Generative Adversarial Networks and Image Synthesis

Neueste Paper

• Toward Early Quality Assessment of Text-to-Image Diffusion Models

  Huanlei Guo, Hongxin Wei, Bingyi Jing · 4. März 2026

  Recent text-to-image (T2I) diffusion and flow-matching models can produce highly realistic images from natural language prompts. In practical scenarios, T2I systems are often run in a ``generate--then--select'' mode: many seeds are sampled and only a few images are kept for use. However, this pipeli…

• Joint Training Across Multiple Activation Sparsity Regimes

  Haotian Wang · 4. März 2026

  Generalization in deep neural networks remains only partially understood. Inspired by the stronger generalization tendency of biological systems, we explore the hypothesis that robust internal representations should remain effective across both dense and sparse activation regimes. To test this idea,…

• RNE: plug-and-play diffusion inference-time control and energy-based training

  Jiajun He, Jos\'e Miguel Hern\'andez-Lobato, Yuanqi Du, Francisco Vargas · 4. März 2026

  Diffusion models generate data by removing noise gradually, which corresponds to the time-reversal of a noising process. However, access to only the denoising kernels is often insufficient. In many applications, we need the knowledge of the marginal densities along the generation trajectory, which e…

• BrandFusion: A Multi-Agent Framework for Seamless Brand Integration in Text-to-Video Generation

  Zihao Zhu, Ruotong Wang, Siwei Lyu, Min Zhang, Baoyuan Wu · 4. März 2026

  The rapid advancement of text-to-video (T2V) models has revolutionized content creation, yet their commercial potential remains largely untapped. We introduce, for the first time, the task of seamless brand integration in T2V: automatically embedding advertiser brands into prompt-generated videos wh…

• Improving Classifier-Free Guidance in Masked Diffusion: Low-Dim Theoretical Insights with High-Dim Impact

  Kevin Rojas, Ye He, Chieh-Hsin Lai, Yuhta Takida, Yuki Mitsufuji, Molei Tao · 4. März 2026

  Classifier-Free Guidance (CFG) is a widely used technique for conditional generation and improving sample quality in continuous diffusion models, and its extensions to discrete diffusion has recently started to be investigated. In order to improve the algorithms in a principled way, this paper start…

• Unsupervised Representation Learning -- an Invariant Risk Minimization Perspective

  Yotam Norman, Ron Meir · 4. März 2026

  We propose a novel unsupervised framework for \emph{Invariant Risk Minimization} (IRM), extending the concept of invariance to settings where labels are unavailable. Traditional IRM methods rely on labeled data to learn representations that are robust to distributional shifts across environments. In…

• Gauge Flow Models

  Alexander Strunk, Roland Assam · 4. März 2026

  This paper introduces Gauge Flow Models, a novel class of Generative Flow Models. These models incorporate a learnable Gauge Field within the Flow Ordinary Differential Equation (ODE). A comprehensive mathematical framework for these models, detailing their construction and properties, is provided. …

• Value Gradient Guidance for Flow Matching Alignment

  Zhen Liu, Tim Z. Xiao, Carles Domingo-Enrich, Weiyang Liu, Dinghuai Zhang · 4. März 2026

  While methods exist for aligning flow matching models--a popular and effective class of generative models--with human preferences, existing approaches fail to achieve both adaptation efficiency and probabilistically sound prior preservation. In this work, we leverage the theory of optimal control an…

• ShareVerse: Multi-Agent Consistent Video Generation for Shared World Modeling

  Jiayi Zhu, Jianing Zhang, Yiying Yang, Wei Cheng, Xiaoyun Yuan · 4. März 2026

  This paper presents ShareVerse, a video generation framework enabling multi-agent shared world modeling, addressing the gap in existing works that lack support for unified shared world construction with multi-agent interaction. ShareVerse leverages the generation capability of large video models and…

• Preconditioned Score and Flow Matching

  Shadab Ahamed, Eshed Gal, Simon Ghyselincks, Md Shahriar Rahim Siddiqui, Moshe Eliasof, Eldad Haber · 4. März 2026

  Flow matching and score-based diffusion train vector fields under intermediate distributions $p_t$, whose geometry can strongly affect their optimization. We show that the covariance $\Sigma_t$ of $p_t$ governs optimization bias: when $\Sigma_t$ is ill-conditioned, and gradient-based training rapidl…

• Frame Guidance: Training-Free Guidance for Frame-Level Control in Video Diffusion Models

  Sangwon Jang, Taekyung Ki, Jaehyeong Jo, Jaehong Yoon, Soo Ye Kim, Zhe Lin, Sung Ju Hwang · 4. März 2026

  Advancements in diffusion models have significantly improved video quality, directing attention to fine-grained controllability. However, many existing methods depend on fine-tuning large-scale video models for specific tasks, which becomes increasingly impractical as model sizes continue to grow. I…

• DREAM: Where Visual Understanding Meets Text-to-Image Generation

  Chao Li, Tianhong Li, Sai Vidyaranya Nuthalapati, Hong-You Chen, Satya Narayan Shukla, Yonghuan Yang, Jun Xiao, Xiangjun Fan, Aashu Singh, Dina Katabi, Shlok Kumar Mishra · 4. März 2026

  Unifying visual representation learning and text-to-image (T2I) generation within a single model remains a central challenge in multimodal learning. We introduce DREAM, a unified framework that jointly optimizes discriminative and generative objectives, while learning strong visual representations. …

• Model Already Knows the Best Noise: Bayesian Active Noise Selection via Attention in Video Diffusion Model

