Generative Adversarial Networks and Image Synthesis

Últimos artículos

• STARFlow-V: End-to-End Video Generative Modeling with Normalizing Flows

  Jiatao Gu, Ying Shen, Tianrong Chen, Laurent Dinh, Yuyang Wang, Miguel Angel Bautista, David Berthelot, Josh Susskind, Shuangfei Zhai · 27 de noviembre de 2025

  Normalizing flows (NFs) are end-to-end likelihood-based generative models for continuous data, and have recently regained attention with encouraging progress on image generation. Yet in the video generation domain, where spatiotemporal complexity and computational cost are substantially higher, stat…

• From Diffusion to One-Step Generation: A Comparative Study of Flow-Based Models with Application to Image Inpainting

  Umang Agarwal, Rudraksh Sangore, Sumit Laddha · 27 de noviembre de 2025

  We present a comprehensive comparative study of three generative modeling paradigms: Denoising Diffusion Probabilistic Models (DDPM), Conditional Flow Matching (CFM), and MeanFlow. While DDPM and CFM require iterative sampling, MeanFlow enables direct one-step generation by modeling the average velo…

• Test-Time Alignment of Text-to-Image Diffusion Models via Null-Text Embedding Optimisation

  Taehoon Kim, Henry Gouk, Timothy Hospedales · 27 de noviembre de 2025

  Test-time alignment (TTA) aims to adapt models to specific rewards during inference. However, existing methods tend to either under-optimise or over-optimise (reward hack) the target reward function. We propose Null-Text Test-Time Alignment (Null-TTA), which aligns diffusion models by optimising the…

• Efficient Training for Human Video Generation with Entropy-Guided Prioritized Progressive Learning

  Changlin Li, Jiawei Zhang, Shuhao Liu, Sihao Lin, Zeyi Shi, Zhihui Li, Xiaojun Chang · 27 de noviembre de 2025

  Human video generation has advanced rapidly with the development of diffusion models, but the high computational cost and substantial memory consumption associated with training these models on high-resolution, multi-frame data pose significant challenges. In this paper, we propose Entropy-Guided Pr…

• SONAR: Spectral-Contrastive Audio Residuals for Generalizable Deepfake Detection

  Ido Nitzan HIdekel, Gal lifshitz, Khen Cohen, Dan Raviv · 27 de noviembre de 2025

  Deepfake (DF) audio detectors still struggle to generalize to out of distribution inputs. A central reason is spectral bias, the tendency of neural networks to learn low-frequency structure before high-frequency (HF) details, which both causes DF generators to leave HF artifacts and leaves those sam…

• Flow Matching Meets PDEs: A Unified Framework for Physics-Constrained Generation

  Giacomo Baldan, Qiang Liu, Alberto Guardone, Nils Thuerey · 27 de noviembre de 2025

  Generative machine learning methods, such as diffusion models and flow matching, have shown great potential in modeling complex system behaviors and building efficient surrogate models. However, these methods typically learn the underlying physics implicitly from data. We propose Physics-Based Flow …

• Momentum Multi-Marginal Schr\"odinger Bridge Matching

  Panagiotis Theodoropoulos, Augustinos D. Saravanos, Evangelos A. Theodorou, Guan-Horng Liu · 27 de noviembre de 2025

  Understanding complex systems by inferring trajectories from sparse sample snapshots is a fundamental challenge in a wide range of domains, e.g., single-cell biology, meteorology, and economics. Despite advancements in Bridge and Flow matching frameworks, current methodologies rely on pairwise inter…

• EmoFeedback$^2$: Reinforcement of Continuous Emotional Image Generation via LVLM-based Reward and Textual Feedback

  Jingyang Jia, Kai Shu, Gang Yang, Long Xing, Xun Chen, Aiping Liu · 27 de noviembre de 2025

  Continuous emotional image generation (C-EICG) is emerging rapidly due to its ability to produce images aligned with both user descriptions and continuous emotional values. However, existing approaches lack emotional feedback from generated images, limiting the control of emotional continuity. Addit…

• Which Layer Causes Distribution Deviation? Entropy-Guided Adaptive Pruning for Diffusion and Flow Models

