Generative Adversarial Networks and Image Synthesis

Neueste Paper

• S-PRESSO: Ultra Low Bitrate Sound Effect Compression With Diffusion Autoencoders And Offline Quantization

  Zineb Lahrichi (IP Paris), Ga\"etan Hadjeres (IP Paris), Ga\"el Richard (IP Paris), Geoffroy Peeters (IP Paris) · 18. Februar 2026

  Neural audio compression models have recently achieved extreme compression rates, enabling efficient latent generative modeling. Conversely, latent generative models have been applied to compression, pushing the limits of continuous and discrete approaches. However, existing methods remain constrain…

• Spanning the Visual Analogy Space with a Weight Basis of LoRAs

  Hila Manor, Rinon Gal, Haggai Maron, Tomer Michaeli, Gal Chechik · 18. Februar 2026

  Visual analogy learning enables image manipulation through demonstration rather than textual description, allowing users to specify complex transformations difficult to articulate in words. Given a triplet $\{\mathbf{a}$, $\mathbf{a}'$, $\mathbf{b}\}$, the goal is to generate $\mathbf{b}'$ such that…

• Universal priors: solving empirical Bayes via Bayesian inference and pretraining

  Nick Cannella, Anzo Teh, Yanjun Han, Yury Polyanskiy · 18. Februar 2026

  We theoretically justify the recent empirical finding of [Teh et al., 2025] that a transformer pretrained on synthetically generated data achieves strong performance on empirical Bayes (EB) problems. We take an indirect approach to this question: rather than analyzing the model architecture or train…

• A unified theory of feature learning in RNNs and DNNs

  Jan P. Bauer, Kirsten Fischer, Moritz Helias, Agostina Palmigiano · 18. Februar 2026

  Recurrent and deep neural networks (RNNs/DNNs) are cornerstone architectures in machine learning. Remarkably, RNNs differ from DNNs only by weight sharing, as can be shown through unrolling in time. How does this structural similarity fit with the distinct functional properties these networks exhibi…

• Latent Regularization in Generative Test Input Generation

  Giorgi Merabishvili, Oliver Wei{\ss}l, Andrea Stocco · 18. Februar 2026

  This study investigates the impact of regularization of latent spaces through truncation on the quality of generated test inputs for deep learning classifiers. We evaluate this effect using style-based GANs, a state-of-the-art generative approach, and assess quality along three dimensions: validity,…

• Syndrome-Flow Consistency Model Achieves One-step Denoising Error Correction Codes

  Haoyu Lei, Chin Wa Lau, Kaiwen Zhou, Nian Guo, Farzan Farnia · 18. Februar 2026

  Error Correction Codes (ECC) are fundamental to reliable digital communication, yet designing neural decoders that are both accurate and computationally efficient remains challenging. Recent denoising diffusion decoders achieve state-of-the-art performance, but their iterative sampling limits practi…

• Refine Now, Query Fast: A Decoupled Refinement Paradigm for Implicit Neural Fields

  Tianyu Xiong, Skylar Wurster, Han-Wei Shen · 18. Februar 2026

  Implicit Neural Representations (INRs) have emerged as promising surrogates for large 3D scientific simulations due to their ability to continuously model spatial and conditional fields, yet they face a critical fidelity-speed dilemma: deep MLPs suffer from high inference cost, while efficient embed…

• Dynamic Training-Free Fusion of Subject and Style LoRAs

  Qinglong Cao, Yuntian Chen, Chao Ma, Xiaokang Yang · 18. Februar 2026

  Recent studies have explored the combination of multiple LoRAs to simultaneously generate user-specified subjects and styles. However, most existing approaches fuse LoRA weights using static statistical heuristics that deviate from LoRA's original purpose of learning adaptive feature adjustments and…

• EIDOS: Latent-Space Predictive Learning for Time Series Foundation Models

  Xinxing Zhou, Qingren Yao, Yiji Zhao, Chenghao Liu, Flora Salim, Xiaojie Yuan, Yanlong Wen, Ming Jin · 17. Februar 2026

