Generative Adversarial Networks and Image Synthesis

Latest papers

• OmniPrism: Learning Disentangled Visual Concept for Image Generation

  Yangyang Li, Daqing Liu, Wu Liu, Allen He, Xinchen Liu, Yongdong Zhang, Guoqing Jin · 13 April 2026

  Creative visual concept generation often draws inspiration from specific concepts in a reference image to produce relevant outcomes. However, existing methods are typically constrained to single-aspect concept generation or are easily disrupted by irrelevant concepts in multi-aspect concept scenario…

• A Predictive View on Streaming Hidden Markov Models

  Gerardo Duran-Martin · 13 April 2026

  We develop a predictive-first optimisation framework for streaming hidden Markov models. Unlike classical approaches that prioritise full posterior recovery under a fully specified generative model, we assume access to regime-specific predictive models whose parameters are learned online while maint…

• Squeeze Evolve: Unified Multi-Model Orchestration for Verifier-Free Evolution

  Monishwaran Maheswaran, Leon Lakhani, Zhongzhu Zhou, Shijia Yang, Junxiong Wang, Coleman Hooper, Yuezhou Hu, Rishabh Tiwari, Jue Wang, Harman Singh, Qingyang Wu, Yuqing Jian, Ce Zhang, Kurt Keutzer, Tri Dao, Xiaoxia Wu, Ben Athiwaratkun, James Zou, Chenfeng Xu · 13 April 2026

  We show that verifier-free evolution is bottlenecked by both diversity and efficiency: without external correction, repeated evolution accelerates collapse toward narrow modes, while the uniform use of a high-cost model wastes compute and quickly becomes economically impractical. We introduce Squeez…

• MixFlow: Mixed Source Distributions Improve Rectified Flows

  Nazir Nayal, Christopher Wewer, Jan Eric Lenssen · 13 April 2026

  Diffusion models and their variations, such as rectified flows, generate diverse and high-quality images, but they are still hindered by slow iterative sampling caused by the highly curved generative paths they learn. An important cause of high curvature, as shown by previous work, is independence b…

• Evolutionary Optimization Trumps Adam Optimization on Embedding Space Exploration

  Dom\'icio Pereira Neto, Jo\~ao Correia, Penousal Machado · 13 April 2026

  Deep diffusion models have revolutionized image generation by producing high-quality outputs. However, achieving specific objectives with these models often requires costly adaptations such as fine-tuning, which can be resource-intensive and time-consuming. An alternative approach is inference-time …

• Envisioning the Future, One Step at a Time

  Stefan Andreas Baumann, Jannik Wiese, Tommaso Martorella, Mahdi M. Kalayeh, Bj\"orn Ommer · 13 April 2026

  Accurately anticipating how complex, diverse scenes will evolve requires models that represent uncertainty, simulate along extended interaction chains, and efficiently explore many plausible futures. Yet most existing approaches rely on dense video or latent-space prediction, expending substantial c…

• Discrete Meanflow Training Curriculum

  Chia-Hong Hsu, Frank Wood · 13 April 2026

  Flow-based image generative models exhibit stable training and produce high quality samples when using multi-step sampling procedures. One-step generative models can produce high quality image samples but can be difficult to optimize as they often exhibit unstable training dynamics. Meanflow models …

• Generative Phomosaic with Structure-Aligned and Personalized Diffusion

  Jaeyoung Chung, Hyunjin Son, Kyoung Mu Lee · 10 April 2026

  We present the first generative approach to photomosaic creation. Traditional photomosaic methods rely on a large number of tile images and color-based matching, which limits both diversity and structural consistency. Our generative photomosaic framework synthesizes tile images using diffusion-based…

• FVD: Inference-Time Alignment of Diffusion Models via Fleming-Viot Resampling

  Shivanshu Shekhar, Sagnik Mukherjee, Jia Yi Zhang, Tong Zhang · 10 April 2026

  We introduce Fleming-Viot Diffusion (FVD), an inference-time alignment method that resolves the diversity collapse commonly observed in Sequential Monte Carlo (SMC) based diffusion samplers. Existing SMC-based diffusion samplers often rely on multinomial resampling or closely related resampling sche…

• FP4 Explore, BF16 Train: Diffusion Reinforcement Learning via Efficient Rollout Scaling

  Yitong Li, Junsong Chen, Shuchen Xue, Pengcuo Zeren, Siyuan Fu, Dinghao Yang, Yangyang Tang, Junjie Bai, Ping Luo, Song Han, Enze Xie · 9 April 2026

  Reinforcement-Learning-based post-training has recently emerged as a promising paradigm for aligning text-to-image diffusion models with human preferences. In recent studies, increasing the rollout group size yields pronounced performance improvements, indicating substantial room for further alignme…

• Incentive-Aware Multi-Fidelity Optimization for Generative Advertising in Large Language Models

  Jiayuan Liu, Barry Wang, Jiarui Gan, Tonghan Wang, Leon Xie, Mingyu Guo, Vincent Conitzer · 9 April 2026

  Generative advertising in large language model (LLM) responses requires optimizing sponsorship configurations under two strict constraints: the strategic behavior of advertisers and the high cost of stochastic generations. To address this, we propose the Incentive-Aware Multi-Fidelity Mechanism (IAM…

• Instance-Adaptive Parametrization for Amortized Variational Inference

  Andrea Pollastro, Andrea Apicella, Francesco Isgr\`o, Roberto Prevete · 9 April 2026

  Latent variable models, including variational autoencoders (VAE), remain a central tool in modern deep generative modeling due to their scalability and a well-founded probabilistic formulation. These models rely on amortized variational inference to enable efficient posterior approximation, but this…

