Generative Adversarial Networks and Image Synthesis

Latest papers

• Using Synthetic Data to estimate the True Error is theoretically and practically doable

  Hai Hoang Thanh, Duy-Tung Nguyen, Hung The Tran, Khoat Than · 4 November 2025

  Accurately evaluating model performance is crucial for deploying machine learning systems in real-world applications. Traditional methods often require a sufficiently large labeled test set to ensure a reliable evaluation. However, in many contexts, a large labeled dataset is costly and labor-intens…

• Cross-fluctuation phase transitions reveal sampling dynamics in diffusion models

  Sai Niranjan Ramachandran, Manish Krishan Lal, Suvrit Sra · 4 November 2025

  We analyse how the sampling dynamics of distributions evolve in score-based diffusion models using cross-fluctuations, a centered-moment statistic from statistical physics. Specifically, we show that starting from an unbiased isotropic normal distribution, samples undergo sharp, discrete transitions…

• Diluting Restricted Boltzmann Machines

  C. D\'iaz-Faloh, R. Mulet · 4 November 2025

  Recent advances in artificial intelligence have relied heavily on increasingly large neural networks, raising concerns about their computational and environmental costs. This paper investigates whether simpler, sparser networks can maintain strong performance by studying Restricted Boltzmann Machine…

• MotionStream: Real-Time Video Generation with Interactive Motion Controls

  Joonghyuk Shin, Zhengqi Li, Richard Zhang, Jun-Yan Zhu, Jaesik Park, Eli Schechtman, Xun Huang · 4 November 2025

  Current motion-conditioned video generation methods suffer from prohibitive latency (minutes per video) and non-causal processing that prevents real-time interaction. We present MotionStream, enabling sub-second latency with up to 29 FPS streaming generation on a single GPU. Our approach begins by a…

• Towards Multi-Fidelity Scaling Laws of Neural Surrogates in CFD

  Paul Setinek, Gianluca Galletti, Johannes Brandstetter · 4 November 2025

  Scaling laws describe how model performance grows with data, parameters and compute. While large datasets can usually be collected at relatively low cost in domains such as language or vision, scientific machine learning is often limited by the high expense of generating training data through numeri…

• Extremal Contours: Gradient-driven contours for compact visual attribution

  Reza Karimzadeh, Albert Alonso, Frans Zdyb, Julius B. Kirkegaard, Bulat Ibragimov · 4 November 2025

  Faithful yet compact explanations for vision models remain a challenge, as commonly used dense perturbation masks are often fragmented and overfitted, needing careful post-processing. Here, we present a training-free explanation method that replaces dense masks with smooth tunable contours. A star-c…

• Where and How to Perturb: On the Design of Perturbation Guidance in Diffusion and Flow Models

  Donghoon Ahn, Jiwon Kang, Sanghyun Lee, Minjae Kim, Jaewon Min, Wooseok Jang, Sangwu Lee, Sayak Paul, Susung Hong, Seungryong Kim · 4 November 2025

  Recent guidance methods in diffusion models steer reverse sampling by perturbing the model to construct an implicit weak model and guide generation away from it. Among these approaches, attention perturbation has demonstrated strong empirical performance in unconditional scenarios where classifier-f…

• LookSync: Large-Scale Visual Product Search System for AI-Generated Fashion Looks

  Pradeep M, Ritesh Pallod, Satyen Abrol, Muthu Raman, Ian Anderson · 4 November 2025

  Generative AI is reshaping fashion by enabling virtual looks and avatars making it essential to find real products that best match AI-generated styles. We propose an end-to-end product search system that has been deployed in a real-world, internet scale which ensures that AI-generated looks presente…

• Learning an Efficient Optimizer via Hybrid-Policy Sub-Trajectory Balance

  Yunchuan Guan, Yu Liu, Ke Zhou, Hui Li, Sen Jia, Zhiqi Shen, Ziyang Wang, Xinglin Zhang, Tao Chen, Jenq-Neng Hwang, Lei Li · 4 November 2025

  Recent advances in generative modeling enable neural networks to generate weights without relying on gradient-based optimization. However, current methods are limited by issues of over-coupling and long-horizon. The former tightly binds weight generation with task-specific objectives, thereby limiti…

• TRISKELION-1: Unified Descriptive-Predictive-Generative AI

  Nardeep Kumar, Arun Kanwar · 4 November 2025

  TRISKELION-1 is a unified descriptive-predictive-generative architecture that integrates statistical, mechanistic, and generative reasoning within a single encoder-decoder framework. The model demonstrates how descriptive representation learning, predictive inference, and generative synthesis can be…

• Vision Foundation Models Can Be Good Tokenizers for Latent Diffusion Models

  Tianci Bi, Xiaoyi Zhang, Yan Lu, Nanning Zheng · 4 November 2025

  The performance of Latent Diffusion Models (LDMs) is critically dependent on the quality of their visual tokenizer. While recent works have explored incorporating Vision Foundation Models (VFMs) via distillation, we identify a fundamental flaw in this approach: it inevitably weakens the robustness o…

• Calibrating and Rotating: A Unified Framework for Weight Conditioning in PEFT

  Da Chang, Peng Xue, Yu Li, Yongxiang Liu, Pengxiang Xu, Shixun Zhang · 4 November 2025

  Parameter-Efficient Fine-Tuning (PEFT) methods are crucial for adapting large pre-trained models. Among these, LoRA is considered a foundational approach. Building on this, the influential DoRA method enhances performance by decomposing weight updates into magnitude and direction. However, its under…

• FLoRA: Fused forward-backward adapters for parameter efficient fine-tuning and reducing inference-time latencies of LLMs

