Generative Adversarial Networks and Image Synthesis

Últimos artículos

• Everything at Every Scale: Scale-Invariant Diffusion with Continuous Super-Resolution

  Zixin Jessie Chen, Zhuo Chen, Archer Wang, Jeff Gore, William T. Freeman, Congyue Deng, Marin Solja\v{c}i\'c · 26 de mayo de 2026

  Creating images from noise is image generation; reconstructing fine details from coarse inputs is super-resolution. Despite their practical differences, both can be understood as reversing information loss across scales. We introduce $\textbf{SKILD}$, a $\textbf{S}$cale-invariant $\textbf{K}$-Space …

• Label-NTK Alignments and A Tighter Convergence Bound in the NTK Regime

  Ruchirinkil Marreddy, Chaoyue Liu · 26 de mayo de 2026

  The Neural Tangent Kernel (NTK) framework explains optimization in over-parameterized neural networks via approximately linearized dynamics, yielding exponential convergence guarantees. However, existing results are often overly pessimistic and do not match the fast training in practice, as they dep…

• Test-Time Self-Adaptive Conditioning for Stable Audio-Driven Talking-Head Generation

  Zhicheng Zhang, Lei Wang, Yu Zhang, Yongsheng Gao · 26 de mayo de 2026

  Audio-driven talking-head generation has achieved remarkable progress with recent models such as AniTalker, FLOAT, and Sonic. Despite their success, most existing approaches rely on a single static reference image to condition the entire video generation process at inference stage. This static condi…

• Small Models, Strong Priors: Architectural Inductive Bias for Parameter-Efficient Neural PDE Solvers

  Shyam Sankaran, Hanwen Wang, Paris Perdikaris · 26 de mayo de 2026

  Neural PDE solvers have followed the scaling trajectory of vision and language, with recent foundation models reaching billions of parameters. We argue that scale is a poor substitute for architectural inductive bias in this domain: structured priors deliver outsized parameter efficiency, and the pa…

• Squeezing Capacity from Multimodal Large Language Models for Subject-driven Generation

  Shuhong Zheng, Aashish Kumar Misraa, Yu-Teng Li, Yu-Jhe Li, Igor Gilitschenski · 26 de mayo de 2026

  Subject-driven image generation aims to synthesize new images that preserve the identity of the given subject while following textual instructions. Existing approaches often encode text and reference images separately. This limits cross-modal reasoning abilities and causes copy-paste artifacts. Rece…

• TUBE: Tangent Upper Bound on Evidence for Discrete Diffusion Language Models

  Arseny Ivanov, Sergei Kholkin, Vladislav Gromadskii, Grigoriy Ksenofontov, Ivan Oseledets, Alexander Korotin · 26 de mayo de 2026

  Log-likelihood is a standard metric for evaluating generative models. Unfortunately, in contrast to autoregressive models (ARMs), discrete diffusion models generally do not admit exact computation of this quantity. Existing evaluations, therefore, rely on the evidence lower bound (ELBO), leaving unc…

• Anatomy-Anchored Self-Supervision: Distilling Vision Foundation Models for Invariant Ultrasound Representation

  Chunzheng Zhu, Yijun Wang, Jianxin Lin, Feng Wang, Hongwei Wang, Lei Zhao, Shengli Li, Kenli Li · 26 de mayo de 2026

  Self-supervised pre-training paradigm has gained increasing prominence for learning transferable representations in medical imaging, yet existing methods for ultrasound (US) images operate at the image or frame level, overlooking the anatomical context for clinical-aligned representation learning. I…

• ArtSplat: Feed-Forward Articulated 3D Gaussian Splatting from Sparse Multi-State Uncalibrated Views

  Inseo Lee, Yoonji Kim, Eugene Sohn, Jiwoong Lee, Jungmin You, Joonseok Lee, Jin-Hwa Kim · 26 de mayo de 2026

