Latest Image Generation Research Papers

The newest Image Generation papers from across the field — arXiv, NeurIPS, CVPR, Nature, and more — refreshed daily and ranked by relevance. Distill AI tracks Image Generation so you don’t have to: get the standout work delivered to your inbox every morning, with 2-sentence summaries and the option to chat with any paper.

Recent papers

• Antibacterial Activity Of Manganese-Doped Zinc Oxide Nanoparticles Against Multidrug Resistant Salmonella Typhi
  Nasir Shah Khalil, Muhammad Saddam, Faraz Ahmad Khan, Shahzad Anwar Durrani et al. · Pakistan Journal of Medical... · Nov 23, 2026

  Background: Multiple drug resistant (MDR) Salmonella Typhi is a public health threat. Due to their unique physicochemical properties, the manganese doped with zinc oxide nanoparticles (Mn-ZnO NPs) have become of interest as possible antimic…

• MoI-Bench: A Benchmark for Image Generation and Editing on Mobile Devices
  Kailai Feng, Haoxiang Rao, Yuxiang Wei, Bo Chen et al. · arXiv · Oct 27, 2026

  Developing on-device image models requires considering practical user needs, task types and device resource constraints. However, existing benchmarks provide limited guidance on identifying capability gaps between on-device models and serve…

• ALADDIN: Adversarial Latent Diffusion Distillation for One-Step Identity Swapping
  Ivan Shchekotov, Timofei Gritsaev, Viacheslav Pirogov, Dmitry Vetrov · arXiv · Oct 27, 2026

  Face swapping transfers a source identity onto a target image while preserving the target's pose, expression, hair, and lighting. The most realistic current methods are diffusion-based, but they need many network evaluations per image. GAN-…

• VPR-Space: A Benchmark for Visual Place Recognition in Space Analog Domains
  Richard Fechner, Peer Neubert · arXiv · Oct 26, 2026

  Visual Place Recognition (VPR) is an important means for loop closure detection in visual Simultaneous Localization and Mapping (SLAM). While state-of-the-art VPR and SLAM approaches excel in urban and feature-rich natural environments, the…

• Standing on Open Shoulders: Regional Fine-Tuning of Open-Weight Camera-Trap Models for UK Wildlife with Modest Data and Compute
  Paul Fergus · arXiv · Oct 23, 2026

  Camera-trap species classification is dominated by large models from well-resourced organisations, which often lack the species-level distinctions regional conservation needs, such as native red versus invasive grey squirrels in the UK. We …

• Squaring-the-Sphere: Distortion-Free and Seamless Panorama Generation via CubeAtlas
  Xuhui Zuo, Chenjie Cao, Tengfei Wang, Junta Wu et al. · arXiv · Oct 22, 2026

  Generating 360-degree panoramas requires both local perspective fidelity and global spherical continuity. Existing representations face a trade-off: equirectangular projection (ERP) enables seamless panorama modeling but suffers from severe…

• Compositionality with Primitives: A Unified View from Euclidean to Hyperbolic Vision-Language Models
  Puru Vaish, Meelad Dashti, Christoph Brune, Pascal Mettes et al. · arXiv · Oct 21, 2026

  Compositional zero-shot learning (CZSL) aims to recognize novel combinations of previously observed objects and attributes. Prior work showed that large-scale vision-language models encode decomposable semantic structures that can be recomp…

• Key Findings for Small UAS for Post-Disaster Damage Assessment from the CURSE'26 Exercise
  Thomas Manzini, Stephen Johnson, Priyankari Perali, David Merrick et al. · arXiv · Oct 21, 2026

  The CLARKE building and road damage assessment AI classifier was incorporated into the Catastrophic Unmanned Remote Sensing Exercise (CURSE) 2026, which trained 23 small uncrewed aerial systems (sUAS) teams from state and local agencies and…

• Spatially Gated Demographic Steering for Debiasing Multi-Person Text-to-Image Generation
  Venkatesh Thirugnana Sambandham, Torsten Schon · arXiv · Oct 21, 2026

  Text-to-Image models reproduce societal stereotypes, and existing mitigation applies one demographic correction to the whole scene. In multi-person scene generation this creates a trade-off: global steering improves aggregate balance only b…

• PsycheMME: A Psychology-Informed Benchmark for Social Understanding and Interaction in Videos
  Heran Hu, Yuhang Dong, Zhucun Xue, Kaiwei Chen et al. · arXiv · Oct 20, 2026