  Changlin Li, Jiawei Zhang, Zeyi Shi, Zongxin Yang, Zhihui Li, Xiaojun Chang · 27 de noviembre de 2025

  Large-scale vision generative models, including diffusion and flow models, have demonstrated remarkable performance in visual generation tasks. However, transferring these pre-trained models to downstream tasks often results in significant parameter redundancy. In this paper, we propose EntPruner, a…

• TSGM: Regular and Irregular Time-series Generation using Score-based Generative Models

  Haksoo Lim, Jaehoon Lee, Sewon Park, Minjung Kim, Noseong Park · 27 de noviembre de 2025

  Score-based generative models (SGMs) have demonstrated unparalleled sampling quality and diversity in numerous fields, such as image generation, voice synthesis, and tabular data synthesis, etc. Inspired by those outstanding results, we apply SGMs to synthesize time-series by learning its conditiona…

• A Conditional Distribution Equality Testing Framework using Deep Generative Learning

  Siming Zheng, Tong Wang, Meifang Lan, Yuanyuan Lin · 27 de noviembre de 2025

  In this paper, we propose a general framework for testing the conditional distribution equality in a two-sample problem, which is most relevant to covariate shift and causal discovery. Our framework is built on neural network-based generative methods and sample splitting techniques by transforming t…

• Training-Free Diffusion Priors for Text-to-Image Generation via Optimization-based Visual Inversion

  Samuele Dell'Erba, Andrew D. Bagdanov · 27 de noviembre de 2025

  Diffusion models have established the state-of-the-art in text-to-image generation, but their performance often relies on a diffusion prior network to translate text embeddings into the visual manifold for easier decoding. These priors are computationally expensive and require extensive training on …

• DinoLizer: Learning from the Best for Generative Inpainting Localization

  Minh Thong Doi (IMT Nord Europe, CRIStAL), Jan Butora (CRIStAL), Vincent Itier (IMT Nord Europe, CRIStAL), J\'er\'emie Boulanger (CRIStAL), Patrick Bas (CRIStAL) · 27 de noviembre de 2025

  We introduce DinoLizer, a DINOv2-based model for localizing manipulated regions in generative inpainting. Our method builds on a DINOv2 model pretrained to detect synthetic images on the B-Free dataset. We add a linear classification head on top of the Vision Transformer's patch embeddings to predic…

• Inferix: A Block-Diffusion based Next-Generation Inference Engine for World Simulation

  Inferix Team, Tianyu Feng, Yizeng Han, Jiahao He, Yuanyu He, Xi Lin, Teng Liu, Hanfeng Lu, Jiasheng Tang, Wei Wang, Zhiyuan Wang, Jichao Wu, Mingyang Yang, Yinghao Yu, Zeyu Zhang, Bohan Zhuang · 27 de noviembre de 2025

  World models serve as core simulators for fields such as agentic AI, embodied AI, and gaming, capable of generating long, physically realistic, and interactive high-quality videos. Moreover, scaling these models could unlock emergent capabilities in visual perception, understanding, and reasoning, p…

• A Gray-box Attack against Latent Diffusion Model-based Image Editing by Posterior Collapse

  Zhongliang Guo, Chun Tong Lei, Lei Fang, Shuai Zhao, Yifei Qian, Jingyu Lin, Zeyu Wang, Cunjian Chen, Ognjen Arandjelovi\'c, Chun Pong Lau · 27 de noviembre de 2025

  Recent advancements in Latent Diffusion Models (LDMs) have revolutionized image synthesis and manipulation, raising significant concerns about data misappropriation and intellectual property infringement. While adversarial attacks have been extensively explored as a protective measure against such m…

• ExDDV: A New Dataset for Explainable Deepfake Detection in Video

  Vlad Hondru, Eduard Hogea, Darian Onchis, Radu Tudor Ionescu · 26 de noviembre de 2025

  The ever growing realism and quality of generated videos makes it increasingly harder for humans to spot deepfake content, who need to rely more and more on automatic deepfake detectors. However, deepfake detectors are also prone to errors, and their decisions are not explainable, leaving humans vul…

• RoPECraft: Training-Free Motion Transfer with Trajectory-Guided RoPE Optimization on Diffusion Transformers

