Generative Adversarial Networks and Image Synthesis

Latest papers

• Spherical VAE with Cluster-Aware Feasible Regions: Guaranteed Prevention of Posterior Collapse

  Zegu Zhang, Jian Zhang · 24 March 2026

  Variational autoencoders (VAEs) frequently suffer from posterior collapse, where the latent variables become uninformative as the approximate posterior degenerates to the prior. While recent work has characterized collapse as a phase transition determined by data covariance properties, existing appr…

• Scaling Laws are Redundancy Laws

  Yuda Bi, Vince D Calhoun · 24 March 2026

  Scaling laws, a defining feature of deep learning, reveal a striking power-law improvement in model performance with increasing dataset and model size. Yet, their mathematical origins, especially the scaling exponent, have remained elusive. In this work, we show that scaling laws can be formally exp…

• WorldCache: Content-Aware Caching for Accelerated Video World Models

  Umair Nawaz, Ahmed Heakl, Ufaq Khan, Abdelrahman Shaker, Salman Khan, Fahad Shahbaz Khan · 24 March 2026

  Diffusion Transformers (DiTs) power high-fidelity video world models but remain computationally expensive due to sequential denoising and costly spatio-temporal attention. Training-free feature caching accelerates inference by reusing intermediate activations across denoising steps; however, existin…

• Adaptive Video Distillation: Mitigating Oversaturation and Temporal Collapse in Few-Step Generation

  Yuyang You, Yongzhi Li, Jiahui Li, Yadong Mu, Quan Chen, Peng Jiang · 24 March 2026

  Video generation has recently emerged as a central task in the field of generative AI. However, the substantial computational cost inherent in video synthesis makes model distillation a critical technique for efficient deployment. Despite its significance, there is a scarcity of methods specifically…

• HamVision: Hamiltonian Dynamics as Inductive Bias for Medical Image Analysis

  Mohamed A Mabrok · 24 March 2026

  We present HamVision, a framework for medical image analysis that uses the damped harmonic oscillator, a fundamental building block of signal processing, as a structured inductive bias for both segmentation and classification tasks. The oscillator's phase-space decomposition yields three functionall…

• Taming Video Models for 3D and 4D Generation via Zero-Shot Camera Control

  Chenxi Song, Yanming Yang, Tong Zhao, Ruibo Li, Chi Zhang · 24 March 2026

  Video diffusion models have rich world priors, but their use in spatial tasks is limited by poor control, spatial-temporal inconsistent results, and entangled scene-camera dynamics. Current approaches, such as per-task fine-tuning or post-process warping, often introduce visual artifacts, fail to ge…

• Not All Layers Are Created Equal: Adaptive LoRA Ranks for Personalized Image Generation

  Donald Shenaj, Federico Errica, Antonio Carta · 24 March 2026

  Low Rank Adaptation (LoRA) is the de facto fine-tuning strategy to generate personalized images from pre-trained diffusion models. Choosing a good rank is extremely critical, since it trades off performance and memory consumption, but today the decision is often left to the community's consensus, re…

• End-to-End Training for Unified Tokenization and Latent Denoising

  Shivam Duggal, Xingjian Bai, Zongze Wu, Richard Zhang, Eli Shechtman, Antonio Torralba, Phillip Isola, William T. Freeman · 24 March 2026

  Latent diffusion models (LDMs) enable high-fidelity synthesis by operating in learned latent spaces. However, training state-of-the-art LDMs requires complex staging: a tokenizer must be trained first, before the diffusion model can be trained in the frozen latent space. We propose UNITE - an autoen…

• Memory-Efficient Fine-Tuning Diffusion Transformers via Dynamic Patch Sampling and Block Skipping

  Sunghyun Park, Jeongho Kim, Hyoungwoo Park, Debasmit Das, Sungrack Yun, Munawar Hayat, Jaegul Choo, Fatih Porikli, Seokeon Choi · 24 March 2026

  Diffusion Transformers (DiTs) have significantly enhanced text-to-image (T2I) generation quality, enabling high-quality personalized content creation. However, fine-tuning these models requires substantial computational complexity and memory, limiting practical deployment under resource constraints.…

• Efficient Zero-Shot AI-Generated Image Detection

  Ryosuke Sonoda, Ramya Srinivasan · 24 March 2026

  The rapid progress of text-to-image models has made AI-generated images increasingly realistic, posing significant challenges for accurate detection of generated content. While training-based detectors often suffer from limited generalization to unseen images, training-free approaches offer better r…

• Uncertainty Quantification for Distribution-to-Distribution Flow Matching in Scientific Imaging

  Dongxia Wu, Yuhui Zhang, Serena Yeung-Levy, Emma Lundberg, Emily B. Fox · 24 March 2026

  Distribution-to-distribution generative models support scientific imaging tasks ranging from modeling cellular perturbation responses to translating medical images across conditions. Trustworthy generation requires both reliability (generalization across labs, devices, and experimental conditions) a…

• On the Interplay of Priors and Overparametrization in Bayesian Neural Network Posteriors

  Julius Kobialka, Emanuel Sommer, Chris Kolb, Juntae Kwon, Daniel Dold, David R\"ugamer · 24 March 2026

  Bayesian neural network (BNN) posteriors are often considered impractical for inference, as symmetries fragment them, non-identifiabilities inflate dimensionality, and weight-space priors are seen as meaningless. In this work, we study how overparametrization and priors together reshape BNN posterio…

• Probing the Latent World: Emergent Discrete Symbols and Physical Structure in Latent Representations

  Liu hung ming · 24 March 2026

  Video world models trained with Joint Embedding Predictive Architectures (JEPA) acquire rich spatiotemporal representations by predicting masked regions in latent space rather than reconstructing pixels. This removes the visual verification pathway of generative models, creating a structural interpr…