• Dynamic Context Evolution for Scalable Synthetic Data Generation

  Ryan Lingo, Rajeev Chhajer · 9 April 2026

  Large language models produce repetitive output when prompted independently across many batches, a phenomenon we term cross-batch mode collapse: the progressive loss of output diversity when a language model is prompted repeatedly without access to its prior generations. Practitioners have long miti…

• ODE-free Neural Flow Matching for One-Step Generative Modeling

  Xiao Shou · 9 April 2026

  Diffusion and flow matching models generate samples by learning time-dependent vector fields whose integration transports noise to data, requiring tens to hundreds of network evaluations at inference. We instead learn the transport map directly. We propose Optimal Transport Neural Flow Matching (OT-…

• The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment

  Rishab Balasubramanian, Pin-Jie Lin, Rituraj Sharma, Anjie Fang, Fardin Abdi, Viktor Rozgic, Zheng Du, Mohit Bansal, Tu Vu · 9 April 2026

  We investigate whether post-trained capabilities can be transferred across models without retraining, with a focus on transfer across different model scales. We propose the Master Key Hypothesis, which states that model capabilities correspond to directions in a low-dimensional latent subspace that …

• Energy-Regularized Spatial Masking: A Novel Approach to Enhancing Robustness and Interpretability in Vision Models

  Tom Devynck Bilal Faye Djamel Bouchaffra Nadjib Lazaar Hanane Azzag Mustapha Lebbah · 9 April 2026

  Deep convolutional neural networks achieve remarkable performance by exhaustively processing dense spatial feature maps, yet this brute-force strategy introduces significant computational redundancy and encourages reliance on spurious background correlations. As a result, modern vision models remain…

• Physics-Informed Spectral Modeling for Hyperspectral Imaging

  Zuzanna Gawrysiak, Krzysztof Krawiec · 9 April 2026

  We present PhISM, a physics-informed deep learning architecture that learns without supervision to explicitly disentangle hyperspectral observations and model them with continuous basis functions. PhISM outperforms prior methods on several classification and regression benchmarks, requires limited l…

• Graph-PiT: Enhancing Structural Coherence in Part-Based Image Synthesis via Graph Priors

  Junbin Zhang, Meng Cao, Feng Tan, Yikai Lin, Yuexian Zou · 8 April 2026

  Achieving fine-grained and structurally sound controllability is a cornerstone of advanced visual generation. Existing part-based frameworks treat user-provided parts as an unordered set and therefore ignore their intrinsic spatial and semantic relationships, which often results in compositions that…

• Inference-Time Scaling of Diffusion Language Models via Trajectory Refinement

  Meihua Dang, Jiaqi Han, Minkai Xu, Kai Xu, Akash Srivastava, Stefano Ermon · 8 April 2026

  Discrete diffusion models have recently emerged as strong alternatives to autoregressive language models, matching their performance through large-scale training. However, inference-time control remains relatively underexplored. In this work, we study how to steer generation toward desired rewards w…

• Modality-Aware and Anatomical Vector-Quantized Autoencoding for Multimodal Brain MRI

  Mingjie Li, Edward Kim, Yue Zhao, Ehsan Adeli, Kilian M. Pohl · 8 April 2026

  Learning a robust Variational Autoencoder (VAE) is a fundamental step for many deep learning applications in medical image analysis, such as MRI synthesizes. Existing brain VAEs predominantly focus on single-modality data (i.e., T1-weighted MRI), overlooking the complementary diagnostic value of oth…

• OrthoFuse: Training-free Riemannian Fusion of Orthogonal Style-Concept Adapters for Diffusion Models

  Ali Aliev, Kamil Garifullin, Nikolay Yudin, Vera Soboleva, Alexander Molozhavenko, Ivan Oseledets, Aibek Alanov, Maxim Rakhuba · 8 April 2026

  In a rapidly growing field of model training there is a constant practical interest in parameter-efficient fine-tuning and various techniques that use a small amount of training data to adapt the model to a narrow task. However, there is an open question: how to combine several adapters tuned for di…

• Neural Network Pruning via QUBO Optimization

  Osama Orabi, Artur Zagitov, Hadi Salloum, Viktor A. Lobachev, Kasymkhan Khubiev, Yaroslav Kholodov · 8 April 2026

  Neural network pruning can be formulated as a combinatorial optimization problem, yet most existing approaches rely on greedy heuristics that ignore complex interactions between filters. Formal optimization methods such as Quadratic Unconstrained Binary Optimization (QUBO) provide a principled alter…

• A Theoretical Framework for Statistical Evaluability of Generative Models

  Shashaank Aiyer, Yishay Mansour, Shay Moran, Han Shao · 8 April 2026

  Statistical evaluation aims to estimate the generalization performance of a model using held-out i.i.d.\ test data sampled from the ground-truth distribution. In supervised learning settings such as classification, performance metrics such as error rate are well-defined, and test error reliably appr…

• SCMAPR: Self-Correcting Multi-Agent Prompt Refinement for Complex-Scenario Text-to-Video Generation

  Chengyi Yang, Pengzhen Li, Jiayin Qi, Aimin Zhou, Ji Wu, Ji Liu · 8 April 2026

  Text-to-Video (T2V) generation has benefited from recent advances in diffusion models, yet current systems still struggle under complex scenarios, which are generally exacerbated by the ambiguity and underspecification of text prompts. In this work, we formulate complex-scenario prompt refinement as…

• PromptEvolver: Prompt Inversion through Evolutionary Optimization in Natural-Language Space

  Asaf Buchnick, Aviv Shamsian, Aviv Navon, Ethan Fetaya · 8 April 2026

  Text-to-image generation has progressed rapidly, but faithfully generating complex scenes requires extensive trial-and-error to find the exact prompt. In the prompt inversion task, the goal is to recover a textual prompt that can faithfully reconstruct a given target image. Currently, existing metho…