  Kwanyoung Kim, Sanghyun Kim · 3. März 2026

  The choice of initial noise strongly affects quality and prompt alignment in video diffusion; different seeds for the same prompt can yield drastically different results. While recent methods use externally designed priors (e.g., frequency filtering or inter-frame smoothing), they often overlook int…

• RAISE: Requirement-Adaptive Evolutionary Refinement for Training-Free Text-to-Image Alignment

  Liyao Jiang, Ruichen Chen, Chao Gao, Di Niu · 3. März 2026

  Recent text-to-image (T2I) diffusion models achieve remarkable realism, yet faithful prompt-image alignment remains challenging, particularly for complex prompts with multiple objects, relations, and fine-grained attributes. Existing training-free inference-time scaling methods rely on fixed iterati…

• SkeleGuide: Explicit Skeleton Reasoning for Context-Aware Human-in-Place Image Synthesis

  Chuqiao Wu, Jin Song, Yiyun Fei · 3. März 2026

  Generating realistic and structurally plausible human images into existing scenes remains a significant challenge for current generative models, which often produce artifacts like distorted limbs and unnatural poses. We attribute this systemic failure to an inability to perform explicit reasoning ov…

• CoVAE: correlated multimodal generative modeling

  Federico Caretti, Guido Sanguinetti · 3. März 2026

  Multimodal Variational Autoencoders have emerged as a popular tool to extract effective representations from rich multimodal data. However, such models rely on fusion strategies in latent space that destroy the joint statistical structure of the multimodal data, with profound implications for genera…

• Optimisation of SOUP-GAN and CSR-GAN for High Resolution MR Images Reconstruction

  Muneeba Rashid, Hina Shakir, Humaira Mehwish, Asarim Amir, Reema Qaiser Khan · 3. März 2026

  Magnetic Resonance (MR) imaging is a diagnostic tool used in modern medicine; however, its output can be affected by motion artefacts and may be limited by equipment. This research focuses on MRI image quality enhancement using two efficient Generative Adversarial Networks (GANs) models: SOUP-GAN an…

• Learning Boltzmann Generators via Constrained Mass Transport

  Christopher von Klitzing, Denis Blessing, Henrik Schopmans, Pascal Friederich, Gerhard Neumann · 3. März 2026

  Efficient sampling from high-dimensional and multimodal unnormalized probability distributions is a central challenge in many areas of science and machine learning. We focus on Boltzmann generators (BGs) that aim to sample the Boltzmann distribution of physical systems, such as molecules, at a given…

• Compensation-free Machine Unlearning in Text-to-Image Diffusion Models by Eliminating the Mutual Information

  Xinwen Cheng, Jingyuan Zhang, Zhehao Huang, Yingwen Wu, Xiaolin Huang · 3. März 2026

  The powerful generative capabilities of diffusion models have raised growing privacy and safety concerns regarding generating sensitive or undesired content. In response, machine unlearning (MU) -- commonly referred to as concept erasure (CE) in diffusion models -- has been introduced to remove spec…

• Does Generation Require Memorization? Creative Diffusion Models using Ambient Diffusion

  Kulin Shah, Alkis Kalavasis, Adam R. Klivans, Giannis Daras · 3. März 2026

  There is strong empirical evidence that the state-of-the-art diffusion modeling paradigm leads to models that memorize the training set, especially when the training set is small. Prior methods to mitigate the memorization problem often lead to a decrease in image quality. Is it possible to obtain s…

• LLaDA-o: An Effective and Length-Adaptive Omni Diffusion Model

  Zebin You, Xiaolu Zhang, Jun Zhou, Chongxuan Li, Ji-Rong Wen · 3. März 2026

  We present \textbf{LLaDA-o}, an effective and length-adaptive omni diffusion model for multimodal understanding and generation. LLaDA-o is built on a Mixture of Diffusion (MoD) framework that decouples discrete masked diffusion for text understanding and continuous diffusion for visual generation, w…

• Evaluating GFlowNet from partial episodes for stable and flexible policy-based training

  Puhua Niu, Shili Wu, Xiaoning Qian · 3. März 2026

  Generative Flow Networks (GFlowNets) were developed to learn policies for efficiently sampling combinatorial candidates by interpreting their generative processes as trajectories in directed acyclic graphs. In the value-based training workflow, the objective is to enforce the balance over partial ep…

• Concept-TRAK: Understanding how diffusion models learn concepts through concept-level attribution

  Yonghyun Park, Chieh-Hsin Lai, Satoshi Hayakawa, Yuhta Takida, Naoki Murata, Wei-Hsiang Liao, Woosung Choi, Kin Wai Cheuk, Junghyun Koo, Yuki Mitsufuji · 3. März 2026

  While diffusion models excel at image generation, their growing adoption raises critical concerns about copyright issues and model transparency. Existing attribution methods identify training examples influencing an entire image, but fall short in isolating contributions to specific elements, such a…

• Effective and Efficient Masked Image Generation Models

  Zebin You, Jingyang Ou, Xiaolu Zhang, Jun Hu, Jun Zhou, Chongxuan Li · 3. März 2026

  Although masked image generation models and masked diffusion models are designed with different motivations and objectives, we observe that they can be unified within a single framework. Building upon this insight, we carefully explore the design space of training and sampling, identifying key facto…

• Probabilistic Learning and Generation in Deep Sequence Models

  Wenlong Chen · 3. März 2026

  Despite exceptional predictive performance of Deep sequence models (DSMs), the main concern of their deployment centers around the lack of uncertainty awareness. In contrast, probabilistic models quantify the uncertainty associated with unobserved variables with rules of probability. Notably, Bayesi…