  Most time series foundation models are pretrained by directly predicting future observations, which often yields weakly structured latent representations that capture surface noise rather than coherent and predictable temporal dynamics. In this work, we introduce EIDOS, a foundation model family tha…

• AdaCorrection: Adaptive Offset Cache Correction for Accurate Diffusion Transformers

  Dong Liu, Yanxuan Yu, Ben Lengerich, Ying Nian Wu · 17. Februar 2026

  Diffusion Transformers (DiTs) achieve state-of-the-art performance in high-fidelity image and video generation but suffer from expensive inference due to their iterative denoising structure. While prior methods accelerate sampling by caching intermediate features, they rely on static reuse schedules…

• BitDance: Scaling Autoregressive Generative Models with Binary Tokens

  Yuang Ai, Jiaming Han, Shaobin Zhuang, Weijia Mao, Xuefeng Hu, Ziyan Yang, Zhenheng Yang, Huaibo Huang, Xiangyu Yue, Hao Chen · 17. Februar 2026

  We present BitDance, a scalable autoregressive (AR) image generator that predicts binary visual tokens instead of codebook indices. With high-entropy binary latents, BitDance lets each token represent up to $2^{256}$ states, yielding a compact yet highly expressive discrete representation. Sampling …

• From Prompt to Production:Automating Brand-Safe Marketing Imagery with Text-to-Image Models

  Parmida Atighehchian, Henry Wang, Andrei Kapustin, Boris Lerner, Tiancheng Jiang, Taylor Jensen, Negin Sokhandan · 17. Februar 2026

  Text-to-image models have made significant strides, producing impressive results in generating images from textual descriptions. However, creating a scalable pipeline for deploying these models in production remains a challenge. Achieving the right balance between automation and human feedback is cr…

• Pawsterior: Variational Flow Matching for Structured Simulation-Based Inference

  Jorge Carrasco-Pollo, Floor Eijkelboom, Jan-Willem van de Meent · 17. Februar 2026

  We introduce Pawsterior, a variational flow-matching framework for improved and extended simulation-based inference (SBI). Many SBI problems involve posteriors constrained by structured domains, such as bounded physical parameters or hybrid discrete-continuous variables, yet standard flow-matching m…

• Conditionally Whitened Generative Models for Probabilistic Time Series Forecasting

  Yanfeng Yang, Siwei Chen, Pingping Hu, Zhaotong Shen, Yingjie Zhang, Zhuoran Sun, Shuai Li, Ziqi Chen, Kenji Fukumizu · 17. Februar 2026

  Probabilistic forecasting of multivariate time series is challenging due to non-stationarity, inter-variable dependencies, and distribution shifts. While recent diffusion and flow matching models have shown promise, they often ignore informative priors such as conditional means and covariances. In t…

• Multi-scale Autoregressive Models are Laplacian, Discrete, and Latent Diffusion Models in Disguise

  Steve Hong, Samuel Belkadi · 17. Februar 2026

  We reinterpret Visual Autoregressive (VAR) models as iterative refinement models to identify which design choices drive their quality-efficiency trade-off. Instead of treating VAR only as next-scale autoregression, we formalise it as a deterministic forward process that builds a Laplacian-style late…

• Simulating the Real World: A Unified Survey of Multimodal Generative Models

  Yuqi Hu, Longguang Wang, Xian Liu, Ling-Hao Chen, Yuwei Guo, Yukai Shi, Ce Liu, Anyi Rao, Zeyu Wang, Hui Xiong · 17. Februar 2026

  Understanding and replicating the real world is a critical challenge in Artificial General Intelligence (AGI) research. To achieve this, many existing approaches, such as world models, aim to capture the fundamental principles governing the physical world, enabling more accurate simulations and mean…

• FUTON: Fourier Tensor Network for Implicit Neural Representations

  Pooya Ashtari, Pourya Behmandpoor, Nikos Deligiannis, Aleksandra Pizurica · 17. Februar 2026

