Generative Adversarial Networks and Image Synthesis

Neueste Paper

• Explainability in Generative Medical Diffusion Models: A Faithfulness-Based Analysis on MRI Synthesis

  Surjo Dey, Pallabi Saikia · 11. Februar 2026

  This study investigates the explainability of generative diffusion models in the context of medical imaging, focusing on Magnetic resonance imaging (MRI) synthesis. Although diffusion models have shown strong performance in generating realistic medical images, their internal decision making process …

• Mitigating the Likelihood Paradox in Flow-based OOD Detection via Entropy Manipulation

  Donghwan Kim, Hyunsoo Yoon · 11. Februar 2026

  Deep generative models that can tractably compute input likelihoods, including normalizing flows, often assign unexpectedly high likelihoods to out-of-distribution (OOD) inputs. We mitigate this likelihood paradox by manipulating input entropy based on semantic similarity, applying stronger perturba…

• Causality in Video Diffusers is Separable from Denoising

  Xingjian Bai, Guande He, Zhengqi Li, Eli Shechtman, Xun Huang, Zongze Wu · 11. Februar 2026

  Causality -- referring to temporal, uni-directional cause-effect relationships between components -- underlies many complex generative processes, including videos, language, and robot trajectories. Current causal diffusion models entangle temporal reasoning with iterative denoising, applying causal …

• Reward-Guided Discrete Diffusion via Clean-Sample Markov Chain for Molecule and Biological Sequence Design

  Prin Phunyaphibarn, Minhyuk Sung · 11. Februar 2026

  Discrete diffusion models have recently emerged as a powerful class of generative models for chemistry and biology data. In these fields, the goal is to generate various samples with high rewards (e.g., drug-likeness in molecules), making reward-based guidance crucial. Most existing methods are base…

• NarraScore: Bridging Visual Narrative and Musical Dynamics via Hierarchical Affective Control

  Yufan Wen, Zhaocheng Liu, YeGuo Hua, Ziyi Guo, Lihua Zhang, Chun Yuan, Jian Wu · 11. Februar 2026

  Synthesizing coherent soundtracks for long-form videos remains a formidable challenge, currently stalled by three critical impediments: computational scalability, temporal coherence, and, most critically, a pervasive semantic blindness to evolving narrative logic. To bridge these gaps, we propose Na…

• Quantifying Epistemic Uncertainty in Diffusion Models

  Aditi Gupta, Raphael A. Meyer, Yotam Yaniv, Elynn Chen, N. Benjamin Erichson · 11. Februar 2026

  To ensure high quality outputs, it is important to quantify the epistemic uncertainty of diffusion models.Existing methods are often unreliable because they mix epistemic and aleatoric uncertainty. We introduce a method based on Fisher information that explicitly isolates epistemic variance, produci…

• MieDB-100k: A Comprehensive Dataset for Medical Image Editing

  Yongfan Lai, Wen Qian, Bo Liu, Hongyan Li, Hao Luo, Fan Wang, Bohan Zhuang, Shenda Hong · 11. Februar 2026

  The scarcity of high-quality data remains a primary bottleneck in adapting multimodal generative models for medical image editing. Existing medical image editing datasets often suffer from limited diversity, neglect of medical image understanding and inability to balance quality with scalability. To…

• Coupled Inference in Diffusion Models for Semantic Decomposition

  Calvin Yeung, Ali Zakeri, Zhuowen Zou, Mohsen Imani · 11. Februar 2026

  Many visual scenes can be described as compositions of latent factors. Effective recognition, reasoning, and editing often require not only forming such compositional representations, but also solving the decomposition problem. One popular choice for constructing these representations is through the…

• Minimum Distance Summaries for Robust Neural Posterior Estimation

  Sherman Khoo, Dennis Prangle, Song Liu, Mark Beaumont · 11. Februar 2026

  Simulation-based inference (SBI) enables amortized Bayesian inference by first training a neural posterior estimator (NPE) on prior-simulator pairs, typically through low-dimensional summary statistics, which can then be cheaply reused for fast inference by querying it on new test observations. Beca…

• Model soups need only one ingredient

  Alireza Abdollahpoorrostam, Nikolaos Dimitriadis, Adam Hazimeh, Pascal Frossard · 11. Februar 2026

  Fine-tuning large pre-trained models on a target distribution often improves in-distribution (ID) accuracy, but at the cost of out-of-distribution (OOD) robustness as representations specialize to the fine-tuning data. Weight-space ensembling methods, such as Model Soups, mitigate this effect by ave…

• FADE: Selective Forgetting via Sparse LoRA and Self-Distillation

  Carolina R. Kelsch, Leonardo S. B. Pereira, Natnael Mola, Luis H. Arribas, Juan C. S. M. Avedillo · 10. Februar 2026

  Machine Unlearning aims to remove the influence of specific data or concepts from trained models while preserving overall performance, a capability increasingly required by data protection regulations and responsible AI practices. Despite recent progress, unlearning in text-to-image diffusion models…

• Trajectory Stitching for Solving Inverse Problems with Flow-Based Models

  Alexander Denker, Moshe Eliasof, Zeljko Kereta, Carola-Bibiane Sch\"onlieb · 10. Februar 2026

  Flow-based generative models have emerged as powerful priors for solving inverse problems. One option is to directly optimize the initial latent code (noise), such that the flow output solves the inverse problem. However, this requires backpropagating through the entire generative trajectory, incurr…

