Generative Adversarial Networks and Image Synthesis

Últimos artículos

• Adaptive Clinical-Aware Latent Diffusion for Multimodal Brain Image Generation and Missing Modality Imputation

  Rong Zhou, Houliang Zhou, Yao Su, Brian Y. Chen, Yu Zhang, Lifang He, Alzheimer's Disease Neuroimaging Initiative · 11 de marzo de 2026

  Multimodal neuroimaging provides complementary insights for Alzheimer's disease diagnosis, yet clinical datasets frequently suffer from missing modalities. We propose ACADiff, a framework that synthesizes missing brain imaging modalities through adaptive clinical-aware diffusion. ACADiff learns mapp…

• Generative Drifting is Secretly Score Matching: a Spectral and Variational Perspective

  Erkan Turan, Maks Ovsjanikov · 11 de marzo de 2026

  Generative Modeling via Drifting has recently achieved state-of-the-art one-step image generation through a kernel-based drift operator, yet the success is largely empirical and its theoretical foundations remain poorly understood. In this paper, we make the following observation: \emph{under a Gaus…

• BridgeDiff: Bridging Human Observations and Flat-Garment Synthesis for Virtual Try-Off

  Shuang Liu, Ao Yu, Linkang Cheng, Xiwen Huang, Li Zhao, Junhui Liu, Zhiting Lin, Yu Liu · 11 de marzo de 2026

  Virtual try-off (VTOFF) aims to recover canonical flat-garment representations from images of dressed persons for standardized display and downstream virtual try-on. Prior methods often treat VTOFF as direct image translation driven by local masks or text-only prompts, overlooking the gap between on…

• Expressivity-Efficiency Tradeoffs for Hybrid Sequence Models

  John Cooper, Ilias Diakonikolas, Mingchen Ma, Frederic Sala · 11 de marzo de 2026

  Hybrid sequence models--combining Transformer and state-space model layers--seek to gain the expressive versatility of attention as well as the computational efficiency of state-space model layers. Despite burgeoning interest in hybrid models, we lack a basic understanding of the settings where--and…

• The Temporal Markov Transition Field

  Michael Leznik · 11 de marzo de 2026

  The Markov Transition Field (MTF), introduced by Wang and Oates (2015), encodes a time series as a two-dimensional image by mapping each pair of time steps to the transition probability between their quantile states, estimated from a single global transition matrix. This construction is efficient wh…

• B-DENSE: Branching For Dense Ensemble Network Supervision Efficiency

  Cherish Puniani, Tushar Kumar, Arnav Bendre, Gaurav Kumar, Shree Singhi · 11 de marzo de 2026

  Inspired by non-equilibrium thermodynamics, diffusion models have achieved state-of-the-art performance in generative modeling. However, their iterative sampling nature results in high inference latency. While recent distillation techniques accelerate sampling, they discard intermediate trajectory s…

• The Gaussian-Multinoulli Restricted Boltzmann Machine: A Potts Model Extension of the GRBM

  Nikhil Kapasi, Mohamed Elfouly, William Whitehead, Luke Theogarajan · 11 de marzo de 2026

  Many real-world tasks, from associative memory to symbolic reasoning, benefit from discrete, structured representations that standard continuous latent models can struggle to express. We introduce the Gaussian-Multinoulli Restricted Boltzmann Machine (GM-RBM), a generative energy-based model that ex…

• Statistical Inference via Generative Models: Flow Matching and Causal Inference

  Shinto Eguchi · 11 de marzo de 2026

  Generative AI has achieved remarkable empirical success, but from the perspective of statistics it often remains opaque: its predictions may be accurate, yet the underlying mechanism is difficult to interpret, analyze, and trust. This book reinterprets generative AI in the language of statistics, us…

• Reviving ConvNeXt for Efficient Convolutional Diffusion Models

  Taesung Kwon, Lorenzo Bianchi, Lennart Wittke, Felix Watine, Fabio Carrara, Jong Chul Ye, Romann Weber, Vinicius Azevedo · 11 de marzo de 2026

  Recent diffusion models increasingly favor Transformer backbones, motivated by the remarkable scalability of fully attentional architectures. Yet the locality bias, parameter efficiency, and hardware friendliness--the attributes that established ConvNets as the efficient vision backbone--have seen l…

• An AI-powered Bayesian Generative Modeling Approach for Arbitrary Conditional Inference

  Qiao Liu, Wing Hung Wong · 11 de marzo de 2026

  Modern data analysis increasingly requires flexible conditional inference P(X_B | X_A) where (X_A, X_B) is an arbitrary partition of observed variable X. Existing approaches are either restricted to a fixed conditioning structure or depend strongly on the distribution of conditioning masks during tr…

• A Generative Sampler for distributions with possible discrete parameter based on Reversibility

  Lei Li, Zhen Wang, Lishuo Zhang · 11 de marzo de 2026

  Learning to sample from complex unnormalized distributions is a fundamental challenge in computational physics and machine learning. While score-based and variational methods have achieved success in continuous domains, extending them to discrete or mixed-variable systems remains difficult due to il…

• Heterogeneous Decentralized Diffusion Models

  Zhiying Jiang, Raihan Seraj, Marcos Villagra, Bidhan Roy · 10 de marzo de 2026

  Training frontier-scale diffusion models often requires substantial computational resources concentrated in tightly coupled clusters, limiting participation to well-resourced institutions. While Decentralized Diffusion Models (DDM) enable training multiple experts in isolation, existing approaches r…

• Improved Constrained Generation by Bridging Pretrained Generative Models

  Xiaoxuan Liang, Saeid Naderiparizi, Yunpeng Liu, Berend Zwartsenberg, Frank Wood · 10 de marzo de 2026

