Generative Adversarial Networks and Image Synthesis

Últimos artículos

• Bures-Wasserstein Importance-Weighted Evidence Lower Bound: Exposition and Applications

  Peiwen Jiang, Takuo Matsubara, Minh-Ngoc Tran · 5 de febrero de 2026

  The Importance-Weighted Evidence Lower Bound (IW-ELBO) has emerged as an effective objective for variational inference (VI), tightening the standard ELBO and mitigating the mode-seeking behaviour. However, optimizing the IW-ELBO in Euclidean space is often inefficient, as its gradient estimators s…

• WIND: Weather Inverse Diffusion for Zero-Shot Atmospheric Modeling

  Michael Aich, Andreas F\"urst, Florian Sestak, Carlos Ruiz-Gonzalez, Niklas Boers, Johannes Brandstetter · 5 de febrero de 2026

  Deep learning has revolutionized weather and climate modeling, yet the current landscape remains fragmented: highly specialized models are typically trained individually for distinct tasks. To unify this landscape, we introduce WIND, a single pre-trained foundation model capable of replacing special…

• MirrorLA: Reflecting Feature Map for Vision Linear Attention

  Weikang Meng, Liangyu Huo, Yadan Luo, Yaowei Wang, Yingjian Li, Zheng Zhang · 5 de febrero de 2026

  Linear attention significantly reduces the computational complexity of Transformers from quadratic to linear, yet it consistently lags behind softmax-based attention in performance. We identify the root cause of this degradation as the non-negativity constraint imposed on kernel feature maps: standa…

• Inference-Time Alignment for Diffusion Models via Variationally Stable Doob's Matching

  Jinyuan Chang, Chenguang Duan, Yuling Jiao, Yi Xu, Jerry Zhijian Yang · 5 de febrero de 2026

  Inference-time alignment for diffusion models aims to adapt a pre-trained reference diffusion model toward a target distribution without retraining the reference score network, thereby preserving the generative capacity of the reference model while enforcing desired properties at the inference time.…

• PromptSplit: Revealing Prompt-Level Disagreement in Generative Models

  Mehdi Lotfian, Mohammad Jalali, Farzan Farnia · 5 de febrero de 2026

  Prompt-guided generative AI models have rapidly expanded across vision and language domains, producing realistic and diverse outputs from textual inputs. The growing variety of such models, trained with different data and architectures, calls for principled methods to identify which types of prompts…

• SparVAR: Exploring Sparsity in Visual AutoRegressive Modeling for Training-Free Acceleration

  Zekun Li, Ning Wang, Tongxin Bai, Changwang Mei, Peisong Wang, Shuang Qiu, Jian Cheng · 5 de febrero de 2026

  Visual AutoRegressive (VAR) modeling has garnered significant attention for its innovative next-scale prediction paradigm. However, mainstream VAR paradigms attend to all tokens across historical scales at each autoregressive step. As the next scale resolution grows, the computational complexity of …

• Sparse-to-Sparse Training of Diffusion Models

  In\^es Cardoso Oliveira, Decebal Constantin Mocanu, Luis A. Leiva · 5 de febrero de 2026

  Diffusion models (DMs) are a powerful type of generative models that have achieved state-of-the-art results in various image synthesis tasks and have shown potential in other domains, such as natural language processing and temporal data modeling. Despite their stable training dynamics and ability t…

• Low-Dimensional Adaptation of Rectified Flow: A Diffusion and Stochastic Localization Perspective

  Saptarshi Roy, Alessandro Rinaldo, Purnamrita Sarkar · 5 de febrero de 2026

  In recent years, Rectified flow (RF) has gained considerable popularity largely due to its generation efficiency and state-of-the-art performance. In this paper, we investigate the degree to which RF automatically adapts to the intrinsic low dimensionality of the support of the target distribution t…

