Generative Adversarial Networks and Image Synthesis

Latest papers

• Conditional neural control variates for variance reduction in Bayesian inverse problems

  Ali Siahkoohi, Hyunwoo Oh · 26 February 2026

  Bayesian inference for inverse problems involves computing expectations under posterior distributions -- e.g., posterior means, variances, or predictive quantities -- typically via Monte Carlo (MC) estimation. When the quantity of interest varies significantly under the posterior, accurate estimates…

• Inference-time Alignment via Sparse Junction Steering

  Runyi Hu, Jie Zhang, Shiqian Zhao, Jiale Meng, Jiwei Li, Jason Zeng, Ming Wu, Michael Heinrich, Yonggang Wen, Tianwei Zhang · 26 February 2026

  Token-level steering has emerged as a pivotal approach for inference-time alignment, enabling fine grained control over large language models by modulating their output distributions without parameter updates. While effective, existing methods rely on dense intervention at every decoding step. This …

• Bayesian Generative Adversarial Networks via Gaussian Approximation for Tabular Data Synthesis

  Bahrul Ilmi Nasution, Mark Elliot, Richard Allmendinger · 26 February 2026

  Generative Adversarial Networks (GAN) have been used in many studies to synthesise mixed tabular data. Conditional tabular GAN (CTGAN) have been the most popular variant but struggle to effectively navigate the risk-utility trade-off. Bayesian GAN have received less attention for tabular data, but h…

• Beyond Static Artifacts: A Forensic Benchmark for Video Deepfake Reasoning in Vision Language Models

  Zheyuan Gu, Qingsong Zhao, Yusong Wang, Zhaohong Huang, Xinqi Li, Cheng Yuan, Jiaowei Shao, Chi Zhang, Xuelong Li · 26 February 2026

  Current Vision-Language Models (VLMs) for deepfake detection excel at identifying spatial artifacts but overlook a critical dimension: temporal inconsistencies in video forgeries. Adapting VLMs to reason about these dynamic cues remains a distinct challenge. To bridge this gap, we propose Forensic A…

• NESTOR: A Nested MOE-based Neural Operator for Large-Scale PDE Pre-Training

  Dengdi Sun, Xiaoya Zhou, Xiao Wang, Hao Si, Wanli Lyu, Jin Tang, Bin Luo · 26 February 2026

  Neural operators have emerged as an efficient paradigm for solving PDEs, overcoming the limitations of traditional numerical methods and significantly improving computational efficiency. However, due to the diversity and complexity of PDE systems, existing neural operators typically rely on a single…

• Provably Safe Generative Sampling with Constricting Barrier Functions

  Darshan Gadginmath, Ahmed Allibhoy, Fabio Pasqualetti · 26 February 2026

  Flow-based generative models, such as diffusion models and flow matching models, have achieved remarkable success in learning complex data distributions. However, a critical gap remains for their deployment in safety-critical domains: the lack of formal guarantees that generated samples will satisfy…

• The Design Space of Tri-Modal Masked Diffusion Models

  Louis Bethune, Victor Turrisi, Bruno Kacper Mlodozeniec, Pau Rodriguez Lopez, Lokesh Boominathan, Nikhil Bhendawade, Amitis Shidani, Joris Pelemans, Theo X. Olausson, Devon Hjelm, Paul Dixon, Joao Monteiro, Pierre Ablin, Vishnu Banna, Arno Blaas, Nick Henderson, Kari Noriy, Dan Busbridge, Josh Susskind, Marco Cuturi, Irina Belousova, Luca Zappella, Russ Webb, Jason Ramapuram · 26 February 2026

  Discrete diffusion models have emerged as strong alternatives to autoregressive language models, with recent work initializing and fine-tuning a base unimodal model for bimodal generation. Diverging from previous approaches, we introduce the first tri-modal masked diffusion model pretrained from scr…

• See and Fix the Flaws: Enabling VLMs and Diffusion Models to Comprehend Visual Artifacts via Agentic Data Synthesis

  Jaehyun Park, Minyoung Ahn, Minkyu Kim, Jonghyun Lee, Jae-Gil Lee, Dongmin Park · 25 February 2026

