Generative Adversarial Networks and Image Synthesis

Derniers papiers

• Smoothing Dark Areas in Molecular Latent Diffusion

  Xi Wang, Jiahan Li, Yuxuan Xia, Yingcheng Wu, Shaoyi Zheng, Shengjie Wang · 15 juin 2026

  Latent diffusion is a promising framework for scalable 3D molecular generation, but it requires a latent space that remains smooth, valid, and navigable beyond posterior samples. Existing molecular VAEs, however, are typically learned through reconstruction-based objectives, which do not guarantee s…

• CineOrchestra: Unified Entity-Centric Conditioning for Cinematic Video Generation

  Sharath Girish, Tsai-Shien Chen, Zhikang Dong, Mukesh Singhal, Hao Chen, Sergey Tulyakov, Aliaksandr Siarohin · 15 juin 2026

  Cinematic video depicts multiple subjects acting or interacting at specific moments, captured with deliberate camera movement, and stitched together by shot transitions. Together, these elements demand a level of fine-grained control beyond current text-to-video models. Existing work addresses each …

• SuperThoughts: Reasoning Tokens in Superposition

  Zheyang Xiong, Shivam Garg, Max Yu, Vaishnavi Shrivastava, Haoyu Zhao, Anastasios Kyrillidis, Dimitris Papailiopoulos · 15 juin 2026

  Long Chain-of-Thought (CoT) reasoning improves LLM problem-solving but is computationally expensive due to sequential token generation. While recent works explore reasoning in continuous latent spaces to bypass discrete token generation, they often struggle with training stability and fail to scale …

• Deep Spectral Learning of Embedded Latent Transfer Operators for Stochastic Dynamical Systems

  Ryogo Tanaka, Yoshinobu Kawahara · 15 juin 2026

  We propose a spectral learning method for stochastic nonlinear dynamical systems represented with embedded latent transfer operators in deep feature spaces. We instantiate the method as Deep Spectral Encoder (DSE), an operator-based latent state-space model in which a time-invariant neural encoder i…

• Pix2Pix-Hybrid: Structure-Guided Conditional Synthesis of Hajj Crowd Images with Multi-Channel Conditioning and Weak Attribute Supervision

  Amirah F. Alshammari, Bander A. Alzahrani, Nahed A. Alowidi · 15 juin 2026

  Developing accurate crowd-counting models for Hajj pilgrimage scenes remains challenging because domain-specific annotated images are scarce and data collection during large gatherings raises privacy concerns. To address these limitations, this paper proposes Pix2Pix-Hybrid (P2P-H), a hybrid conditi…

• Conditioning Matters: Stabilizing Inversion and Attention in Diffusion Image Editing

  Zheyuan Zhan, Hongchen Li, Can Wang, Yinfei Ma, Mingzhen Huang, Ruoshi Bai, Jiawei Chen, Siwei Lyu, Defang Chen · 15 juin 2026

  Inversion-based image editing offers flexible and training-free control but still struggles with inversion accuracy and the trade-off between editing fidelity and background preservation. While recent methods improve inversion formulations or attention interactions, the role of textual conditioning …

• HiLo-Token: Input-Adaptive High-Low Frequency Token Compression for Efficient Image Editing

  Haoran You, Yotam Nitzan, Lingzhi Zhang, Yifan Gong, Mang-Tik Chiu, Connelly Barnes, Yan Kang, Yuqian Zhou, Eli Shechtman, Sohrab Amirghodsi · 15 juin 2026

  Creative image editing tools, such as Photoshop's Remove or Generative Fill buttons, are central to everyday customer use and account for a major share of traffic in Photoshop and Lightroom. However, current generative AI models face significant latency challenges, which become even more pronounced …

• HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers

  Guozhen Zhang, Xuerui Qiu, Yutao Cui, Tianhui Song, Changlin Li, Junzhe Li, Tao Huang, Xiao Zhang, Yang Li, Jianbing Wu, Miles Yang, Zhao Zhong, Liefeng Bo, Limin Wang · 12 juin 2026

