Generative Adversarial Networks and Image Synthesis

Neueste Paper

• Decomposing multimodal embedding spaces with group-sparse autoencoders

  Chiraag Kaushik, Davis Barch, Andrea Fanelli · 29. Januar 2026

  The Linear Representation Hypothesis asserts that the embeddings learned by neural networks can be understood as linear combinations of features corresponding to high-level concepts. Based on this ansatz, sparse autoencoders (SAEs) have recently become a popular method for decomposing embeddings int…

• Deep Neural Networks as Iterated Function Systems and a Generalization Bound

  Jonathan Vacher (MAP5 - UMR 8145) · 29. Januar 2026

  Deep neural networks (DNNs) achieve remarkable performance on a wide range of tasks, yet their mathematical analysis remains fragmented: stability and generalization are typically studied in disparate frameworks and on a case-by-case basis. Architecturally, DNNs rely on the recursive application of …

• Detecting and Mitigating Memorization in Diffusion Models through Anisotropy of the Log-Probability

  Rohan Asthana, Vasileios Belagiannis · 29. Januar 2026

  Diffusion-based image generative models produce high-fidelity images through iterative denoising but remain vulnerable to memorization, where they unintentionally reproduce exact copies or parts of training images. Recent memorization detection methods are primarily based on the norm of score differ…

• Exploring Transformer Placement in Variational Autoencoders for Tabular Data Generation

  An\'ibal Silva, Mois\'es Santos, Andr\'e Restivo, Carlos Soares · 29. Januar 2026

  Tabular data remains a challenging domain for generative models. In particular, the standard Variational Autoencoder (VAE) architecture, typically composed of multilayer perceptrons, struggles to model relationships between features, especially when handling mixed data types. In contrast, Transforme…

• TABED: Test-Time Adaptive Ensemble Drafting for Robust Speculative Decoding in LVLMs

  Minjae Lee, Wonjun Kang, Byeongkeun Ahn, Christian Classen, Kevin Galim, Seunghyuk Oh, Minghao Yan, Hyung Il Koo, Kangwook Lee · 29. Januar 2026

  Speculative decoding (SD) has proven effective for accelerating LLM inference by quickly generating draft tokens and verifying them in parallel. However, SD remains largely unexplored for Large Vision-Language Models (LVLMs), which extend LLMs to process both image and text prompts. To address this …

• Audio Deepfake Detection in the Age of Advanced Text-to-Speech models

  Robin Singh, Aditya Yogesh Nair, Fabio Palumbo, Florian Barbaro, Anna Dyka, Lohith Rachakonda · 29. Januar 2026

  Recent advances in Text-to-Speech (TTS) systems have substantially increased the realism of synthetic speech, raising new challenges for audio deepfake detection. This work presents a comparative evaluation of three state-of-the-art TTS models--Dia2, Maya1, and MeloTTS--representing streaming, LLM-b…

• DeRaDiff: Denoising Time Realignment of Diffusion Models

  Ratnavibusena Don Shahain Manujith, Yang Zhang, Teoh Tze Tzun, Kenji Kawaguchi · 29. Januar 2026

  Recent advances align diffusion models with human preferences to increase aesthetic appeal and mitigate artifacts and biases. Such methods aim to maximize a conditional output distribution aligned with higher rewards whilst not drifting far from a pretrained prior. This is commonly enforced by KL (K…

• Order-Optimal Sample Complexity of Rectified Flows

  Hari Krishna Sahoo, Mudit Gaur, Vaneet Aggarwal · 29. Januar 2026

  Recently, flow-based generative models have shown superior efficiency compared to diffusion models. In this paper, we study rectified flow models, which constrain transport trajectories to be linear from the base distribution to the data distribution. This structural restriction greatly accelerates …

• DIVERSE: Disagreement-Inducing Vector Evolution for Rashomon Set Exploration

  Gilles Eerlings, Brent Zoomers, Jori Liesenborgs, Gustavo Rovelo Ruiz, Kris Luyten · 29. Januar 2026