  Understanding human needs and selecting responses require distinct judgments that aggregate accuracy can obscure. We introduce PsycheMME, a video benchmark informed by psychology, with eight capabilities spanning grounding, states, needs, i…

• Copyright Leakage Detection in AI Generated Videos
  Shaif Chowdhury, Moshiur Rahman Tonmoy · arXiv · Oct 20, 2026

  Video generation models can create realistic-looking video footage from images and text prompts. Some of the recent advances have raised concerns about the reproduction of copyrighted visual content. However, copyright leakage detection in …

• Text-to-Image Generative Modeling Without Language Pretraining
  Keshigeyan Chandrasegaran, Yue Zhao, Armin W. Thomas, Ehsan Adeli et al. · arXiv · Oct 19, 2026

  Modern text-to-image (T2I) systems use internet-scale language pretraining for text-conditioned image generation. We ask whether language pretraining is necessary for strong T2I generation. We introduce Halcyon, a family of early-fusion mul…

• Scaling Vision Foundation Models for Toxicologic Pathology
  Jessica Loo, Theodoros Pissas, Byunghak Kang, Vincent A. Ella et al. · arXiv · Oct 19, 2026

  Here, we present TOX-FM, a family of non-clinical PFMs trained on large-scale diverse histopathology datasets of over one million whole slide images consisting of over 60 organs across six animal species from over 14,000 toxicology studies …

• 3D Diffusion Models for Medical Imaging
  Frank-Peter Schilling, Daniel Barco, Philipp Denzel, Marc Stadelmann · arXiv · Oct 19, 2026

  Generative deep learning methods such as Variational Autoencoders, Generative Adversarial Networks or Diffusion Models have achieved remarkable results in image synthesis. In particular, Diffusion Models have demonstrated superior image fid…

• PALYIM: A Modular, Open-Source Science Gateway for AI-Enabled Palynology Image Analysis
  Sandeep Puthanveetil Satheesan, Luigi Marini, Shu Kong, Carlos Alberto Jaramillo et al. · Zenodo (CERN European Organ... · Oct 19, 2026

  We introduce PALYIM (PALYnology IMage Analysis Platform), a web-based, intelligent, modular, and extensible platform under development for processing and visualizing Z-stack Whole Slide Image collections using published AI models for palyno…

• PreciseEdit: Strong Yet Stable Semantic Transport for One-Step Image Editing
  Jingyi Wang, Xiao Lu · arXiv · Oct 16, 2026

  Recent one-step text-to-image (T2I) models enable efficient image synthesis, opening up new possibilities for interactive Web-based image editing. However, existing one-step editing methods often construct a global transport field through s…

• ReVision: Reprogramming Image Generators for Dense Visual Perception
  Yitong Yang, Yinglin Wang, Xuexin Liu, Wei Chen et al. · arXiv · Oct 16, 2026

  Recent image generators exhibit rich visual priors that can support dense visual perception. However, existing approaches typically encode multiple perception tasks into a shared parameterization, making joint training sensitive to the mixt…

• PONDER: Learning to Generate in the Right Order
  Julius Erbach, Dominik Narnhofer, Bernt Schiele, Jan Eric Lenssen et al. · arXiv · Oct 16, 2026

  We introduce PONDER, a method that learns in which order an image generator should fill in content and which of its earlier predictions to revise. Masked generative models construct a sample by repeatedly filling in subsets of missing varia…

• Which Tokens to Merge? Diffusion Dynamics for Efficient Image Generation
  SeungJu Cha, Ye-Chan Kim, HyunGee Kim, Sungho Koh et al. · arXiv · Oct 15, 2026

  Token merging has emerged as an effective training-free strategy for accelerating diffusion models by reducing redundant token computation while minimizing generation degradation. A key challenge is determining which tokens can be safely me…

• Not Just a Subject: Capturing Adaptive Scene-Specific Variance for Visual Storytelling
  SeungJu Cha, Ye-Chan Kim, Kwanyoung Lee, Dong-Jin Kim · arXiv · Oct 15, 2026

  Recent advancements in diffusion models have significantly improved text-to-image generation, enabling their application to visual storytelling, where coherent image sequences are generated from narrative prompts. However, existing methods …