  Holistic visual tokenizers are fundamental to unified multimodal models (UMMs) as they map diverse visual inputs into a unified representation space. In this paper, we present HYDRA-X, the first UMM that unifies image and video tokenization within a single Vision Transformer (ViT). Our design is dri…

• SmartFont: Dynamic Condition Allocation for Few-Shot Font Generation

  Zian Yang, Zixin Wang · 12 juin 2026

  Few-shot font generation simultaneously requires global structural completeness and fine-grained local style fidelity. Existing methods usually either rely on global content-style modeling, which is robust but imperfectly disentangled, or emphasize component/local modeling, which captures fine detai…

• Towards More General Control of Diffusion Models Using Jeffrey Guidance

  Rapha\"el Razafindralambo, R\'emy Sun, Fr\'ed\'eric Precioso, Jes Frellsen, Pierre-Alexandre Mattei · 12 juin 2026

  A key strength of diffusion models lies in their flexibility, since their outputs can be controlled at sampling time through guidance. However, beyond simple cases such as conditional sampling, the target distribution is often left implicit, defined only through a sampling rule or a heuristic energy…

• OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data

  Jiwen Liu, Shujuan Li, Zhixue Fang, Xiaohan Li, Yan Zhou, Zijie Meng, Zhimin Zhang, Yawen Luo, Guoxin Zhang, Yu-Shen Liu, Pengfei Wan · 12 juin 2026

  Cloning camera motion from reference videos is an important task in video generation, as videos provide intuitive and precise control. Existing methods either directly use parametric representations that fail to handle multi-shot generation or synthesize cross-paired data, which suffer from data sca…

• EPIG: Emotion-Based Prompting for Personalised Image Generation

  Emna Othmen, Mohamed Yassine Landolsi, Lotfi Ben Romdhane · 12 juin 2026

  Text-to-image diffusion models have achieved impressive results in synthesizing high-quality images from natural language prompts. However, commonly used prompting strategies remain relatively generic, limiting the model's ability to accurately express emotional intent and nuanced affective attribut…

• Two-Layer Linear Auto-Regressive Models Estimate Latent States

  Yahya Sattar, Sunmook Choi, Leo Maynard-Zhang, Yassir Jedra, Maryam Fazel, Sarah Dean · 12 juin 2026

  Auto-regressive models have emerged as powerful tools for sequential data, from language to video. Understanding how and why these models learn latent representations remains an open theoretical question. In this work, we demonstrate that when trained by empirical risk minimization on data from part…

• Unstable Features, Reproducible Subspaces: Understanding Seed Dependence in Sparse Autoencoders

  Gleb Gerasimov, Timofei Rusalev, Nikita Balagansky, Daniil Laptev, Vadim Kurochkin, Daniil Gavrilov · 11 juin 2026

  Sparse autoencoders (SAEs) are widely used to interpret neural network representations, but their utility depends on whether the learned features are reproducible across training runs. We study this question through \emph{feature stability}: for each SAE feature, we estimate the probability that a s…

• MultiToP: Learning to Patch Visual Tokens to Mitigate Hallucinations in Video Large Multimodal Models

  Yuansheng Gao, Wenbin Xing, Jiahao Yuan, Kaiwen Zhou, Han Bao, Zonghui Wang, Wenzhi Chen · 11 juin 2026

  Video Large Multimodal Models have achieved remarkable progress in video understanding, yet they remain prone to hallucinations, where generated responses are not faithfully supported by the input video. In this paper, we propose MultiToP, a multimodal-context-aware visual token patching framework t…

• A New Perspective on Precision and Recall for Generative Models

  Benjamin Sykes (Unicaen, Ensicaen, Greyc), Lo\"ic Simon (Unicaen, Ensicaen, Greyc), Julien Rabin (Unicaen, Ensicaen, Greyc), Jalal Fadili (Unicaen, Ensicaen, Greyc) · 11 juin 2026

  With the recent success of generative models in image and text, the question of their evaluation has recently gained a lot of attention. While most methods from the state of the art rely on scalar metrics, the introduction of Precision and Recall (PR) for generative model has opened up a new avenue …

• Physics-informed generative AI for semiconductor manufacturing: Enforcing hard physical constraints in generative models by construction

  Yaser Mike Banad, Sarah Sharif · 11 juin 2026

  Generative models are increasingly used to propose designs, data, and control actions for physical systems, yet many such systems are governed by hard physical constraints rather than by perceptual plausibility. Semiconductor manufacturing provides a demanding test case: generated masks, layouts, sy…

• What Uncertainties Do We Need for Dynamical Systems?