  We propose DIVERSE, a framework for systematically exploring the Rashomon set of deep neural networks, the collection of models that match a reference model's accuracy while differing in their predictive behavior. DIVERSE augments a pretrained model with Feature-wise Linear Modulation (FiLM) layers …

• Latent Object Permanence: Topological Phase Transitions, Free-Energy Principles, and Renormalization Group Flows in Deep Transformer Manifolds

  Faruk Alpay, Bugra Kilictas · 29. Januar 2026

  We study the emergence of multi-step reasoning in deep Transformer language models through a geometric and statistical-physics lens. Treating the hidden-state trajectory as a flow on an implicit Riemannian manifold, we analyze the layerwise covariance spectrum of activations, where $C^{(\ell)}=\math…

• FAIRT2V: Training-Free Debiasing for Text-to-Video Diffusion Models

  Haonan Zhong, Wei Song, Tingxu Han, Maurice Pagnucco, Jingling Xue, Yang Song · 29. Januar 2026

  Text-to-video (T2V) diffusion models have achieved rapid progress, yet their demographic biases, particularly gender bias, remain largely unexplored. We present FairT2V, a training-free debiasing framework for text-to-video generation that mitigates encoder-induced bias without finetuning. We first …

• LightSBB-M: Bridging Schr\"odinger and Bass for Generative Diffusion Modeling

  Alexandre Alouadi, Pierre Henry-Labord\`ere, Gr\'egoire Loeper, Othmane Mazhar, Huy\^en Pham, Nizar Touzi · 28. Januar 2026

  The Schrodinger Bridge and Bass (SBB) formulation, which jointly controls drift and volatility, is an established extension of the classical Schrodinger Bridge (SB). Building on this framework, we introduce LightSBB-M, an algorithm that computes the optimal SBB transport plan in only a few iteration…

• Streaming-dLLM: Accelerating Diffusion LLMs via Suffix Pruning and Dynamic Decoding

  Zhongyu Xiao, Zhiwei Hao, Jianyuan Guo, Yong Luo, Jia Liu, Jie Xu, Han Hu · 28. Januar 2026

  Diffusion Large Language Models (dLLMs) offer a compelling paradigm for natural language generation, leveraging parallel decoding and bidirectional attention to achieve superior global coherence compared to autoregressive models. While recent works have accelerated inference via KV cache reuse or he…

• CP Loss: Channel-wise Perceptual Loss for Time Series Forecasting

  Yaohua Zha, Chunlin Fan, Peiyuan Liu, Yong Jiang, Tao Dai, Hai Wu, Shu-Tao Xia · 28. Januar 2026

  Multi-channel time-series data, prevalent across diverse applications, is characterized by significant heterogeneity in its different channels. However, existing forecasting models are typically guided by channel-agnostic loss functions like MSE, which apply a uniform metric across all channels. Thi…

• RealStats: A Rigorous Real-Only Statistical Framework for Fake Image Detection

  Haim Zisman, Uri Shaham · 28. Januar 2026

  As generative models continue to evolve, detecting AI-generated images remains a critical challenge. While effective detection methods exist, they often lack formal interpretability and may rely on implicit assumptions about fake content, potentially limiting robustness to distributional shifts. In …

• Post-LayerNorm Is Back: Stable, ExpressivE, and Deep

  Chen Chen, Lai Wei · 28. Januar 2026

  Large language model (LLM) scaling is hitting a wall. Widening models yields diminishing returns, and extending context length does not improve fundamental expressivity. In contrast, depth scaling offers theoretically superior expressivity, yet current Transformer architectures struggle to train rel…

• Sim-and-Human Co-training for Data-Efficient and Generalizable Robotic Manipulation

  Kaipeng Fang, Weiqing Liang, Yuyang Li, Ji Zhang, Pengpeng Zeng, Lianli Gao, Jingkuan Song, Heng Tao Shen · 28. Januar 2026