• Phaedra: Learning High-Fidelity Discrete Tokenization for the Physical Science

  Levi Lingsch, Georgios Kissas, Johannes Jakubik, Siddhartha Mishra · 5 de febrero de 2026

  Tokens are discrete representations that allow modern deep learning to scale by transforming high-dimensional data into sequences that can be efficiently learned, generated, and generalized to new tasks. These have become foundational for image and video generation and, more recently, physical simul…

• Adaptive Prompt Elicitation for Text-to-Image Generation

  Xinyi Wen, Lena Hegemann, Xiaofu Jin, Shuai Ma, Antti Oulasvirta · 5 de febrero de 2026

  Aligning text-to-image generation with user intent remains challenging, for users who provide ambiguous inputs and struggle with model idiosyncrasies. We propose Adaptive Prompt Elicitation (APE), a technique that adaptively asks visual queries to help users refine prompts without extensive writing.…

• Generative Modeling via Drifting

  Mingyang Deng, He Li, Tianhong Li, Yilun Du, Kaiming He · 5 de febrero de 2026

  Generative modeling can be formulated as learning a mapping f such that its pushforward distribution matches the data distribution. The pushforward behavior can be carried out iteratively at inference time, for example in diffusion and flow-based models. In this paper, we propose a new paradigm call…

• TruKAN: Towards More Efficient Kolmogorov-Arnold Networks Using Truncated Power Functions

  Ali Bayeh, Samira Sadaoui, Malek Mouhoub · 5 de febrero de 2026

  To address the trade-off between computational efficiency and adherence to Kolmogorov-Arnold Network (KAN) principles, we propose TruKAN, a new architecture based on the KAN structure and learnable activation functions. TruKAN replaces the B-spline basis in KAN with a family of truncated power funct…

• Imbalance-Robust and Sampling-Efficient Continuous Conditional GANs via Adaptive Vicinity and Auxiliary Regularization

  Xin Ding, Yun Chen, Yongwei Wang, Kao Zhang, Sen Zhang, Peibei Cao, Xiangxue Wang · 4 de febrero de 2026

  Recent advances in conditional generative modeling have introduced Continuous conditional Generative Adversarial Network (CcGAN) and Continuous Conditional Diffusion Model (CCDM) for estimating high-dimensional data distributions conditioned on scalar, continuous regression labels (e.g., angles, age…

• Fast Sampling for Flows and Diffusions with Lazy and Point Mass Stochastic Interpolants

  Gabriel Damsholt, Jes Frellsen, Susanne Ditlevsen · 4 de febrero de 2026

  Stochastic interpolants unify flows and diffusions, popular generative modeling frameworks. A primary hyperparameter in these methods is the interpolation schedule that determines how to bridge a standard Gaussian base measure to an arbitrary target measure. We prove how to convert a sample path of …

• Patronus: Interpretable Diffusion Models with Prototypes

  Nina Weng, Aasa Feragen, Siavash Bigdeli · 4 de febrero de 2026

  Uncovering the opacity of diffusion-based generative models is urgently needed, as their applications continue to expand while their underlying procedures largely remain a black box. With a critical question -- how can the diffusion generation process be interpreted and understood? -- we proposed Pa…

• From Vicious to Virtuous Cycles: Synergistic Representation Learning for Unsupervised Video Object-Centric Learning

  Hyun Seok Seong, WonJun Moon, Jae-Pil Heo · 4 de febrero de 2026

  Unsupervised object-centric learning models, particularly slot-based architectures, have shown great promise in decomposing complex scenes. However, their reliance on reconstruction-based training creates a fundamental conflict between the sharp, high-frequency attention maps of the encoder and the …

• Spectral Evolution Search: Efficient Inference-Time Scaling for Reward-Aligned Image Generation

  Jinyan Ye, Zhongjie Duan, Zhiwen Li, Cen Chen, Daoyuan Chen, Yaliang Li, Yingda Chen · 4 de febrero de 2026