• Selective Fine-Tuning for Targeted and Robust Concept Unlearning

  Mansi, Avinash Kori, Francesca Toni, Soteris Demetriou · 10. Februar 2026

  Text guided diffusion models are used by millions of users, but can be easily exploited to produce harmful content. Concept unlearning methods aim at reducing the models' likelihood of generating harmful content. Traditionally, this has been tackled at an individual concept level, with only a handfu…

• stable-worldmodel-v1: Reproducible World Modeling Research and Evaluation

  Lucas Maes, Quentin Le Lidec, Dan Haramati, Nassim Massaudi, Damien Scieur, Yann LeCun, Randall Balestriero · 10. Februar 2026

  World Models have emerged as a powerful paradigm for learning compact, predictive representations of environment dynamics, enabling agents to reason, plan, and generalize beyond direct experience. Despite recent interest in World Models, most available implementations remain publication-specific, se…

• Condition Errors Refinement in Autoregressive Image Generation with Diffusion Loss

  Yucheng Zhou, Hao Li, Jianbing Shen · 10. Februar 2026

  Recent studies have explored autoregressive models for image generation, with promising results, and have combined diffusion models with autoregressive frameworks to optimize image generation via diffusion losses. In this study, we present a theoretical analysis of diffusion and autoregressive model…

• Optimizing Few-Step Generation with Adaptive Matching Distillation

  Lichen Bai, Zikai Zhou, Shitong Shao, Wenliang Zhong, Shuo Yang, Shuo Chen, Bojun Chen, Zeke Xie · 10. Februar 2026

  Distribution Matching Distillation (DMD) is a powerful acceleration paradigm, yet its stability is often compromised in Forbidden Zone, regions where the real teacher provides unreliable guidance while the fake teacher exerts insufficient repulsive force. In this work, we propose a unified optimizat…

• Probabilistic Forecasting via Autoregressive Flow Matching

  Ahmed ElGazzar, Marcel van Gerven · 10. Februar 2026

  In this work, we propose FlowTime, a generative model for probabilistic forecasting of multivariate timeseries data. Given historical measurements and optional future covariates, we formulate forecasting as sampling from a learned conditional distribution over future trajectories. Specifically, we d…

• TextResNet: Decoupling and Routing Optimization Signals in Compound AI Systems via Deep Residual Tuning

  Suizhi Huang, Mei Li, Han Yu, Xiaoxiao Li · 10. Februar 2026

  Textual Gradient-style optimizers (TextGrad) enable gradient-like feedback propagation through compound AI systems. However, they do not work well for deep chains. The root cause of this limitation stems from the Semantic Entanglement problem in these extended workflows. In standard textual backprop…

• PISCO: Precise Video Instance Insertion with Sparse Control

  Xiangbo Gao, Renjie Li, Xinghao Chen, Yuheng Wu, Suofei Feng, Qing Yin, Zhengzhong Tu · 10. Februar 2026

  The landscape of AI video generation is undergoing a pivotal shift: moving beyond general generation - which relies on exhaustive prompt-engineering and "cherry-picking" - towards fine-grained, controllable generation and high-fidelity post-processing. In professional AI-assisted filmmaking, it is c…

• Riemannian MeanFlow

  Dongyeop Woo, Marta Skreta, Seonghyun Park, Sungsoo Ahn, Kirill Neklyudov · 10. Februar 2026

  Diffusion and flow models have become the dominant paradigm for generative modeling on Riemannian manifolds, with successful applications in protein backbone generation and DNA sequence design. However, these methods require tens to hundreds of neural network evaluations at inference time, which can…

• Hybrid Dual-Path Linear Transformations for Efficient Transformer Architectures

  Vladimer Khasia · 10. Februar 2026

  Standard Transformer architectures rely heavily on dense linear transformations, treating feature projection as a monolithic, full-rank operation. We argue that this formulation is inefficient and lacks the structural inductive bias necessary for distinguishing between local feature preservation and…

• Harpoon: Generalised Manifold Guidance for Conditional Tabular Diffusion

  Aditya Shankar, Yuandou Wang, Rihan Hai, Lydia Y. Chen · 10. Februar 2026

  Generating tabular data under conditions is critical to applications requiring precise control over the generative process. Existing methods rely on training-time strategies that do not generalise to unseen constraints during inference, and struggle to handle conditional tasks beyond tabular imputat…

• WorldEdit: Towards Open-World Image Editing with a Knowledge-Informed Benchmark

  Wang Lin, Feng Wang, Majun Zhang, Wentao Hu, Tao Jin, Zhou Zhao, Fei Wu, Jingyuan Chen, Alan Yuille, Sucheng Ren · 10. Februar 2026

  Recent advances in image editing models have demonstrated remarkable capabilities in executing explicit instructions, such as attribute manipulation, style transfer, and pose synthesis. However, these models often face challenges when dealing with implicit editing instructions, which describe the ca…

• A-FloPS: Accelerating Diffusion Models via Adaptive Flow Path Sampler

  Cheng Jin, Zhenyu Xiao, Yuantao Gu · 10. Februar 2026

  Diffusion models deliver state-of-the-art generative performance across diverse modalities but remain computationally expensive due to their inherently iterative sampling process. Existing training-free acceleration methods typically improve numerical solvers for the reverse-time ODE, yet their effe…

• Equalized Generative Treatment: Matching f-divergences for Fairness in Generative Models

  Alexandre Verine, Rafael Pinot, Florian Le Bronnec · 10. Februar 2026

  Fairness is a crucial concern for generative models, which not only reflect but can also amplify societal and cultural biases. Existing fairness notions for generative models are largely adapted from classification and focus on balancing the probability of generating samples from each sensitive grou…