  Despite recent advances in diffusion models, AI generated images still often contain visual artifacts that compromise realism. Although more thorough pre-training and bigger models might reduce artifacts, there is no assurance that they can be completely eliminated, which makes artifact mitigation a…

• Latent-Augmented Discrete Diffusion Models

  Dario Shariatian, Alain Durmus, Umut Simsekli, Stefano Peluchetti · 25 February 2026

  Discrete diffusion models have emerged as a powerful class of models and a promising route to fast language generation, but practical implementations typically rely on factored reverse transitions that ignore cross-token dependencies and degrade performance in the few-step regime. We propose Latent-…

• MultiModalPFN: Extending Prior-Data Fitted Networks for Multimodal Tabular Learning

  Wall Kim, Chaeyoung Song, Hanul Kim · 25 February 2026

  Recently, TabPFN has gained attention as a foundation model for tabular data. However, it struggles to integrate heterogeneous modalities such as images and text, which are common in domains like healthcare and marketing, thereby limiting its applicability. To address this, we present the Multi-Moda…

• Selecting Optimal Variable Order in Autoregressive Ising Models

  Shiba Biswal, Marc Vuffray, Andrey Y. Lokhov · 25 February 2026

  Autoregressive models enable tractable sampling from learned probability distributions, but their performance critically depends on the variable ordering used in the factorization via complexities of the resulting conditional distributions. We propose to learn the Markov random field describing the …

• VINA: Variational Invertible Neural Architectures

  Shubhanshu Shekhar, Mohammad Javad Khojasteh, Ananya Acharya, Tony Tohme, Kamal Youcef-Toumi · 25 February 2026

  The distinctive architectural features of normalizing flows (NFs), notably bijectivity and tractable Jacobians, make them well-suited for generative modeling. Invertible neural networks (INNs) build on these principles to address supervised inverse problems, enabling direct modeling of both forward …

• The Diffusion Duality, Chapter II: $\Psi$-Samplers and Efficient Curriculum

  Justin Deschenaux, Caglar Gulcehre, Subham Sekhar Sahoo · 25 February 2026

  Uniform-state discrete diffusion models excel at few-step generation and guidance due to their ability to self-correct, making them preferred over autoregressive or Masked diffusion models in these settings. However, their sampling quality plateaus with ancestral samplers as the number of steps incr…

• Communication-Inspired Tokenization for Structured Image Representations

  Aram Davtyan, Yusuf Sahin, Yasaman Haghighi, Sebastian Stapf, Pablo Acuaviva, Alexandre Alahi, Paolo Favaro · 25 February 2026

  Discrete image tokenizers have emerged as a key component of modern vision and multimodal systems, providing a sequential interface for transformer-based architectures. However, most existing approaches remain primarily optimized for reconstruction and compression, often yielding tokens that capture…

• GENSR: Symbolic Regression Based in Equation Generative Space

  Qian Li, Yuxiao Hu, Juncheng Liu, Yuntian Chen · 25 February 2026

  Symbolic Regression (SR) tries to reveal the hidden equations behind observed data. However, most methods search within a discrete equation space, where the structural modifications of equations rarely align with their numerical behavior, leaving fitting error feedback too noisy to guide exploration…

• Echoes Over Time: Unlocking Length Generalization in Video-to-Audio Generation Models

  Christian Simon, MAsato Ishii, Wei-Yao Wang, Koichi Saito, Akio Hayakawa, Dongseok Shim, Zhi Zhong, Shuyang Cui, Shusuke Takahashi, Takashi Shibuya, Yuki Mitsufuji · 25 February 2026

  Scaling multimodal alignment between video and audio is challenging, particularly due to limited data and the mismatch between text descriptions and frame-level video information. In this work, we tackle the scaling challenge in multimodal-to-audio generation, examining whether models trained on sho…

• LESA: Learnable Stage-Aware Predictors for Diffusion Model Acceleration

  Peiliang Cai, Jiacheng Liu, Haowen Xu, Xinyu Wang, Chang Zou, Linfeng Zhang · 25 February 2026

