · Informatics Study Program, Faculty of Informatics and Electrical · Informatics Department, Institut Teknologi Sepuluh Nopember
CONFLUX: A Latent Diffusion Model for 3D Chest-CT Synthesis with RL Post-Training
Jul 3, 2026Max Van Puyvelde, Halil Ibrahim Gulluk, Wim Van Criekinge +1Latent Diffusion Models Medical Image Synthesis
Department of Biomedical Data Science, Stanford University School of Medicine · Department of Mathematical Modelling, Statistics & Bioinformatics, Ghent University · Department of Electrical Engineering, Stanford University
BiSLW: Bi-Spectral Latent Watermarking for Generative Diffusion Models
Jul 2, 2026Aryan PanditDiffusion Model Watermarking Latent Diffusion Models
PDPM Indian Institute of Information Technology, Jabalpur, India
InterCMDM: Block-Causal Diffusion for Autoregressive Human Interaction Generation
Jul 2, 2026Qing Yu, Kent FujiwaraDiffusion Transformer Latent Diffusion Models
LY Corporation, Tokyo, Japan
MapDreamer: Aerial Imagery Conditioned Latent Diffusion for Lane-Level Map Generation
Jul 1, 2026Julian Brandes, Philipp Crocoll, Wolfram BurgardHD Map Construction Latent Diffusion Models
Department CSAI at University of Technology Nuremberg, Nuremberg, Germany · Robert Bosch GmbH, Stuttgart
SynLaD: Latent Diffusion for Generating Synthesizable Molecules Conditioned on 3D Pharmacophore Profiles
Jul 1, 2026Miruna Cretu, John Bradshaw, Patricia Suriana +6Latent Diffusion Models 3D Molecular Generation
University of Cambridge, Cambridge, UK · Prescient Design (AI for Drug Discovery), Genentech, South San Francisco, USA · Work done during an internship at Prescient Design
No Prompt, No Leaks: A Robust Generative Steganography Framework via Prompt-Free Diffusion
Jun 30, 2026Jingwen Cai, Fen Xiao, Shuhua Deng +1Latent Diffusion Models Diffusion-Based Image Generation
MOE Key Laboratory of Intelligent Computing and Information Processing, Xiangtan University, Xiangtan 411105, China · College of Information Science and Engineering, Hunan Normal University, Changsha 410006, China
Patch-PODiff-ViT: Structured Latent Diffusion with Patchwise POD for Super-Resolution and Uncertainty Quantification
Jun 30, 2026Onkar Jadhav, Tim French, Matthew Rayson +1Diffusion Models for Image Restoration Uncertainty Quantification
School of Earth and Oceans, UWA Oceans Institute University of Western Australia Crawley, WA, Australia · School of Physics, Mathematics and Computing, Computer Science and Software Engineering University of Western Australia Crawley, WA, Australia
WarpI2I: Image Warping for Image-to-Image Translation
Jun 30, 2026Shen Zheng, Anurag Ghosh, Gaurav Parmar +1Image-to-Image Translation Latent Diffusion Models
Carnegie Mellon University
Rethinking Forgery Attacks on Semantic Watermarks in Black-Box Settings: A Geometric Distortion Perspective
Jun 29, 2026Cheng-Yi Lee, Yichi Zhang, Yuchen Yang +2Latent Diffusion Models Digital Image Forensics
Academia Sinica, Taipei, Taiwan, ROC · The Pennsylvania State University, PA, US
Bidirectional Autoregressive Latent Diffusion for Forward and Inverse Magnetohydrodynamics
Jun 28, 2026Alexander ScheinkerUncertainty Quantification Autoregressive Diffusion
Los Alamos National Laboratory, Los Alamos, NM, 87545.
Evidence-Based Text-Conditioned 3D CT Synthesis for Ovarian Cancer
Jun 27, 2026Francesca Pia Panaccione, Eugenio Lomurno, Francesca Fati +11Medical Imaging Latent Diffusion Models
1AIRLab, Politecnico di Milano, Milan, Italy · 2NEARLab, Politecnico di Milano, Milan, Italy · 3Istituto Europeo di Oncologia, Milan, Italy +2
Latent Diffusion Posterior Sampling with Surrogate Likelihood Guidance for PDE Inverse Problems
Jun 25, 2026Yuanzhe Wang, Alexandre M. TartakovskyLatent Diffusion Models Bayesian Inverse Problems
Department of Civil and Environmental Engineering University of Illinois Urbana-Champaign Urbana, IL 61801
TensorLDM: A Component-Wise Latent Diffusion Model for Volumetric DTI Reconstruction from Sparse DWIs
Jun 24, 2026Junhyeok Lee, Kyu Sung ChoiLatent Diffusion Models Accelerated MRI Reconstruction
Interdisciplinary Program in Cancer Biology, Seoul National University College of Medicine · Department of Radiology, Seoul National University Hospital · Department of Radiology, Seoul National University College of Medicine +1
Anatomically-conditioned Latent Diffusion Model for Data-Efficient Few-Shot Cross-Domain 3D Glioma MRI Synthesis
Jun 24, 2026Salman Shaik, Truong Thanh Hung Nguyen, Hung CaoLatent Diffusion Models Medical Image Synthesis
Analytics Everywhere Lab, University of New Brunswick, Canada
Latent Block-Diffusion Temporal Point Processes: A Semi-Autoregressive Framework for Asynchronous Event Sequence Generation
Jun 23, 2026Shuai Zhang, Yancheng Chen, Chuan Zhou +5Temporal Point Processes Latent Diffusion Models
Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing 100190, China · Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100093, China · Department of Data Science, City University of Hong Kong, Hong Kong 999077, China +1
PeLAP-A: Adaptive Latent Pruning for Lightweight Latent Diffusion Models
Jun 22, 2026Kissa Zahra, Zaib Un NisaLatent Diffusion Models Neural Network Pruning
Department of Computer Science, National University of Computer and Emerging Sciences
The Impact of VAE Design on Latent Pose Representations for Diffusion-based Sign Language Production
Jun 22, 2026Guilhem Fauré, Mostafa Sadeghi, Sam Bigeard +1Variational Autoencoders Representation Learning
MULTISPEECH · Universit´e de Lorraine, CNRS, Inria, LORIA · LORIA
FedOT: Ownership Verification and Leakage Tracing via Watermarks for Federated LDMs
Jun 22, 2026Wenlong Cheng, Yuan Gan, Yunqiu Xu +1Diffusion Model Watermarking Latent Diffusion Models
Northwest Normal University · The University of Tokyo · National University of Singapore +1
SeFi-Image: A Text-to-Image Foundation Model with Semantic-First Diffusion
Jun 21, 2026Ruoyu Feng, Jinming Liu, Yuqi Wang +7Latent Diffusion Models T2I Generation
SeFi Team
VT-DUDA: Visual Token Conditioning for Diffusion-guided Unsupervised Domain Adaptation
Jun 19, 2026Xuan Qi, Daniele Berardini, Dario Serez +2Synthetic Data Augmentation Unsupervised Domain Adaptation
AI for Good (AIGO), Istituto Italiano di Tecnologia · DITEN, University of Genoa · MaLGa, DIBRIS, University of Genoa +1
Diffusion-Driven State Space Models
Jun 19, 2026Jack Ruder, Michael WojnowiczLatent Dynamics Modeling Latent Diffusion Models
1Montana State University
CrossFlow: One-Step Generation Across Latent and Pixel Spaces
Jun 18, 2026Xiyuan Wang, Xiao Zhang, Yang Li +4Flow Matching Latent Diffusion Models
Institute for Artificial Intelligence, Peking University · Tencent · Fudan University
Addressing Detail Bottlenecks in Latent Diffusion for RGB-to-SWIR Image Translation
Jun 18, 2026Kaili Wang, Martin Dimitrievski, Jose Maria Salvador +3Image-to-Image Translation Latent Diffusion Models
imec, 3001 Leuven, Belgium · imec-IPI-Ghent University, 9000 Ghent, Belgium · Yale University, New Haven, CT, USA
DiffMath: Symbol- and Graph-Aware Latent Diffusion Transformer for Handwritten Mathematical Expression Generation
Jun 18, 2026Wei Pan, Xuhan Zheng, Yilin Shi +5Diffusion Transformer Latent Diffusion Models
South China University of Technology · Huawei Technologies Co., Ltd.

