Generative Adversarial Networks and Image Synthesis

Derniers papiers

• WAV: Multi-Resolution Block Residual Routing for Deep Decoder-Only Transformers

  Kehan Wang · 8 juin 2026

  Residual connections are central to training deep Transformers, but standard PreNorm residual streams aggregate sublayer updates with fixed unit weights. Recent Attention Residuals replace this fixed accumulation with content-dependent depth-wise routing, and Block Attention Residuals make the mecha…

• FreeAnimate: Training-Free Human Image Animation with Preview-Guided Denoising

  Yuan Zeng, Yujia Shi, Zongqing Lu, QingMin Liao · 8 juin 2026

  Human Image Animation has seen significant advancements, primarily driven by diffusion models. However, existing methods typically demand substantial training data and resources to achieve high-quality results, limiting generalization and accessibility. In this work, we introduce \emph{FreeAnimate},…

• Where Rectified Flows Leak: Characterising Membership Signals Along the Interpolation Path

  Thomas Sesmat, Gabriel Meseguer-Brocal, Geoffroy Peeters · 8 juin 2026

  Understanding what generative models retain from training data remains challenging, with implications for copyright and privacy. Beyond verbatim reproduction, models can encode subtler traces of their training data that never surface in their outputs yet remain exploitable. We study this regime for …

• Drifting Models for Surrogate Flow Modeling

  Chris R. Jung, Markus D\"orr, Natalie J\"ungling, Jennifer Niessner, Adam T. M\"uller, Nicolaj C. Stache · 8 juin 2026

  While Computational Fluid Dynamics (CFD) provides high-fidelity flow fields for optimizing indoor environments, its computational cost limits rapid exploration. To solve this problem generative surrogates offer better distribution modeling than deterministic networks, but iterative sampling is slow.…

• Multiscale POD of Transformer Attention Fields: Scale-Selective Analysis via Morlet Scalogram

  Athanasios Zeris · 8 juin 2026

  We introduce scale-selective Proper Orthogonal Decomposition (POD) for transformer attention fields, inspired by the use of POD for extracting energetically dominant modes from turbulent flow ensembles. The Morlet continuous wavelet transform identifies dominant temporal scales in the attention lag …

• TrioPose: Native Triple-Stream Diffusion Transformers for Pose-Guided Text-to-Image Generation

  Dian Gu, Zhengyi Yang · 8 juin 2026

  Pose-guided text-to-image generation often suffers from limb distortions and feature crosstalk in complex multi-person scenarios. While existing UNet-based adapters struggle with long-range spatial dependencies, emerging Multimodal Diffusion Transformers (MM-DiTs) offer superior global modeling. How…

• Beyond Linear and Overcomplete Regimes: A Mean-Field Analysis of Bottleneck Autoencoders

  Santanu Das, Ramyak Bilas, Pascal Esser, Satyaki Mukherjee · 8 juin 2026

  Autoencoders (AEs) learn low-dimensional representations by mapping data into a latent space while minimizing reconstruction error. Despite their empirical success, theoretical understanding remains limited and largely restricted to linear models or settings without a bottleneck. In this work, we st…

• CULTURESCORE: Evaluating Cultural Faithfulness in Video Generation Models

  Anku Rani, Wei Dai, Shravan Nayak, Pattie Maes, Mahdi M. Kalayeh, Paul Pu Liang · 8 juin 2026

  As video generation models like Veo 3.1 and LTX-2 advance, their ability to accurately represent diverse global cultures remains a critical yet understudied frontier. Current metrics, such as VideoScore, only measure visual quality but offer no mechanism for assessing cultural faithfulness. Conseque…

• ScatterPrism: convergence for generative simulation and inverse problems in particle and nuclear physics

  Zeyu Xia, Tyler Kim, Trevor Reed, Judy Fox, Geoffrey Fox, Adam Szczepaniak · 8 juin 2026

  High-fidelity simulations and complex inverse problems, such as detector modeling and unfolding, are computationally intensive bottlenecks across subatomic physics, yet essential for accurate physical interpretation. While Conditional Flow Matching (CFM) offers a robust acceleration approach, we dem…

• Direct 3D-Aware Object Insertion via Decomposed Visual Proxies

  Jingbo Gong, Yikai Wang, Yushi Lan, Yuhao Wan, Ziheng Ouyang, Rui Zhao, Ming-Ming Cheng, Qibin Hou, Chen Change Loy · 8 juin 2026

  Object insertion aims to seamlessly composite a reference object into a specified region of a background image. Recent diffusion-based methods achieve high visual quality but formulate insertion as a simple 2D inpainting task, providing no explicit control over the object's 3D pose and limiting thei…

• Breaking the Lock-in: Diversifying Text-to-Image Generation via Representation Modulation

  Dahee Kwon, Haeun Lee, Jaesik Choi · 8 juin 2026

  Recent text-to-image models built on large-scale Transformer backbones and flow-based objectives deliver strong text-image alignment and high visual quality, yet often produce overly similar samples under a fixed prompt. Existing diversity-enhancement methods alleviate this issue, but typically requ…

• The Invisible Hand of Physics: When Video Diffusion Models Know More Than They Show

  Parsa Esmati, Somjit Nath, Katja Hofmann, Derek Nowrouzezahrai, Samira Ebrahimi Kahou, Majid Mirmehdi · 5 juin 2026

  Modern video diffusion models generate increasingly realistic and temporally coherent videos, motivating their use as candidate world simulators. Yet it remains unclear whether these models internally encode physical structure, or merely reproduce motion patterns seen during training. We study this …

• Double Preconditioning (DoPr): Optimization for Test-Time Performance, not Validation Loss