  Articulated object reconstruction from sparse-view images is an ill-posed problem that requires simultaneous inference of geometry and underlying articulation structure. Existing methods for articulated object reconstruction based on NeRF and 3D Gaussian Splatting (3DGS) typically rely on dense view…

• Concept Unlearning via Cross-Attention Activation Projection for Diffusion Models

  Saemi Moon, Suhyeon Jun, Seoyeon Lee, Dongwoo Kim · 26 de mayo de 2026

  Concept unlearning aims to erase a target concept from a pretrained text-to-image diffusion model without retraining. Closed-form methods are attractive in this setting because they apply a single deterministic edit to the cross-attention weights and add no inference-time cost. Existing closed-form …

• From Latent Space to Training Data: Explainable Specialization in Minimal MLPs

  Enrique Alba, Ezequiel Lopez-Rubio · 26 de mayo de 2026

  We here study whether training biases can make hidden neurons specialize in minimal one-hidden-layer MLPs, and whether such specialization improves prototype-based reconstruction of the training dataset from the learned weights. We consider Gaussianactivation MLPs of width equal to dataset size and …

• Channel-wise Vector Quantization

  Wei Song, Tianhang Wang, Yitong Chen, Tong Zhang, Zuxuan Wu, Ming Li, Jiaqi Wang, Kaicheng Yu · 26 de mayo de 2026

  We present Channel-wise Vector Quantization (CVQ), a novel image tokenization paradigm that replaces patch-wise tokens with channel-wise tokens. Unlike conventional vector quantization, which assigns a discrete token to each patch feature vector, CVQ quantizes each channel of the feature map. This f…

• Diff-Instruct with Diffused Reward: Towards Principled One-step Generator RL

  Junyi Wu, Weijian Luo, Haoyang Zheng, Runzhe Zhang, Guang Lin Haoyang Zheng Runzhe Zhang Guang Lin · 26 de mayo de 2026

  Recent advances in one-step text-to-image generation have enabled real-time synthesis with remarkable efficiency and quality. Previous reinforcement learning methods for one-step generators combine image-space reward optimization with diffusion noisy-space distribution matching. This paradigm brings…

• CollectionLoRA: Collecting 50 Effects in 1 LoRA via Multi-Teacher On-Policy Distillation

  Fangtai Wu, Hailong Guo, Shijie Huang, Jiayi Song, Yubo Huang, Mushui Liu, Zhao Wang, Yunlong Yu, Jiaming Liu, Ruihua Huang · 26 de mayo de 2026

  Customized image editing aims to equip pre-trained diffusion models with specific visual effects using limited paired data, typically via Low-Rank Adaptation (LoRA). As the number of desired effects grows, storing and dynamically loading numerous these effect LoRAs significantly increases deployment…

• Characterizing the Representational Capacity of Neural Processes

  Robin Young · 26 de mayo de 2026

  What functions can Neural Processes represent? We analyze the representational capacity of popular NP architectures: Conditional Neural Processes (CNPs), Attentive Neural Processes (ANPs), Transformer Neural Processes (TNPs), and their latent variants. We prove these architectures form a strict hier…

• {\Phi}-Noise: Training-Free Temporal Video Conditioning via Phase-Based Noise Manipulation

  Ofir Abramovich, Nadav Z. Cohen, Adi Rosenthal, Ariel Shamir · 26 de mayo de 2026

  Latent video diffusion models generate videos by progressively transforming Gaussian noise into realistic samples conditioned on text or visual inputs. However, existing conditioning methods often require additional training and computational overhead. Motivated by recent findings on the importance …

• K-U-KAN: Koopman-Enhanced U-KAN for 3D Dental Reconstruction from a Single Panoramic X-ray Radiograph

  Bikram Keshari Parida, Abhijit Sen, Wonsang You · 26 de mayo de 2026

  A panoramic X-ray compresses a 3D jaw into a 2D strip; we aim to recover the missing depth cleanly and fast. Existing implicit neural representations render realistic volumes but are slow to train, sensitive to sampling and positional encodings, and costly in practice. Pure CNN baselines are efficie…

• SURGE: Approximation and Training Free Particle Filter for Diffusion Surrogate

  Lifu Wei, Yinuo Ren, Naichen Shi, Yiping Lu · 26 de mayo de 2026

  Data assimilation (DA) addresses the problem of sequentially estimating the state of a dynamical system from noisy and incomplete observations. In this work, we employ a diffusion model as a world model to simulate and predict the system's dynamics. Recently, score-based diffusion models have learne…

• Guess the Unified Model: How Much Can We Recover from Generated Images?