• SCOPE: Semantic Bounded Credit Optimization for Prompt Engineering in Text-to-image Generation
  Yufei Jiao, Jinfa Huang, Zeyue Xue, Tianyu Xie et al. · arXiv · Oct 15, 2026

  Reinforcement learning (RL) enables language models to improve text-to-image (T2I) generation by rewriting prompts for a frozen image generator. Existing methods typically apply a single signal derived from the image to individual subword t…

• CommerceGen-Studio: An End-to-End Framework for Commercial-Grade Main-Image Generation
  Xiaoli Xu, Zhengtao Wu, Zhengze Xu, Tao Liu et al. · arXiv · Oct 14, 2026

  We present CommerceGen-Studio, an end-to-end framework for generating commercial-grade main images for e-commerce Stock Keeping Units (SKUs). Our framework is organized along a three-stage pipeline of information extraction, semantic rewrit…

• InstantFusion: A Shared Latent Interface for Heterogeneous Image Generators
  Xuanlang Dai, Jiazi Bu, Yujie Zhou, Yuhong Liu et al. · arXiv · Oct 9, 2026

  Diffusion/flow models have emerged as the de facto paradigms for image generation, giving rise to a diverse family of modern generators with increasingly heterogeneous architectures and representations. Despite their remarkable generation c…

• UkrMeme: Multimodal Explainable Persuasion Detection in Ukrainian Memes
  Nazar Andrushko, Vera Schmitt, Veronika Solopova · arXiv · Oct 9, 2026

  Memes play a central role in modern online communication, especially in contexts of political conflict where visual and textual cues combine to convey persuasive messages. We study persuasive technique detection in Ukrainian memes using vis…

• State-Isolated Vision Mamba via Update-Tendency Routing for Underwater Image Enhancement
  Yan Luo, Laibin Chang, Zefan Feng, Yi'ang Chen et al. · arXiv · Oct 9, 2026

  Vision Mamba has recently emerged as an efficient alternative to convolutional and Transformer-based architectures by modeling long-range spatial dependencies through recurrent state evolution. Existing studies primarily improve token seria…

• BudgetPix: Compute-Adaptive Tokenization for Pixel-Space Image Diffusion
  Ozgur Kara, Yujia Chen, Daniel Watson, David Forsyth et al. · arXiv · Oct 8, 2026

  Most image generation models rely on uniform tokenization, allocating the exact same computational budget to equally-sized image patches. This static paradigm cannot adapt to different resource constraints at inference time, and yields subo…

• Slot3R: Set-Associative Spatial Memory for Streaming 3D Reconstruction
  Xiyuan Zhang, Yanming Yang, Kaiyuan Xu, Ruibo Li et al. · arXiv · Oct 8, 2026

  Streaming 3D reconstruction must preserve evidence from each frame while processing an expanding scene online. Spatial memory is a natural fit because it organizes history by reconstructed 3D location. Yet Point3R uses spatial proximity bot…

• QuadTok: Quadtree Visual Tokenizer for Autoregressive Image Generation
  Yucheng Mao, Zeyuan Chen, Xiaojun Shan, Xiang Zhang et al. · arXiv · Oct 7, 2026

  We introduce QuadTok, a novel framework for visual tokenization and autoregressive image generation. Compared to traditional approaches using 2D grids or 1D token sequences, we propose a hierarchical quadtree structure, bridging the gap bet…

• Multitask Conditional Generative Adversarial Network Enables Automatic Whole Knee Cartilage and Menisci Segmentation and Reliable T1\r{ho} and T2 Quantification Without High-Resolution Morphological Images
  Ahmed Tahseen Minhaz, Richard Lartey, Zhiyuan Zhang, Jeehun Kim et al. · arXiv · Oct 5, 2026

  Early osteoarthritis detection through quantitative MRI (qMRI) requires accurate cartilage and meniscus segmentation, traditionally necessitating time-consuming, costly 3D high-resolution Double Echo Steady-State (DESS) MRI scans. This stud…

• Harmful Content Generation in Text-to-Image Models: Capabilities and Moderation Limitations
  Paschalis Giakoumoglou, Manos Schinas, Symeon Papadopoulos · arXiv · Oct 5, 2026

  Text-to-image generative models can produce highly realistic imagery but also raise concerns about harmful misuse. While safety mechanisms exist, systematic evaluations of their effectiveness against realistic attacks remain limited. We pre…