  Yusuf Sale, Christopher B\"ulte, Felix Czaja, Joshua Stiller, Eyke H\"ullermeier · 11 juin 2026

  The distinction between aleatoric and epistemic uncertainty has received considerable attention in machine learning research, mainly in the context of supervised learning but also in other settings such as generative modeling. In this paper, we offer a machine learning perspective on uncertainty mod…

• AnchorEdit: Maintaining Temporal Consistency in Multi-turn Image Editing via Causal Memory

  Hang Xu, Xiaoxiao Ma, Guohui Zhang, Yu Hu, Siming Fu, Jie Huang, Lin Song, Haoyang Huang, Nan Duan, Feng Zhao · 11 juin 2026

  Multi-turn image editing is essential for iterative design, yet current models often struggle with identity drift and error accumulation over successive steps. While existing research leverages video priors for consistency, their reliance on bidirectional attention is fundamentally misaligned with t…

• ARGUS: Stacked Multi-View Identity Mosaic Injection for Subject-Preserving Video Generation

  Zijie Meng, Jiwen Liu, Yufei Liu, Chengzhuo Tong, Xiaoqiang Liu, Yuanxing Zhang, Yulong Xu, Pengfei Wan · 11 juin 2026

  Subject-preserving video generation is not solved by frontal-face similarity alone: a generated person must remain recognizable across motion, large viewpoint changes, expression shifts, occlusion, scale variation, and conflicts among text, first-frame, and identity references. We argue that the cen…

• Holding the FP8 Quality Ceiling at 8-Bit Weights and Activations: INT8 and GGUF Post-Training Quantization of Ideogram 4.0 for Consumer GPUs

  Deep Gandhi, Ali Asaria, Tony Salomone · 11 juin 2026

  Post-training quantization lets large text-to-image diffusion transformers run on consumer GPUs, yet the hardware-specific trade-offs are seldom measured directly. We quantize Ideogram 4.0 - a 9.3B flow-matching diffusion transformer (DiT), shipped as two separate-weight copies of a single-stream 34…

• It\^o maps for any-step SDEs

  Zhengkai Pan, Peter Potaptchik, Wenxi Yao, Michael S. Albergo, Jakiw Pidstrigach · 10 juin 2026

  Recent one-step generative models accelerate sampling by learning deterministic flow maps of the underlying dynamics. These methods rely on learning from ordinary differential equations, leaving open how to define an exact distillation procedure for stochastic dynamics. We introduce the It\^o map, a…

• Few-step Generative Models as Lossy Compression

  Fuma Kimishima, Jinjia Zhou · 10 juin 2026

  DiffC provides a principled way to reuse pre-trained diffusion models for lossy compression, but its encoding and decoding procedures remain slow because they require many discretized forward and reverse steps. We study whether few-step generative models -- Rectified Flow, Consistency Trajectory Mod…

• The Emergence of Reproducibility and Generalizability in Diffusion Models

  Huijie Zhang, Jinfan Zhou, Yifu Lu, Minzhe Guo, Peng Wang, Liyue Shen, Qing Qu · 10 juin 2026

  In this work, we investigate an intriguing and prevalent phenomenon of diffusion models which we term as "consistent model reproducibility": given the same starting noise input and a deterministic sampler, different diffusion models often yield remarkably similar outputs. We confirm this phenomenon …

• Exploring the Design Space of Reward Backpropagation for Flow Matching

  Ruoyu Wang, Boye Niu, Xiangxin Zhou, Yushi Huang, Tongliang Liu, Chi Zhang · 10 juin 2026

  Aligning text-to-image flow matching models with human preferences via direct reward backpropagation is sample-efficient but hampered by two well-known pathologies: activations cannot be stored across the full sampling trajectory at modern model scale, and chained Jacobian products across steps infl…