  Jasin Cekinmez, Ryo Mitsuhashi, Addison J. Wu, Yida Yin · 26 de mayo de 2026

  With unified model-generated images now widespread online, attributing their model of origin offers a path toward transparency and deeper insight into the characteristic behaviors of individual models. Prior work has explored provenance in LLM-generated text, diffusion model images, and datasets, bu…

• Courant: a State-Adaptive Perceiver-Based Neural Surrogate with Local Support and Interpretable Field Decomposition

  Anuj Kumar, Josiah Bjorgaard, Nikolaos Bouklas, Matteo Salvador, Alexander Lavin · 26 de mayo de 2026

  We introduce "Courant", a Perceiver-based encoder-processor-decoder surrogate model that has latent features exhibiting adaptive specialization and local support in the physical space, enabling functionality akin to an adaptive hp-refinement scheme, an attribute that is highly desirable in tradition…

• Mosaic: Compositional Multi-Concept Erasure via Vector Field Blending

  Junseok Ko, Jungwoo Kim, Jong-Seok Lee · 26 de mayo de 2026

  Concept erasure has emerged as a key research direction for ensuring safe and ethical image synthesis in Text-to-Image (T2I) models. While existing studies have explored concept erasure across multiple concepts, they typically assume only a single target concept per image, a limitation increasingly …

• Cross-Domain Generalization Limits of Vision Foundation Models in Facial Deepfake Detection

  Ibrahim Delibasoglu · 26 de mayo de 2026

  The rapid evolution of generative models has enabled the creation of hyper-realistic facial deepfakes, exposing a critical vulnerability in modern digital forensics: the inability of detectors to generalize to unseen manipulation techniques. Traditional networks suffer from representation collapse, …

• Adversarial Error Correction for Visual Autoregressive Generation

  Ligong Bi, Tao Huang, Jianyuan Guo, Chang Xu · 26 de mayo de 2026

  Visual Autoregressive (VAR) models have emerged as a powerful paradigm for image synthesis by performing hierarchical next-scale prediction. However, VAR models are inherently prone to cascading error propagation, where subtle coarse-scale mispredictions are amplified across the hierarchy, ultimatel…

• Nano World Models: A Minimalist Implementation of Future Video Prediction

  Siqiao Huang, Partha Kaushik, Michael Chen, Hengkai Pan, Omar Chehab, Fernando Moreno-Pino, Max Simchowitz · 26 de mayo de 2026

  World models have become a central paradigm for learning predictive simulators that support generation, planning, and decision-making. Yet, despite rapid progress in industry-scale interactive video generation, the broader research community still lacks compact, reproducible, and easily extensible i…

• UWM-JEPA: Predictive World Models That Imagine in Belief Space

  Santosh Kumar Radha, Oktay Goktas · 26 de mayo de 2026

  World models for partially observed environments must imagine multiple compatible hidden futures and steer between them under counterfactual actions. Joint Embedding Predictive Architectures (JEPAs) do this in latent space, but a vector-valued latent has no internal structure for carrying the belief…

• Paris 2.0: A Decentralized Diffusion Model for Video Generation

  Ali Rouzbayani, Bidhan Roy, Marcos Villagra, Zhiying Jiang · 26 de mayo de 2026

  We present Paris 2.0, the first video generation model pre-trained through decentralized computation. Its training recipe builds upon Paris 1.0 (arXiv:2510.03434), the first ever open-weight Decentralized Diffusion Model (DDM), which showed that image generation can be trained without a monolithic G…