Generative Adversarial Networks and Image Synthesis

Derniers papiers

• HaineiFRDM: Structure-Preserving Diffusion for Film Restoration under Fast Motion and Diverse Defects

  Rongji Xun, Junjie Yuan, Zhongjie Wang · 23 juin 2026

  Existing film-restoration methods frequently fail under fast motion, producing limb disappearance and structural distortion due to inaccurate motion modeling. Moreover, high-resolution restoration under spatially-persistent and mixed defects remains insufficiently studied. We propose HaineiFRDM, a F…

• Error Highways: Scaling Predictive Coding to Very Deep Networks

  Amirhossein Mohammadi, Alexander G. Ororbia · 23 juin 2026

  Predictive coding networks (PCNs) offer a biologically-plausible, local-learning alternative to back-propagation of errors (backprop). Nevertheless, they have remained largely confined to shallow architectures and evaluated on simple machine intelligence benchmarks. A central obstacle to scaling PCN…

• Semantic Browsing: Controllable Diversity for Image Generation

  Sara Dorfman, Maya Vishnevsky, Omer Dahary, Or Patashnik, Daniel Cohen-Or · 23 juin 2026

  Modern text-to-image models excel in visual fidelity and prompt adherence. However, this strict adherence comes at the cost of diversity: generated samples tend to collapse into a single visual interpretation. Existing methods to improve diversity produce outputs driven by incidental variations rath…

• Tapered Language Models

  Reza Bayat, Ali Behrouz, Aaron Courville · 23 juin 2026

  Modern language models, including transformer, recurrent, and memory-based variants, share a common chassis: a stack of identical layers in which parameters are allocated uniformly across depth. This is a default inherited from the original transformer and largely unchanged since, yet a growing body…

• Geometric and Information Compression of Representations in Deep Learning

  Linara Adilova, Henning Petzka, Asja Fischer, Bernhard C. Geiger · 23 juin 2026

  Deep neural networks transform input data into latent representations that support a wide range of downstream tasks. These representations can be characterized along information-theoretic and geometric dimensions, but their relationship remains poorly understood. A central open question is whether l…

• Encoder-Decoder Manifold Alignment for Idempotent Generation

  Dareen Alharthi, Abdul Waheed, Bhiksha Raj · 23 juin 2026

  Recently, several learning paradigms have been introduced to enforce idempotency in generative models. The goal is to ensure that repeated application of a model leaves samples unchanged once they lie on the target data manifold. In practice, however, many of these approaches fail to achieve exact f…

• Unsupervised Disentanglement Without Compromises : How Functional Orthogonality Enforces Identifiability

  Mathieu Cyrille Simon, Pascal Frossard, Christophe De Vleeschouwer · 23 juin 2026

  This paper explores unsupervised disentangled representation learning from a functional perspective. We define latent concepts as factors that influence observations through locally orthogonal directions, formalized as an orthogonality constraint on the Jacobian of the generative mapping. We prove t…

• DataClaw0: Agentic Tailoring Multimodal Data from Raw Streams

  Cong Wan, Zeyu Guo, Zijian Cai, Jiangyang Li, SongLin Dong, Lin Peng, Xiangyang Luo, Zhiheng Ma, Yihong Gong · 23 juin 2026

  Massive unstructured multimodal streams suffer from high "data entropy," impeding both efficient human knowledge acquisition and high-quality AI post-training. Existing passive annotation paradigms, heavily reliant on heuristic rules or general VLMs, are costly, monotonous, and fail to unlock the de…

• Data Evolution by Wittgenstein's Rule Following

  Aydin Ghojogh, Benyamin Ghojogh · 23 juin 2026

  This paper introduces Wittgenstein's Rule Following (WRF) data evolution, a framework in philomatics for evolving or generating a new dataset from a sequence of previously observed datasets. The method is inspired by Ludwig Wittgenstein's rule-following considerations and his notion of family resemb…

• DiT-Reward: Generative Representations for Text-to-Image Reward Modeling

  Yuanming Yang, Guoqing Ma, Bo Wang, Yuan Zhang, Wei Tang, Chenyi Li, Haoyang Huang, Nan Duan · 23 juin 2026

  Can representations learned for image generation also support the evaluation of generated images? We study text-to-image reward prediction as a downstream task of generative representation learning. To this end, we introduce DiT-Reward, which converts a pretrained text-to-image Diffusion Transformer…

• Retrieval-Augmented Anatomical Guidance for Text-to-CT Generation

  Daniele Molino, Camillo Maria Caruso, Paolo Soda, Valerio Guarrasi · 23 juin 2026

  Text-conditioned generative models for volumetric medical imaging provide semantic control but lack explicit anatomical guidance, often resulting in outputs that are spatially ambiguous or anatomically inconsistent. In contrast, structure-driven methods ensure strong anatomical consistency but typic…

• CultureScore: Evaluating Cultural Faithfulness in Video Generation Models

  Anku Rani, Wei Dai, Shravan Nayak, Pattie Maes, Mahdi M. Kalayeh, Paul Pu Liang · 23 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…

• Safe Few-Step Generation via Velocity Editing

  Yujin Choi, Jaehong Yoon · 23 juin 2026

  Flow matching has recently emerged as a strong paradigm for state-of-the-art text-to-image (T2I) generation, enabling high-quality generation with a small number of sampling steps. As these models are increasingly integrated into real-world applications, ensuring safe and non-sensitive content gener…