  Synthetic simulation data and real-world human data provide scalable alternatives to circumvent the prohibitive costs of robot data collection. However, these sources suffer from the sim-to-real visual gap and the human-to-robot embodiment gap, respectively, which limits the policy's generalization …

• Is Finer Better? The Limits of Microscaling Formats in Large Language Models

  Andrea Fasoli, Monodeep Kar, Chi-Chun Liu, Swagath Venkataramani, Viji Srinivasan, Leland Chang, Naigang Wang · 28. Januar 2026

  Microscaling data formats leverage per-block tensor quantization to enable aggressive model compression with limited loss in accuracy. Unlocking their potential for efficient training and inference necessitates hardware-friendly implementations that handle matrix multiplications in a native format a…

• Nearly Optimal Bayesian Inference for Structural Missingness

  Chen Liang, Donghua Yang, Yutong Zhao, Tianle Zhang, Shenghang Zhou, Zhiyu Liang, Hengtong Zhang, Hongzhi Wang, Ziqi Li, Xiyang Zhang, Zheng Liang, Yifei Li · 28. Januar 2026

  Structural missingness breaks 'just impute and train': values can be undefined by causal or logical constraints, and the mask may depend on observed variables, unobserved variables (MNAR), and other missingness indicators. It simultaneously brings (i) a catch-22 situation with causal loop, predictio…

• Scale-Consistent State-Space Dynamics via Fractal of Stationary Transformations

  Geunhyeok Yu, Hyoseok Hwang · 28. Januar 2026

  Recent deep learning models increasingly rely on depth without structural guarantees on the validity of intermediate representations, rendering early stopping and adaptive computation ill-posed. We address this limitation by formulating a structural requirement for state-space model's scale-consiste…

• Smoothing the Score Function for Generalization in Diffusion Models: An Optimization-based Explanation Framework

  Xinyu Zhou, Jiawei Zhang, Stephen J. Wright · 28. Januar 2026

  Diffusion models achieve remarkable generation quality, yet face a fundamental challenge known as memorization, where generated samples can replicate training samples exactly. We develop a theoretical framework to explain this phenomenon by showing that the empirical score function (the score functi…

• GenCP: Towards Generative Modeling Paradigm of Coupled Physics

  Tianrun Gao, Haoren Zheng, Wenhao Deng, Haodong Feng, Tao Zhang, Ruiqi Feng, Qianyi Chen, Tailin Wu · 28. Januar 2026

  Real-world physical systems are inherently complex, often involving the coupling of multiple physics, making their simulation both highly valuable and challenging. Many mainstream approaches face challenges when dealing with decoupled data. Besides, they also suffer from low efficiency and fidelity …

• SNR-Edit: Structure-Aware Noise Rectification for Inversion-Free Flow-Based Editing

  Lifan Jiang, Boxi Wu, Yuhang Pei, Tianrun Wu, Yongyuan Chen, Yan Zhao, Shiyu Yu, Deng Cai · 28. Januar 2026

  Inversion-free image editing using flow-based generative models challenges the prevailing inversion-based pipelines. However, existing approaches rely on fixed Gaussian noise to construct the source trajectory, leading to biased trajectory dynamics and causing structural degradation or quality loss.…

• Diffusion models for multivariate subsurface generation and efficient probabilistic inversion

  Roberto Miele, Niklas Linde · 28. Januar 2026

  Diffusion models offer stable training and state-of-the-art performance for deep generative modeling tasks. Here, we consider their use in the context of multivariate subsurface modeling and probabilistic inversion. We first demonstrate that diffusion models enhance multivariate modeling capabilitie…

• Cortex-Grounded Diffusion Models for Brain Image Generation

  Fabian Bongratz, Yitong Li, Sama Elbaroudy, Christian Wachinger · 28. Januar 2026

  Synthetic neuroimaging data can mitigate critical limitations of real-world datasets, including the scarcity of rare phenotypes, domain shifts across scanners, and insufficient longitudinal coverage. However, existing generative models largely rely on weak conditioning signals, such as labels or tex…