  Implicit neural representations (INRs) have emerged as powerful tools for encoding signals, yet dominant MLP-based designs often suffer from slow convergence, overfitting to noise, and poor extrapolation. We introduce FUTON (Fourier Tensor Network), which models signals as generalized Fourier series…

• CoCoDiff: Correspondence-Consistent Diffusion Model for Fine-grained Style Transfer

  Wenbo Nie, Zixiang Li, Renshuai Tao, Bin Wu, Yunchao Wei, Yao Zhao · 17. Februar 2026

  Transferring visual style between images while preserving semantic correspondence between similar objects remains a central challenge in computer vision. While existing methods have made great strides, most of them operate at global level but overlook region-wise and even pixel-wise semantic corresp…

• Exposing Diversity Bias in Deep Generative Models: Statistical Origins and Correction of Diversity Error

  Farzan Farnia, Mohammad Jalali, Azim Ospanov · 17. Februar 2026

  Deep generative models have achieved great success in producing high-quality samples, making them a central tool across machine learning applications. Beyond sample quality, an important yet less systematically studied question is whether trained generative models faithfully capture the diversity of…

• NeuronSeek: On Stability and Expressivity of Task-driven Neurons

  Hanyu Pei, Jing-Xiao Liao, Qibin Zhao, Ting Gao, Shijun Zhang, Xiaoge Zhang, Feng-Lei Fan · 17. Februar 2026

  Drawing inspiration from our human brain that designs different neurons for different tasks, recent advances in deep learning have explored modifying a network's neurons to develop so-called task-driven neurons. Prototyping task-driven neurons (referred to as NeuronSeek) employs symbolic regression …

• SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning

  Jintao Zhang, Kai Jiang, Chendong Xiang, Weiqi Feng, Yuezhou Hu, Haocheng Xi, Jianfei Chen, Jun Zhu · 17. Februar 2026

  Many training-free sparse attention methods are effective for accelerating diffusion models. Recently, several works suggest that making sparse attention trainable can further increase sparsity while preserving generation quality. We study three key questions: (1) when do the two common masking rule…

• When Test-Time Guidance Is Enough: Fast Image and Video Editing with Diffusion Guidance

  Ahmed Ghorbel, Badr Moufad, Navid Bagheri Shouraki, Alain Oliviero Durmus, Thomas Hirtz, Eric Moulines, Jimmy Olsson, Yazid Janati · 17. Februar 2026

  Text-driven image and video editing can be naturally cast as inpainting problems, where masked regions are reconstructed to remain consistent with both the observed content and the editing prompt. Recent advances in test-time guidance for diffusion and flow models provide a principled framework for …

• Silent Inconsistency in Data-Parallel Full Fine-Tuning: Diagnosing Worker-Level Optimization Misalignment

  Hong Li, Zhen Zhou, Honggang Zhang, Yuping Luo, Xinyue Wang, Han Gong, Zhiyuan Liu · 17. Februar 2026

  Data-parallel (DP) training with synchronous all-reduce is a dominant paradigm for full-parameter fine-tuning of large language models (LLMs). While parameter synchronization guarantees numerical equivalence of model weights after each iteration, it does not necessarily imply alignment of worker-lev…

• Spectral Collapse in Diffusion Inversion

  Nicolas Bourriez, Alexandre Verine, Auguste Genovesio · 17. Februar 2026

  Conditional diffusion inversion provides a powerful framework for unpaired image-to-image translation. However, we demonstrate through an extensive analysis that standard deterministic inversion (e.g. DDIM) fails when the source domain is spectrally sparse compared to the target domain (e.g., super-…

• Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistency

  Kaiwen Zheng, Yuji Wang, Qianli Ma, Huayu Chen, Jintao Zhang, Yogesh Balaji, Jianfei Chen, Ming-Yu Liu, Jun Zhu, Qinsheng Zhang · 17. Februar 2026

  Although continuous-time consistency models (e.g., sCM, MeanFlow) are theoretically principled and empirically powerful for fast academic-scale diffusion, its applicability to large-scale text-to-image and video tasks remains unclear due to infrastructure challenges in Jacobian-vector product (JVP) …