• Causal Variational Deep Embedding: A Family of Interventional Generators for Confounded Images

  Jingyuan Chen, Kangrui Ruan, Junzhe Zhang · 23 juin 2026

  Deep generative models reproduce the observational distribution of their training data, inheriting any spurious associations it contains. A common source is an unobserved confounder that shapes both an attribute the user wants to control at sampling time and an attribute expected to vary in response…

• MindAlign: Decoding Inner Speech from fMRI Signals via Multimodal Embedding Alignment under Limited Data

  Muxuan Liu, Ichiro Kobayashi, Satoshi Nishida · 23 juin 2026

  Decoding inner speech from non-invasive brain signals remains a fundamental challenge due to the absence of overt linguistic output, limited training data, and large inter-subject variability. Existing brain-to-text approaches often rely on task-specific decoder fine-tuning, which restricts scalabil…

• TailorMind: Towards Preference-Aligned Multimodal Content Generation

  Hengji Zhou, Ye Liu, Yufeng Liu, Si Wu, Lianghao Xia, Liqiang Nie · 23 juin 2026

  Personalized content systems depend on available UGC and struggle when suitable content is absent, delayed, or costly to create. Although multimodal generators can synthesize content on demand, how to translate behavioral traces into generation-ready preferences remains underexplored. We study perso…

• TriMotion: Modality-Agnostic Camera Control for Video Generation

  Seunghyun Shin, Jifei Song, Wooseok Jeon, Hae-Gon Jeon, Jiankang Deng · 23 juin 2026

  Camera motion control is essential for directing viewpoint changes in generative systems. However, existing methods typically condition the generation process on a single specific modality, such as explicit pose trajectories or reference videos, limiting their ability to support heterogeneous user i…

• GroundShot: Visually Consistent Multi-Shot Long Video Generation via Entity-Grounded Shot Scheduling

  Yixuan Lai, Tianjia Shao, Kun Zhou, Weijia Dou, Siyu Zhu, Jingdong Wang · 23 juin 2026

  Generating visually consistent multi-shot videos remains an open challenge. As videos span more shots, inconsistencies can accumulate across shots, causing entities that reappear across shots -- characters, objects, and locations -- to drift away from how they first appear. We observe that viewers j…

• Training-Free Semantic Correction for Autoregressive Visual Models

  Junhao Chen, Chanyu Zhu, Zheqi Lv, Keting Yin, Shengyu Zhang · 23 juin 2026

  Autoregressive visual models (AVMs) based on next-scale prediction have emerged as a prominent paradigm for image and video synthesis. However, decomposing the generation process into discrete scales with varying granularities in AVM makes semantic errors difficult to identify and correct, thereby u…

• On the Sparsity-Storage-Accuracy Tradeoff in Parsimoniously Activated Dictionary Learning

  Zihui Zhao, Yuanbo Tang, Yang Li · 23 juin 2026

  Dictionary learning has long been studied from both optimization and probabilistic perspectives. While formulations with element-wise sparsity regularization (e.g., L1-based sparse coding) admit well-established probabilistic interpretations, many structured variants that impose global constraints l…

• Understanding Parallel Samplers in Masked Diffusion via Random Walks on Graphs

  Vansh Bansal, Cho Cholyeon, Syamantak Kumar, Sujay Sanghavi, Purnamrita Sarkar · 23 juin 2026

  In this paper, we propose using random walks on graphs as a verifiable sandbox to study different parallel sampling strategies in masked diffusion models (MDMs). We train an MDM on random walk samples from a fixed graph. The graph or the transition kernel is never shown to the model explicitly and p…

• ScalingAttention: Discovering Intrinsic Sparse Attention Topology for Video Diffusion Transformers

  Ruiliang Zhou, Xuecheng Wu, Kang He, Guangyun Han, Bin Liu, Qinqin Chen, Wende Xu, Qingjie Zhao, Chengru Song · 23 juin 2026

  While Diffusion Transformers (DiTs) have revolutionized high-fidelity video generation, their reliance on 3D full attention creates a quadratic computational bottleneck. Existing sparse methods face a dilemma: dynamic pruning suffers from prohibitive runtime overhead and memory fragmentation, while …

• Balancing Performance and Diversity in GRPO Autoregressive Text-to-Image Post-Training

  Yuanhao Chiang, Hongbo Duan, Chunru Yang, Jiahua Pei, Yi Liu, Xueqian Wang · 23 juin 2026

  Autoregressive text-to-image (T2I) generation has recently advanced rapidly, yet aligning generated images with human preferences remains challenging. GRPO-style online reinforcement learning provides an effective framework; however, existing methods typically treat reference-policy divergence as fi…

• Hierarchical Concept-to-Appearance Guidance for Multi-Subject Image Generation

  Yijia Xu, Zihao Wang, Haokun Gui, Jinshi Cui · 23 juin 2026

  Multi-subject image generation aims to synthesize images that faithfully preserve the identities of multiple reference subjects while following textual instructions. However, existing methods often suffer from identity inconsistency and limited compositional control, as they rely on diffusion models…

• One-Step Flow Matching for Generative Modeling of Path-Dependent Physical Fields

  Yijing Zhou, Jasmin Jelovica · 23 juin 2026

  Physical simulations for intricate geometries with path-dependent constitutive models face difficulties due to the enormous computational cost they require. Recently, the emergence of generative AI models, which succeed in image and video synthesis tasks, has provided a promise to further improve si…