  Dhananjaya Gowda, Seoha Song, Junhyun Lee, Harshith Goka · 4 November 2025

  As the large language models (LLMs) grow in size each day, efficient training and fine-tuning has never been as important as nowadays. This resulted in the great interest in parameter efficient fine-tuning (PEFT), and effective methods including low-rank adapters (LoRA) has emerged. Although the var…

• Game-theoretic distributed learning of generative models for heterogeneous data collections

  Dmitrij Schlesinger, Boris Flach · 4 November 2025

  One of the main challenges in distributed learning arises from the difficulty of handling heterogeneous local models and data. In light of the recent success of generative models, we propose to meet this challenge by building on the idea of exchanging synthetic data instead of sharing model paramete…

• Demystifying MaskGIT Sampler and Beyond: Adaptive Order Selection in Masked Diffusion

  Satoshi Hayakawa, Yuhta Takida, Masaaki Imaizumi, Hiromi Wakaki, Yuki Mitsufuji · 3 November 2025

  Masked diffusion models have shown promising performance in generating high-quality samples in a wide range of domains, but accelerating their sampling process remains relatively underexplored. To investigate efficient samplers for masked diffusion, this paper theoretically analyzes the MaskGIT samp…

• BI-DCGAN: A Theoretically Grounded Bayesian Framework for Efficient and Diverse GANs

  Mahsa Valizadeh, Rui Tuo, James Caverlee · 3 November 2025

  Generative Adversarial Networks (GANs) are proficient at generating synthetic data but continue to suffer from mode collapse, where the generator produces a narrow range of outputs that fool the discriminator but fail to capture the full data distribution. This limitation is particularly problematic…

• Sparse Model Inversion: Efficient Inversion of Vision Transformers for Data-Free Applications

  Zixuan Hu, Yongxian Wei, Li Shen, Zhenyi Wang, Lei Li, Chun Yuan, Dacheng Tao · 3 November 2025

  Model inversion, which aims to reconstruct the original training data from pre-trained discriminative models, is especially useful when the original training data is unavailable due to privacy, usage rights, or size constraints. However, existing dense inversion methods attempt to reconstruct the en…

• Jasmine: A Simple, Performant and Scalable JAX-based World Modeling Codebase

  Mihir Mahajan, Alfred Nguyen, Franz Srambical, Stefan Bauer · 3 November 2025

  While world models are increasingly positioned as a pathway to overcoming data scarcity in domains such as robotics, open training infrastructure for world modeling remains nascent. We introduce Jasmine, a performant JAX-based world modeling codebase that scales from single hosts to hundreds of acce…

• Simplex-to-Euclidean Bijections for Categorical Flow Matching

  Bernardo Williams, Victor M. Yeom-Song, Marcelo Hartmann, Arto Klami · 3 November 2025

  We propose a method for learning and sampling from probability distributions supported on the simplex. Our approach maps the open simplex to Euclidean space via smooth bijections, leveraging the Aitchison geometry to define the mappings, and supports modeling categorical data by a Dirichlet interpol…

• Panprediction: Optimal Predictions for Any Downstream Task and Loss

  Sivaraman Balakrishnan, Nika Haghtalab, Daniel Hsu, Brian Lee, Eric Zhao · 3 November 2025

  Supervised learning is classically formulated as training a model to minimize a fixed loss function over a fixed distribution, or task. However, an emerging paradigm instead views model training as extracting enough information from data so that the model can be used to minimize many losses on many …

• MIRO: MultI-Reward cOnditioned pretraining improves T2I quality and efficiency

  Nicolas Dufour, Lucas Degeorge, Arijit Ghosh, Vicky Kalogeiton, David Picard · 31 October 2025

  Current text-to-image generative models are trained on large uncurated datasets to enable diverse generation capabilities. However, this does not align well with user preferences. Recently, reward models have been specifically designed to perform post-hoc selection of generated images and align them…

• SPARKE: Scalable Prompt-Aware Diversity and Novelty Guidance in Diffusion Models via RKE Score

  Mohammad Jalali, Haoyu Lei, Amin Gohari, Farzan Farnia · 31 October 2025

  Diffusion models have demonstrated remarkable success in high-fidelity image synthesis and prompt-guided generative modeling. However, ensuring adequate diversity in generated samples of prompt-guided diffusion models remains a challenge, particularly when the prompts span a broad semantic spectrum …

• BOLT-GAN: Bayes-Optimal Loss for Stable GAN Training

  Mohammadreza Tavasoli Naeini, Ali Bereyhi, Morteza Noshad, Ben Liang, Alfred O. Hero III · 30 October 2025

  We introduce BOLT-GAN, a simple yet effective modification of the WGAN framework inspired by the Bayes Optimal Learning Threshold (BOLT). We show that with a Lipschitz continuous discriminator, BOLT-GAN implicitly minimizes a different metric distance than the Earth Mover (Wasserstein) distance and …

• Symplectic Generative Networks (SGNs): A Hamiltonian Framework for Invertible Deep Generative Modeling

  Agnideep Aich, Ashit Aich · 30 October 2025

  We introduce the \emph{Symplectic Generative Network (SGN)}, a deep generative model that leverages Hamiltonian mechanics to construct an invertible, volume-preserving mapping between a latent space and the data space. By endowing the latent space with a symplectic structure and modeling data genera…

• Riemannian-Geometric Fingerprints of Generative Models

  Hae Jin Song, Laurent Itti · 29 October 2025

  Recent breakthroughs and rapid integration of generative models (GMs) have sparked interest in the problem of model attribution and their fingerprints. For instance, service providers need reliable methods of authenticating their models to protect their IP, while users and law enforcement seek to ve…