  Constrained generative modeling is fundamental to applications such as robotic control and autonomous driving, where models must respect physical laws and safety-critical constraints. In real-world settings, these constraints rarely take the form of simple linear inequalities, but instead complex fe…

• Advances in GRPO for Generation Models: A Survey

  Zexiang Liu, Xianglong He, Yangguang Li · 10 de marzo de 2026

  Large-scale flow matching models have achieved strong performance across generative tasks such as text-to-image, video, 3D, and speech synthesis. However, aligning their outputs with human preferences and task-specific objectives remains challenging. Flow-GRPO extends Group Relative Policy Optimizat…

• One step further with Monte-Carlo sampler to guide diffusion better

  Minsi Ren, Wenhao Deng, Ruiqi Feng, Tailin Wu · 10 de marzo de 2026

  Stochastic differential equation (SDE)-based generative models have achieved substantial progress in conditional generation via training-free differentiable loss-guided approaches. However, existing methodologies utilizing posterior sam- pling typically confront a substantial estimation error, which…

• Foley-Flow: Coordinated Video-to-Audio Generation with Masked Audio-Visual Alignment and Dynamic Conditional Flows

  Shentong Mo, Yibing Song · 10 de marzo de 2026

  Coordinated audio generation based on video inputs typically requires a strict audio-visual (AV) alignment, where both semantics and rhythmics of the generated audio segments shall correspond to those in the video frames. Previous studies leverage a two-stage design where the AV encoders are firstly…

• DreamSAC: Learning Hamiltonian World Models via Symmetry Exploration

  Jinzhou Tang, Fan Feng, Minghao Fu, Wenjun Lin, Biwei Huang, Keze Wang · 10 de marzo de 2026

  Learned world models excel at interpolative generalization but fail at extrapolative generalization to novel physical properties. This limitation arises because they learn statistical correlations rather than the environment's underlying generative rules, such as physical invariances and conservatio…

• Grow, Don't Overwrite: Fine-tuning Without Forgetting

  Dyah Adila, Hanna Mazzawi, Benoit Dherin, Xavier Gonzalvo · 10 de marzo de 2026

  Adapting pre-trained models to specialized tasks often leads to catastrophic forgetting, where new knowledge overwrites foundational capabilities. Existing methods either compromise performance on the new task or struggle to balance training stability with efficient reuse of pre-trained knowledge. W…

• Compression as Adaptation: Implicit Visual Representation with Diffusion Foundation Models

  Jiajun He, Zongyu Guo, Zhaoyang Jia, Xiaoyi Zhang, Jiahao Li, Xiao Li, Bin Li, Jos\'e Miguel Hern\'andez-Lobato, Yan Lu · 10 de marzo de 2026

  Modern visual generative models acquire rich visual knowledge through large-scale training, yet existing visual representations (such as pixels, latents, or tokens) remain external to the model and cannot directly exploit this knowledge for compact storage or reuse. In this work, we introduce a new …

• Wasserstein Gradient Flows for Scalable and Regularized Barycenter Computation

  Eduardo Fernandes Montesuma, Yassir Bendou, Mike Gartrell · 10 de marzo de 2026

  Wasserstein barycenters provide a principled approach for aggregating probability measures, while preserving the geometry of their ambient space. Existing discrete methods are not scalable as they assume access to the complete set of samples from the input measures. Meanwhile, neural network approac…

• X-AVDT: Audio-Visual Cross-Attention for Robust Deepfake Detection

  Youngseo Kim, Kwan Yun, Seokhyeon Hong, Sihun Cha, Colette Suhjung Koo, Junyong Noh · 10 de marzo de 2026

  The surge of highly realistic synthetic videos produced by contemporary generative systems has significantly increased the risk of malicious use, challenging both humans and existing detectors. Against this backdrop, we take a generator-side view and observe that internal cross-attention mechanisms …

• Toward Unified Multimodal Representation Learning for Autonomous Driving

  Ximeng Tao, Dimitar Filev, Gaurav Pandey · 10 de marzo de 2026

  Contrastive Language-Image Pre-training (CLIP) has shown impressive performance in aligning visual and textual representations. Recent studies have extended this paradigm to 3D vision to improve scene understanding for autonomous driving. A common strategy is to employ pairwise cosine similarity bet…

• Momentum SVGD-EM for Accelerated Maximum Marginal Likelihood Estimation

  Adam Rozzio, Rafael Athanasiades, O. Deniz Akyildiz · 10 de marzo de 2026

  Maximum marginal likelihood estimation (MMLE) can be formulated as the optimization of a free energy functional. From this viewpoint, the Expectation-Maximisation (EM) algorithm admits a natural interpretation as a coordinate descent method over the joint space of model parameters and probability me…

• Evo: Autoregressive-Diffusion Large Language Models with Evolving Balance

  Junde Wu, Minhao Hu, Jiayuan Zhu, Yuyuan Liu, Tianyi Zhang, Kang Li, Jingkun Chen, Jiazhen Pan, Min Xu, Yueming Jin · 10 de marzo de 2026

  We introduce \textbf{Evo}, a duality latent trajectory model that bridges autoregressive (AR) and diffusion-based language generation within a continuous evolutionary generative framework. Rather than treating AR decoding and diffusion generation as separate paradigms, Evo reconceptualizes text gene…

• Conditional Unbalanced Optimal Transport Maps: An Outlier-Robust Framework for Conditional Generative Modeling

  Jiwoo Yoon, Kyumin Choi, Jaewoong Choi · 10 de marzo de 2026

  Conditional Optimal Transport (COT) problem aims to find a transport map between conditional source and target distributions while minimizing the transport cost. Recently, these transport maps have been utilized in conditional generative modeling tasks to establish efficient mappings between the dis…