Generative Adversarial Networks and Image Synthesis

Latest papers

• Rethinking Video Generation Model for the Embodied World

  Yufan Deng, Zilin Pan, Hongyu Zhang, Xiaojie Li, Ruoqing Hu, Yufei Ding, Yiming Zou, Yan Zeng, Daquan Zhou · 22 January 2026

  Video generation models have significantly advanced embodied intelligence, unlocking new possibilities for generating diverse robot data that capture perception, reasoning, and action in the physical world. However, synthesizing high-quality videos that accurately reflect real-world robotic interact…

• Beyond Error-Based Optimization: Experience-Driven Symbolic Regression with Goal-Conditioned Reinforcement Learning

  Jianwen Sun, Xinrui Li, Fuqing Li, Xiaoxuan Shen · 22 January 2026

  Symbolic Regression aims to automatically identify compact and interpretable mathematical expressions that model the functional relationship between input and output variables. Most existing search-based symbolic regression methods typically rely on the fitting error to inform the search process. Ho…

• GAT-NeRF: Geometry-Aware-Transformer Enhanced Neural Radiance Fields for High-Fidelity 4D Facial Avatars

  Zhe Chang, Haodong Jin, Ying Sun, Yan Song, Hui Yu · 22 January 2026

  High-fidelity 4D dynamic facial avatar reconstruction from monocular video is a critical yet challenging task, driven by increasing demands for immersive virtual human applications. While Neural Radiance Fields (NeRF) have advanced scene representation, their capacity to capture high-frequency facia…

• Meta Flow Maps enable scalable reward alignment

  Peter Potaptchik, Adhi Saravanan, Abbas Mammadov, Alvaro Prat, Michael S. Albergo, Yee Whye Teh · 22 January 2026

  Controlling generative models is computationally expensive. This is because optimal alignment with a reward function--whether via inference-time steering or fine-tuning--requires estimating the value function. This task demands access to the conditional posterior $p_{1|t}(x_1|x_t)$, the distribution…

• Field-Space Autoencoder for Scalable Climate Emulators

  Johannes Meuer, Maximilian Witte, \'Eti\'enne Pl\'esiat, Thomas Ludwig, Christopher Kadow · 22 January 2026

  Kilometer-scale Earth system models are essential for capturing local climate change. However, these models are computationally expensive and produce petabyte-scale outputs, which limits their utility for applications such as probabilistic risk assessment. Here, we present the Field-Space Autoencode…

• Beyond the Dirac Delta: Mitigating Diversity Collapse in Reinforcement Fine-Tuning for Versatile Image Generation

  Jinmei Liu, Haoru Li, Zhenhong Sun, Chaofeng Chen, Yatao Bian, Bo Wang, Daoyi Dong, Chunlin Chen, Zhi Wang · 21 January 2026

  Reinforcement learning (RL) has emerged as a powerful paradigm for fine-tuning large-scale generative models, such as diffusion and flow models, to align with complex human preferences and user-specified tasks. A fundamental limitation remains \textit{the curse of diversity collapse}, where the obje…

• Context and Transcripts Improve Detection of Deepfake Audios of Public Figures

  Chongyang Gao, Marco Postiglione, Julian Baldwin, Natalia Denisenko, Isabel Gortner, Luke Fosdick, Chiara Pulice, Sarit Kraus, V. S. Subrahmanian · 21 January 2026

  Humans use context to assess the veracity of information. However, current audio deepfake detectors only analyze the audio file without considering either context or transcripts. We create and analyze a Journalist-provided Deepfake Dataset (JDD) of 255 public deepfakes which were primarily contribut…

• Scalable Equilibrium Sampling with Sequential Boltzmann Generators

  Charlie B. Tan, Avishek Joey Bose, Chen Lin, Leon Klein, Michael M. Bronstein, Alexander Tong · 21 January 2026

  Scalable sampling of molecular states in thermodynamic equilibrium is a long-standing challenge in statistical physics. Boltzmann generators tackle this problem by pairing normalizing flows with importance sampling to obtain uncorrelated samples under the target distribution. In this paper, we exten…

