Generative Adversarial Networks and Image Synthesis

Latest papers

• A Unifying Framework for Unsupervised Concept Extraction

  Chandler Squires, Pradeep Ravikumar · 29 April 2026

  Techniques for concept extraction, such as sparse autoencoders and transcoders, aim to extract high-level symbolic concepts from low-level nonsymbolic representations. When these extracted concepts are used for downstream tasks such as model steering and unlearning, it is essential to understand the…

• VAE-Inf: A statistically interpretable generative paradigm for imbalanced classification

  Hongfei Wu, Ruijian Han, Yancheng Yuan · 29 April 2026

  Imbalanced classification remains a pervasive challenge in machine learning, particularly when minority samples are too scarce to provide a robust discriminative boundary. In such extreme scenarios, conventional models often suffer from unstable decision boundaries and a lack of reliable error contr…

• Exploring Time Conditioning in Diffusion Generative Models from Disjoint Noisy Data Manifolds

  Liuzhuozheng Li, Zhiyuan Zhan, Shuhong Liu, Dengyang Jiang, Zanyi Wang, Guang Dai, Jingdong Wang, Mengmeng Wang · 29 April 2026

  Practically, training diffusion models typically requires explicit time conditioning to guide the network through the denoising sampling process. Especially in deterministic methods like DDIM, the absence of time conditioning leads to significant performance degradation. However, other deterministic…

• VibeToken: Scaling 1D Image Tokenizers and Autoregressive Models for Dynamic Resolution Generations

  Maitreya Patel, Jingtao Li, Weiming Zhuang, Yezhou Yang, Lingjuan Lv · 29 April 2026

  We introduce an efficient, resolution-agnostic autoregressive (AR) image synthesis approach that generalizes to arbitrary resolutions and aspect ratios, narrowing the gap to diffusion models at scale. At its core is VibeToken, a novel resolution-agnostic 1D Transformer-based image tokenizer that enc…

• Learning Illumination Control in Diffusion Models

  Nishit Anand, Manan Suri, Christopher Metzler, Dinesh Manocha, Ramani Duraiswami · 29 April 2026

  Controlling illumination in images is essential for photography and visual content creation. While closed-source models have demonstrated impressive illumination control, open-source alternatives either require heavy control inputs like depth maps or do not release their data and code. We present a …

• PhysCodeBench: Benchmarking Physics-Aware Symbolic Simulation of 3D Scenes via Self-Corrective Multi-Agent Refinement

  Tianyidan Xie, Peiyu Wang, Yuyi Qian, Yuxuan Wang, Rui Ma, Ying Tai, Song Wu, Qian Wang, Lanjun Wang, Zili Yi · 29 April 2026

  Physics-aware symbolic simulation of 3D scenes is critical for robotics, embodied AI, and scientific computing, requiring models to understand natural language descriptions of physical phenomena and translate them into executable simulation environments. While large language models (LLMs) excel at g…

• EAD-Net: Emotion-Aware Talking Head Generation with Spatial Refinement and Temporal Coherence

  Yahui Li, Yinfeng Yu, Liejun Wang, Shengjie Shen · 29 April 2026

  Emotionally talking head video generation aims to generate expressive portrait videos with accurate lip synchronization and emotional facial expressions. Current methods rely on simple emotional labels, leading to insufficient semantic information. While introducing high-level semantics enhances exp…

• Diffusion-Guided Feature Selection via Nishimori Temperature: Noise-Based Spectral Embedding

  Vasiliy S. Usatyuk, Denis A. Sapozhnikov, Sergey I. Egorov · 28 April 2026

  We propose Noise-Based Spectral Embedding (NBSE), a physics-informed framework for selecting informative features from high-dimensional data without greedy search. NBSE constructs a sparse similarity graph on the samples and identifies the Nishimori temperature $\beta_N$ the critical inverse tempera…

• Transformer as an Euler Discretization of Score-based Variational Flow

  Huadong Liao · 28 April 2026

  Despite the Transformer's dominance across machine learning, its architecture remains largely heuristic and lacks a unified theoretical foundation. We introduce Score-based Variational Flow (SVFlow), a continuous-time dynamical system for representation learning in which the state evolves according …