  Diffusion models have achieved remarkable success in image and video generation tasks. However, the high computational demands of Diffusion Transformers (DiTs) pose a significant challenge to their practical deployment. While feature caching is a promising acceleration strategy, existing methods bas…

• Deep unfolding of MCMC kernels: scalable, modular & explainable GANs for high-dimensional posterior sampling

  Jonathan Spence, Tob\'ias I. Liaudat, Konstantinos Zygalakis, Marcelo Pereyra · 25 February 2026

  Markov chain Monte Carlo (MCMC) methods are fundamental to Bayesian computation, but can be computationally intensive, especially in high-dimensional settings. Push-forward generative models, such as generative adversarial networks (GANs), variational auto-encoders and normalising flows offer a comp…

• When Pretty Isn't Useful: Investigating Why Modern Text-to-Image Models Fail as Reliable Training Data Generators

  Krzysztof Adamkiewicz, Brian Moser, Stanislav Frolov, Tobias Christian Nauen, Federico Raue, Andreas Dengel · 25 February 2026

  Recent text-to-image (T2I) diffusion models produce visually stunning images and demonstrate excellent prompt following. But do they perform well as synthetic vision data generators? In this work, we revisit the promise of synthetic data as a scalable substitute for real training sets and uncover a …

• Momentum Guidance: Plug-and-Play Guidance for Flow Models

  Runlong Liao, Jian Yu, Baiyu Su, Chi Zhang, Lizhang Chen, Qiang Liu · 25 February 2026

  Flow-based generative models have become a strong framework for high-quality generative modeling, yet pretrained models are rarely used in their vanilla conditional form: conditional samples without guidance often appear diffuse and lack fine-grained detail due to the smoothing effects of neural net…

• PCA-VAE: Differentiable Subspace Quantization without Codebook Collapse

  Hao Lu, Onur C. Koyun, Yongxin Guo, Zhengjie Zhu, Abbas Alili, Metin Nafi Gurcan · 24 February 2026

  Vector-quantized autoencoders deliver high-fidelity latents but suffer inherent flaws: the quantizer is non-differentiable, requires straight-through hacks, and is prone to collapse. We address these issues at the root by replacing VQ with a simple, principled, and fully differentiable alternative: …

• Localized Concept Erasure in Text-to-Image Diffusion Models via High-Level Representation Misdirection

  Uichan Lee, Jeonghyeon Kim, Sangheum Hwang · 24 February 2026

  Recent advances in text-to-image (T2I) diffusion models have seen rapid and widespread adoption. However, their powerful generative capabilities raise concerns about potential misuse for synthesizing harmful, private, or copyrighted content. To mitigate such risks, concept erasure techniques have em…

• A Markovian View of Iterative-Feedback Loops in Image Generative Models: Neural Resonance and Model Collapse

  Vibhas Kumar Vats, David J. Crandall, Samuel Goree · 24 February 2026

  AI training datasets will inevitably contain AI-generated examples, leading to ``feedback'' in which the output of one model impacts the training of another. It is known that such iterative feedback can lead to model collapse, yet the mechanisms underlying this degeneration remain poorly understood.…

• When Pretty Isn't Useful: Investigating Why Modern Text-to-Image Models Fail as Reliable Training Data Generators

  Krzysztof Adamkiewicz, Brian Moser, Stanislav Frolov, Tobias Christian Nauen, Federico Raue, Andreas Dengel · 24 February 2026

  Recent text-to-image (T2I) diffusion models produce visually stunning images and demonstrate excellent prompt following. But do they perform well as synthetic vision data generators? In this work, we revisit the promise of synthetic data as a scalable substitute for real training sets and uncover a …

• Training-Free Generative Modeling via Kernelized Stochastic Interpolants

  Florentin Coeurdoux, Etienne Lempereur, Nathana\"el Cuvelle-Magar, Thomas Eboli, St\'ephane Mallat, Anastasia Borovykh, Eric Vanden-Eijnden · 24 February 2026

  We develop a kernel method for generative modeling within the stochastic interpolant framework, replacing neural network training with linear systems. The drift of the generative SDE is $\hat b_t(x) = \nabla\phi(x)^\top\eta_t$, where $\eta_t\in\R^P$ solves a $P\times P$ system computable from data, …