• TwoHead-SwinFPN: A Unified DL Architecture for Synthetic Manipulation, Detection and Localization in Identity Documents

  Chan Naseeb, Adeel Ashraf Cheema, Hassan Sami, Tayyab Afzal, Muhammad Omair, Usman Habib · 21 January 2026

  The proliferation of sophisticated generative AI models has significantly escalated the threat of synthetic manipulations in identity documents, particularly through face swapping and text inpainting attacks. This paper presents TwoHead-SwinFPN, a unified deep learning architecture that simultaneous…

• Tensorization of neural networks for improved privacy and interpretability

  Jos\'e Ram\'on Pareja Monturiol, Alejandro Pozas-Kerstjens, David P\'erez-Garc\'ia · 21 January 2026

  We present a tensorization algorithm for constructing tensor train/matrix product state (MPS) representations of functions, drawing on sketching and cross interpolation ideas. The method only requires black-box access to the target function and a small set of sample points defining the domain of int…

• NoiseFormer -- Noise Diffused Symmetric Attention Transformer

  Phani Kumar, Nyshadham, Jyothendra Varma, Polisetty V R K, Aditya Rathore · 21 January 2026

  Transformer architecture has been very successful long runner in the field of Deep Learning (DL) and Large Language Models (LLM) because of its powerful attention-based learning and parallel-natured architecture. As the models grow gigantic in terms of memory footprint, difficulties in fitting the m…

• Transport Based Mean Flows for Generative Modeling

  Elaheh Akbari, Ping He, Ahmadreza Moradipari, Yikun Bai, Soheil Kolouri · 21 January 2026

  Flow-matching generative models have emerged as a powerful paradigm for continuous data generation, achieving state-of-the-art results across domains such as images, 3D shapes, and point clouds. Despite their success, these models suffer from slow inference due to the requirement of numerous sequent…

• ESPLoRA: Enhanced Spatial Precision with Low-Rank Adaption in Text-to-Image Diffusion Models for High-Definition Synthesis

  Andrea Rigo, Luca Stornaiuolo, Mauro Martino, Bruno Lepri, Nicu Sebe · 21 January 2026

  Diffusion models have revolutionized text-to-image (T2I) synthesis, producing high-quality, photorealistic images. However, they still struggle to properly render the spatial relationships described in text prompts. To address the lack of spatial information in T2I generations, existing methods typi…

• Joint Discriminative-Generative Modeling via Dual Adversarial Training

  Xuwang Yin, Claire Zhang, Julie Steele, Nir Shavit, Tony T. Wang · 21 January 2026

  Simultaneously achieving robust classification and high-fidelity generative modeling within a single framework presents a significant challenge. Hybrid approaches, such as Joint Energy-Based Models (JEM), interpret classifiers as EBMs but are often limited by the instability and poor sample quality …

• Discriminant Learning-based Colorspace for Blade Segmentation

  Ra\"ul P\'erez-Gonzalo, Andreas Espersen, Antonio Agudo · 21 January 2026

  Suboptimal color representation often hinders accurate image segmentation, yet many modern algorithms neglect this critical preprocessing step. This work presents a novel multidimensional nonlinear discriminant analysis algorithm, Colorspace Discriminant Analysis (CSDA), for improved segmentation. E…

• Mixture of Distributions Matters: Dynamic Sparse Attention for Efficient Video Diffusion Transformers

  Yuxi Liu, Yipeng Hu, Zekun Zhang, Kunze Jiang, Kun Yuan · 21 January 2026

  While Diffusion Transformers (DiTs) have achieved notable progress in video generation, this long-sequence generation task remains constrained by the quadratic complexity inherent to self-attention mechanisms, creating significant barriers to practical deployment. Although sparse attention methods a…

• SlimDiff: Training-Free, Activation-Guided Hands-free Slimming of Diffusion Models