• Generalized Discrete Diffusion from Snapshots

  Oussama Zekri, Th\'eo Uscidda, Nicolas Boull\'e, Anna Korba · 24 March 2026

  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 grea…

• Memory-V2V: Memory-Augmented Video-to-Video Diffusion for Consistent Multi-Turn Editing

  Dohun Lee, Chun-Hao Paul Huang, Xuelin Chen, Jong Chul Ye, Duygu Ceylan, Hyeonho Jeong · 24 March 2026

  Video-to-video diffusion models achieve impressive single-turn editing performance, but practical editing workflows are inherently iterative. When edits are applied sequentially, existing models treat each turn independently, often causing previously generated regions to drift or be overwritten. We …

• InjectFlow: Weak Guides Strong via Orthogonal Injection for Flow Matching

  Dayu Wang, Jiaye Yang, Weikang Li, Jiahui Liang, Yang Li · 24 March 2026

  Flow Matching (FM) has recently emerged as a leading approach for high-fidelity visual generation, offering a robust continuous-time alternative to ordinary differential equation (ODE) based models. However, despite their success, FM models are highly sensitive to dataset biases, which cause severe …

• FIGURA: A Modular Prompt Engineering Method for Artistic Figure Photography in Safety-Filtered Text-to-Image Models

  Luca Cazzaniga · 24 March 2026

  Safety filters in commercial text-to-image (T2I) models systematically block legitimate artistic content involving the human figure, treating classical nude photography with the same restrictiveness as explicit material. While prior research has documented this problem extensively, no operational sy…

• CRoCoDiL: Continuous and Robust Conditioned Diffusion for Language

  Roy Uziel, Omer Belhasin, Itay Levi, Akhiad Bercovich, Ran El-Yaniv, Ran Zilberstein, Michael Elad · 24 March 2026

  Masked Diffusion Models (MDMs) provide an efficient non-causal alternative to autoregressive generation but often struggle with token dependencies and semantic incoherence due to their reliance on discrete marginal distributions. We address these limitations by shifting the diffusion process into a …

• EARTalking: End-to-end GPT-style Autoregressive Talking Head Synthesis with Frame-wise Control

  Yuzhe Weng, Haotian Wang, Yuanhong Yu, Jun Du, Shan He, Xiaoyan Wu, Haoran Xu · 24 March 2026

  Audio-driven talking head generation aims to create vivid and realistic videos from a static portrait and speech. Existing AR-based methods rely on intermediate facial representations, which limit their expressiveness and realism. Meanwhile, diffusion-based methods generate clip-by-clip, lacking fin…

• A Multihead Continual Learning Framework for Fine-Grained Fashion Image Retrieval with Contrastive Learning and Exponential Moving Average Distillation

  Ling Xiao, Toshihiko Yamasaki · 24 March 2026

  Most fine-grained fashion image retrieval (FIR) methods assume a static setting, requiring full retraining when new attributes appear, which is costly and impractical for dynamic scenarios. Although pretrained models support zero-shot inference, their accuracy drops without supervision, and no prior…

• Beyond the Birkhoff Polytope: Spectral-Sphere-Constrained Hyper-Connections

  Zhaoyi Liu, Haichuan Zhang, Ang Li · 24 March 2026

  Hyper-Connections (HC) generalize residual connections into multiple streams, employing residual matrices for cross-stream feature mixing to enrich model expressivity. However, unconstrained mixing disrupts the identity mapping property intrinsic to the residual connection, causing unstable training…

• Positional Segmentor-Guided Counterfactual Fine-Tuning for Spatially Localized Image Synthesis

  Tian Xia, Matthew Sinclair, Andreas Schuh, Fabio De Sousa Ribeiro, Raghav Mehta, Rajat Rasal, Esther Puyol-Ant\'on, Samuel Gerber, Kersten Petersen, Michiel Schaap, Ben Glocker · 24 March 2026

  Counterfactual image generation enables controlled data augmentation, bias mitigation, and disease modeling. However, existing methods guided by external classifiers or regressors are limited to subject-level factors (e.g., age) and fail to produce localized structural changes, often resulting in gl…

• SpatialReward: Verifiable Spatial Reward Modeling for Fine-Grained Spatial Consistency in Text-to-Image Generation

  Sashuai Zhou, Qiang Zhou, Junpeng Ma, Yue Cao, Ruofan Hu, Ziang Zhang, Xiaoda Yang, Zhibin Wang, Jun Song, Cheng Yu, Bo Zheng, Zhou Zhao · 24 March 2026

  Recent advances in text-to-image (T2I) generation via reinforcement learning (RL) have benefited from reward models that assess semantic alignment and visual quality. However, most existing reward models pay limited attention to fine-grained spatial relationships, often producing images that appear …

• Amortized Variational Inference for Logistic Regression with Missing Covariates

  M. Cherifi, Aude Sportisse, Xujia Zhu, Mohammed Nabil El Korso, A. Mesloub · 24 March 2026

  Missing covariate data pose a significant challenge to statistical inference and machine learning, particularly for classification tasks like logistic regression. Classical iterative approaches (EM, multiple imputation) are often computationally intensive, sensitive to high missingness rates, and li…

• Noise Titration: Exact Distributional Benchmarking for Probabilistic Time Series Forecasting

  Qilin Wang · 24 March 2026

  Modern time series forecasting is evaluated almost entirely through passive observation of single historical trajectories, rendering claims about a model's robustness to non-stationarity fundamentally unfalsifiable. We propose a paradigm shift toward interventionist, exact-statistical benchmarking. …