  Ahmet Berke Gokmen, Yigit Ekin, Bahri Batuhan Bilecen, Aysegul Dundar · 26 de noviembre de 2025

  We propose RoPECraft, a training-free video motion transfer method for diffusion transformers that operates solely by modifying their rotary positional embeddings (RoPE). We first extract dense optical flow from a reference video, and utilize the resulting motion offsets to warp the complex-exponent…

• LikePhys: Evaluating Intuitive Physics Understanding in Video Diffusion Models via Likelihood Preference

  Jianhao Yuan, Fabio Pizzati, Francesco Pinto, Lars Kunze, Ivan Laptev, Paul Newman, Philip Torr, Daniele De Martini · 26 de noviembre de 2025

  Intuitive physics understanding in video diffusion models plays an essential role in building general-purpose physically plausible world simulators, yet accurately evaluating such capacity remains a challenging task due to the difficulty in disentangling physics correctness from visual appearance in…

• CGCE: Classifier-Guided Concept Erasure in Generative Models

  Viet Nguyen, Vishal M. Patel · 26 de noviembre de 2025

  Recent advancements in large-scale generative models have enabled the creation of high-quality images and videos, but have also raised significant safety concerns regarding the generation of unsafe content. To mitigate this, concept erasure methods have been developed to remove undesirable concepts …

• ModHiFi: Identifying High Fidelity predictive components for Model Modification

  Dhruva Kashyap, Chaitanya Murti, Pranav K Nayak, Tanay Narshana, Chiranjib Bhattacharyya · 26 de noviembre de 2025

  Open weight models, which are ubiquitous, rarely provide access to their training data or loss function. This makes modifying such models for tasks such as pruning or unlearning constrained by this unavailability an active area of research. Existing techniques typically require gradients or ground-t…

• Latent Diffusion Inversion Requires Understanding the Latent Space

  Mingxing Rao, Bowen Qu, Daniel Moyer · 26 de noviembre de 2025

  The recovery of training data from generative models (``model inversion'') has been extensively studied for diffusion models in the data domain. The encoder/decoder pair and corresponding latent codes have largely been ignored by inversion techniques applied to latent space generative models, e.g., …

• Leveraging Unlabeled Data from Unknown Sources via Dual-Path Guidance for Deepfake Face Detection

  Zhiqiang Yang, Renshuai Tao, Chunjie Zhang, guodong yang, Xiaolong Zheng, Yao Zhao · 26 de noviembre de 2025

  Existing deepfake detection methods heavily rely on static labeled datasets. However, with the proliferation of generative models, real-world scenarios are flooded with massive amounts of unlabeled fake face data from unknown sources. This presents a critical dilemma: detectors relying solely on exi…

• Training-Free Generation of Diverse and High-Fidelity Images via Prompt Semantic Space Optimization

  Debin Meng, Chen Jin, Zheng Gao, Yanran Li, Ioannis Patras, Georgios Tzimiropoulos · 26 de noviembre de 2025

  Image diversity remains a fundamental challenge for text-to-image diffusion models. Low-diversity models tend to generate repetitive outputs, increasing sampling redundancy and hindering both creative exploration and downstream applications. A primary cause is that generation often collapses toward …

• STARFlow-V: End-to-End Video Generative Modeling with Normalizing Flow

  Jiatao Gu, Ying Shen, Tianrong Chen, Laurent Dinh, Yuyang Wang, Miguel Angel Bautista, David Berthelot, Josh Susskind, Shuangfei Zhai · 26 de noviembre de 2025

  Normalizing flows (NFs) are end-to-end likelihood-based generative models for continuous data, and have recently regained attention with encouraging progress on image generation. Yet in the video generation domain, where spatiotemporal complexity and computational cost are substantially higher, stat…

• FunDiff: Diffusion Models over Function Spaces for Physics-Informed Generative Modeling

  Sifan Wang, Zehao Dou, Siming Shan, Tong-Rui Liu, Lu Lu · 26 de noviembre de 2025

  Recent advances in generative modeling -- particularly diffusion models and flow matching -- have achieved remarkable success in synthesizing discrete data such as images and videos. However, adapting these models to physical applications remains challenging, as the quantities of interest are contin…