  Arani Roy, Shristi Das Biswas, Kaushik Roy · 21 January 2026

  Diffusion models (DMs), lauded for their generative performance, are computationally prohibitive due to their billion-scale parameters and iterative denoising dynamics. Existing efficiency techniques, such as quantization, timestep reduction, or pruning, offer savings in compute, memory, or runtime …

• Lightning Fast Caching-based Parallel Denoising Prediction for Accelerating Talking Head Generation

  Jianzhi Long, Wenhao Sun, Rongcheng Tu, Dacheng Tao · 21 January 2026

  Diffusion-based talking head models generate high-quality, photorealistic videos but suffer from slow inference, limiting practical applications. Existing acceleration methods for general diffusion models fail to exploit the temporal and spatial redundancies unique to talking head generation. In thi…

• An Elementary Approach to Scheduling in Generative Diffusion Models

  Qiang Sun, H. Vincent Poor, Wenyi Zhang · 21 January 2026

  An elementary approach to characterizing the impact of noise scheduling and time discretization in generative diffusion models is developed. Considering a simplified model where the source distribution is multivariate Gaussian with a given covariance matrix, the explicit closed-form evolution trajec…

• Generating metamers of human scene understanding

  Ritik Raina, Abe Leite, Alexandros Graikos, Seoyoung Ahn, Dimitris Samaras, Gregory J. Zelinsky · 21 January 2026

  Human vision combines low-resolution "gist" information from the visual periphery with sparse but high-resolution information from fixated locations to construct a coherent understanding of a visual scene. In this paper, we introduce MetamerGen, a tool for generating scenes that are aligned with lat…

• When Are Two Scores Better Than One? Investigating Ensembles of Diffusion Models

  Rapha\"el Razafindralambo, R\'emy Sun, Fr\'ed\'eric Precioso, Damien Garreau, Pierre-Alexandre Mattei · 19 January 2026

  Diffusion models now generate high-quality, diverse samples, with an increasing focus on more powerful models. Although ensembling is a well-known way to improve supervised models, its application to unconditional score-based diffusion models remains largely unexplored. In this work we investigate w…

• Your One-Stop Solution for AI-Generated Video Detection

  Long Ma, Zihao Xue, Yan Wang, Zhiyuan Yan, Jin Xu, Xiaorui Jiang, Haiyang Yu, Yong Liao, Zhen Bi · 19 January 2026

  Recent advances in generative modeling can create remarkably realistic synthetic videos, making it increasingly difficult for humans to distinguish them from real ones and necessitating reliable detection methods. However, two key limitations hinder the development of this field. \textbf{From th…

• Fine-Tuning Diffusion Models via Intermediate Distribution Shaping

  Gautham Govind Anil, Shaan Ul Haque, Nithish Kannen, Dheeraj Nagaraj, Sanjay Shakkottai, Karthikeyan Shanmugam · 16 January 2026

  Diffusion models are widely used for generative tasks across domains. While pre-trained diffusion models effectively capture the training data distribution, it is often desirable to shape these distributions using reward functions to align with downstream applications. Policy gradient methods, such …

• In-Context Operator Learning on the Space of Probability Measures

  Frank Cole, Dixi Wang, Yineng Chen, Yulong Lu, Rongjie Lai · 16 January 2026

  We introduce \emph{in-context operator learning on probability measure spaces} for optimal transport (OT). The goal is to learn a single solution operator that maps a pair of distributions to the OT map, using only few-shot samples from each distribution as a prompt and \emph{without} gradient updat…

• Discrete Feynman-Kac Correctors

  Mohsin Hasan, Viktor Ohanesian, Artem Gazizov, Yoshua Bengio, Al\'an Aspuru-Guzik, Roberto Bondesan, Marta Skreta, Kirill Neklyudov · 16 January 2026

  Discrete diffusion models have recently emerged as a promising alternative to the autoregressive approach for generating discrete sequences. Sample generation via gradual denoising or demasking processes allows them to capture hierarchical non-sequential interdependencies in the data. These custom p…