Jul 13, 2026, cs.CVJ/K move · Enter open · S save

Slot-RAE: Streamlining Object-Centric Learning via Direct Representation Auto-Encoders

Alexandre Chapin, Emmanuel Dellandrea, Liming Chen

LIRIS, imagine

Latent Diffusion Models Image Generation Object-Centric Representation Learning

Open paper AskPDF arXiv

Deploying object-centric models for real-world scene understanding typically requires complex pipelines to achieve both robust scene decomposition and high-fidelity generation. Recent diffusion-based approaches have improved visual quality, but they almost universally rely on heavy, pretrained generative priors (e.g., Stable Diffusion) and external VAE latent spaces. In this paper, we propose Slot-RAE, a much simpler, fully integrated framework that operates directly within the continuous semantic feature space of visual foundation models (e.g., DINOv3). Slot-RAE employs a feature-space diffusion process using a Diffusion Transformer (DiT) decoder and a Representation Alignment (REPA) head. Unlike existing diffusion-based objectcentric methods that rely heavily on subsidized text-toimage priors, the generative core of Slot-RAE (Slot Attention and the DiT) is trained from scratch within the frozen VFM feature space. This eliminates the need for VAE bottlenecks and task-agnostic generative pre-training. Experiments on the COCO dataset demonstrate that despite its architectural simplicity, Slot-RAE achieves state-of-the-art results. It delivers comparable unsupervised object discovery, higher-fidelity image reconstruction, and robust zero-shot compositionality, all while being significantly faster and more computationally efficient than existing object-centric latent diffusion models.

Momentum

Related topics

Latest papers 143