  Inference-time scaling offers a versatile paradigm for aligning visual generative models with downstream objectives without parameter updates. However, existing approaches that optimize the high-dimensional initial noise suffer from severe inefficiency, as many search directions exert negligible inf…

• Robust Representation Learning in Masked Autoencoders

  Anika Shrivastava, Renu Rameshan, Samar Agnihotri · 4 de febrero de 2026

  Masked Autoencoders (MAEs) achieve impressive performance in image classification tasks, yet the internal representations they learn remain less understood. This work started as an attempt to understand the strong downstream classification performance of MAE. In this process we discover that represe…

• Enhancing Quantum Diffusion Models for Complex Image Generation

  Jeongbin Jo, Santanam Wishal, Shah Md Khalil Ullah, Shan Kowalski, Dikshant Dulai · 4 de febrero de 2026

  Quantum generative models offer a novel approach to exploring high-dimensional Hilbert spaces but face significant challenges in scalability and expressibility when applied to multi-modal distributions. In this study, we explore a Hybrid Quantum-Classical U-Net architecture integrated with Adaptive …

• Lookahead Sample Reward Guidance for Test-Time Scaling of Diffusion Models

  Yeongmin Kim, Donghyeok Shin, Byeonghu Na, Minsang Park, Richard Lee Kim, Il-Chul Moon · 4 de febrero de 2026

  Diffusion models have demonstrated strong generative performance; however, generated samples often fail to fully align with human intent. This paper studies a test-time scaling method that enables sampling from regions with higher human-aligned reward values. Existing gradient guidance methods appro…

• Inference-time Unlearning Using Conformal Prediction

  Somnath Basu Roy Chowdhury, Rahul Kidambi, Avinava Dubey, David Wang, Gokhan Mergen, Amr Ahmed, Aranyak Mehta · 4 de febrero de 2026

  Machine unlearning is the process of efficiently removing specific information from a trained machine learning model without retraining from scratch. Existing unlearning methods, which often provide provable guarantees, typically involve retraining a subset of model parameters based on a forget set.…

• Training-Free Self-Correction for Multimodal Masked Diffusion Models

  Yidong Ouyang, Panwen Hu, Zhengyan Wan, Zhe Wang, Liyan Xie, Dmitriy Bespalov, Ying Nian Wu, Guang Cheng, Hongyuan Zha, Qiang Sun · 4 de febrero de 2026

  Masked diffusion models have emerged as a powerful framework for text and multimodal generation. However, their sampling procedure updates multiple tokens simultaneously and treats generated tokens as immutable, which may lead to error accumulation when early mistakes cannot be revised. In this work…

• Distance Marching for Generative Modeling

  Zimo Wang, Ishit Mehta, Haolin Lu, Chung-En Sun, Ge Yan, Tsui-Wei Weng, Tzu-Mao Li · 4 de febrero de 2026

  Time-unconditional generative models learn time-independent denoising vector fields. But without time conditioning, the same noisy input may correspond to multiple noise levels and different denoising directions, which interferes with the supervision signal. Inspired by distance field modeling, we p…

• PRISM: Deriving a White-Box Transformer as a Signal-Noise Decomposition Operator via Maximum Coding Rate Reduction

  Dongchen Huang · 4 de febrero de 2026

  Deep learning models, particularly Transformers, are often criticized as "black boxes" and lack interpretability. We propose Prism, a white-box attention-based architecture derived from the principles of Maximizing Coding Rate Reduction ($\text{MCR}^2$). By modeling the attention mechanism as a grad…

• Variational Sparse Paired Autoencoders (vsPAIR) for Inverse Problems and Uncertainty Quantification

  Jack Michael Solomon, Rishi Leburu, Matthias Chung · 4 de febrero de 2026

  Inverse problems are fundamental to many scientific and engineering disciplines; they arise when one seeks to reconstruct hidden, underlying quantities from noisy measurements. Many applications demand not just point estimates but interpretable uncertainty. Providing fast inference alongside uncerta…