  Thomas T. Zhang, Alok Shah, Yifei Zhang, Vincent Zhang, Nikolai Matni, Max Simchowitz · 5 juin 2026

  Many modern applications of deep learning involve training a neural network via a one-step prediction loss (e.g., $L^2$ regression, cross-entropy), but deploy the network by rolling out along its own predictions. Key examples include autoregressive language modeling, flow-based generative modeling, …

• Edit-R2: Context-Aware Reinforcement Learning for Multi-Turn Image Editing

  Yuxiao Ye, Haoran He, Fangyuan Kong, Xintao Wang, Pengfei Wan, Kun Gai, Ling Pan · 5 juin 2026

  Text-guided image editing has advanced rapidly with diffusion models and unified multimodal foundation models. However, most existing methods remain confined to single-turn settings, overlooking the more realistic scenario of multi-turn in-context editing, where users iteratively refine an image thr…

• Your GFlowNet Secretly Learns an Optimal Transport Plan

  Ian Maksimov, Nikita Morozov, Denis Belomestny, Sergey Samsonov · 5 juin 2026

  Generative Flow Networks (GFlowNets) are a framework for sampling structured objects via stochastic trajectories in a directed graph. In this work, we establish a theoretical connection between non-acyclic GFlowNets and optimal transport (OT). We show that fixing the initial flow distribution in a m…

• Do Models Share Safety Representations? Cross-Model Steering for Safe Visual Generation

  Tobia Poppi, Silvia Cappelletti, Sara Sarto, Florian Schiffers, Garin Kessler, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara · 5 juin 2026

  Recent progress in generative modeling has made safety control a central challenge, yet existing approaches remain largely model-specific, requiring retraining or tailored interventions for each new architecture. In this work, we ask whether safety can be represented as a portable latent direction, …

• Pretraining Recurrent Networks without Recurrence

  Akarsh Kumar, Phillip Isola · 5 juin 2026

  Training recurrent neural networks (RNNs) requires assigning credit across long sequences of computations. Standard backpropagation through time (BPTT) addresses this problem poorly: it is sequential in time, limiting parallelism, and suffers from vanishing or exploding gradients, making long-range …

• F3-Tokenizer: Taming Audio Autoencoder Latents for Understanding and Generation

  Dinghao Zhou, Xingchen Song, Di Wu, Pengyu Cheng, Shengfan Shen, Sixiang Lv · 5 juin 2026

  Continuous audio autoencoders reconstruct waveforms well but often produce latents with weak structure for understanding, while self-supervised audio encoders capture semantics but are not directly decodable. This mismatch complicates a single audio tokenizer that must support both understanding and…

• FoeGlass: Simple In-Context Learning Is Enough for Red Teaming Audio Deepfake Detectors

  Sepehr Dehdashtian, Jacob H Seidman, Vishnu N Boddeti, Gaurav Bharaj · 4 juin 2026

  Audio deepfake detection (ADD) models are critical for countering the malicious use of text-to-speech (TTS) models. Evaluating and strengthening ADD models requires developing datasets that span the space of generated audio and highlight high-error regions. Existing dataset development strategies fa…

• Optimal Transport Flow Matching by Design

  Shimon Malnick, Matan Rusanovsky, Ohad Fried, Shai Avidan · 4 juin 2026

  Flow matching models learn to transport samples from a simple prior distribution to a complex data distribution. When prior-data pairs are coupled via optimal transport (OT), the learned trajectories are straight and non-crossing, enabling fast, even single-step, generation. However, computing the O…

• Activation Steering of Video Generation Models via Reduced-Order Linear Optimal Control

  Jihoon Hong, Alice Chan, Qiyue Dai, Julian Skifstad, Glen Chou · 4 juin 2026

  Text-to-video (T2V) models trained on large-scale web data can generate undesired content, motivating interventions that reduce harmful outputs without sacrificing visual quality. Activation steering offers an attractive mechanistic alternative to finetuning and prompt filtering, but existing T2V st…

• GeM-NR: Geometry-Aware Multi-View Editing for Nonrigid Scene Changes

  Josef Bengtson, Yaroslava Lochman, Fredrik Kahl · 4 juin 2026

  Recent developments in multi-view image editing with generative models have brought us a step closer toward general 3D content generation and customization. Most existing works focus on rigid or appearance-only edits by utilizing the geometry of the unedited scene. This naturally limits these method…

• Efficient and Training-Free Single-Image Diffusion Models

  Haojun Qiu, Kiriakos N. Kutulakos, David B. Lindell · 4 juin 2026

  We consider the problem of generating images whose internal structure -- defined by the distribution of patches across multiple scales -- matches that of a single reference image. Recent approaches address this problem by training a diffusion model on a single image. But even in this setting, traini…

• OA-CutMix: Correcting the Label Bias of CutMix

  Tobias Christian Nauen, Stanislav Frolov, Federico Raue, Brian B. Moser, Andreas Dengel · 4 juin 2026

  CutMix has become the de facto standard mixing augmentation, yet its label assignment rests on a flawed assumption: The area of the pasted patch faithfully reflects its semantic contribution to the mixed image. In practice, however, patches frequently land on background regions, assigning label cred…

• RePercENT: Scaling Disentangled Representation Learning Beyond Two Modalities

  Vasiliki Rizou, Pascal Frossard, Dorina Thanou · 4 juin 2026

  To leverage the full potential of multimodal data, we need representations that go beyond the state-of-the-art alignment and fusion approaches and exploit all cross-modal interactions without sacrificing modality-specific information. Learning disentangled representations is a principled way to iden…