• Diffusion Templates: A Unified Plugin Framework for Controllable Diffusion

  Zhongjie Duan, Hong Zhang, Yingda Chen · 28 April 2026

  Controllable diffusion methods have substantially expanded the practical utility of diffusion models, but they are typically developed as isolated, backbone-specific systems with incompatible training pipelines, parameter formats, and runtime hooks. This fragmentation makes it difficult to reuse inf…

• On the Memorization of Consistency Distillation for Diffusion Models

  Bingqing Jiang, Difan Zou · 28 April 2026

  Diffusion models are central to modern generative modeling, and understanding how they balance memorization and generalization is critical for reliable deployment. Recent work has shown that memorization in diffusion models is shaped by training dynamics, with generalization and memorization emergin…

• Score-Repellent Monte Carlo: Toward Efficient Non-Markovian Sampler with Constant Memory in General State Spaces

  Jie Hu, Lingyun Chen, Geeho Kim, Jinyoung Choi, Bohyung Han, Do Young Eun · 28 April 2026

  History-dependent sampling can reduce long-run Monte Carlo variance by discouraging redundant revisits, but existing schemes typically encode history through empirical measure on finite state spaces, which is infeasible in high-dimensional discrete configuration spaces or ill-posed in continuous dom…

• Accelerating New Product Introduction for Visual Quality Inspection via Few-Shot Diffusion-Based Defect Synthesis

  Serkan Hamdi G\"u\u{g}\"ul, Kemal Levi, Burak Acar · 28 April 2026

  Industrial visual inspection systems often suffer from a severe scarcity of labeled defect data, particularly during the early stages of New Product Introduction (NPI). This limitation hinders the deployment of robust supervised detectors precisely when automated quality control is most needed. We p…

• Learning an Image Editing Model without Image Editing Pairs

  Nupur Kumari, Sheng-Yu Wang, Nanxuan Zhao, Yotam Nitzan, Yuheng Li, Krishna Kumar Singh, Richard Zhang, Eli Shechtman, Jun-Yan Zhu, Xun Huang · 28 April 2026

  Recent image editing models have achieved impressive results while following natural language editing instructions, but they rely on supervised fine-tuning with large datasets of input-target pairs. This is a critical bottleneck, as such naturally occurring pairs are hard to curate at scale. Current…

• Physics-Informed Temporal U-Net for High-Fidelity Fluid Interpolation

  Eshwar R. A., Nevin Mathew Thomas, Nehal G, Farida M. Begam · 28 April 2026

  Reconstructing high-fidelity fluid dynamics from sparse temporal observations is quite challenging, mainly due to the chaotic and non-linear nature of fluid transport. Standard deep learning-based interpolation methods often tend to regress to the mean, which results in spatial blurring and temporal…

• Meta-CoT: Enhancing Granularity and Generalization in Image Editing

  Shiyi Zhang, Yiji Cheng, Tiankai Hang, Zijin Yin, Runze He, Yu Xu, Wenxun Dai, Yunlong Lin, Chunyu Wang, Qinglin Lu, Yansong Tang · 28 April 2026

  Unified multi-modal understanding/generative models have shown improved image editing performance by incorporating fine-grained understanding into their Chain-of-Thought (CoT) process. However, a critical question remains underexplored: what forms of CoT and training strategy can jointly enhance bot…

• When Does Removing LayerNorm Help? Activation Bounding as a Regime-Dependent Implicit Regularizer

  Lucky Verma · 28 April 2026

  Dynamic Tanh (DyT) removes LayerNorm by bounding activations with a learned tanh(alpha x). We show that this bounding is a regime-dependent implicit regularizer, not a uniformly beneficial replacement. Across GPT-2-family models spanning 64M to 3.78B parameters and 1M to 118M tokens, with Llama and …

• Geometry Preserving Loss Functions Promote Improved Adaptation of Blackbox Generative Model

  Sinjini Mitra, Constantine Kyriakakis, Shenyuan Liang, Anuj Srivastava, Pavan Turaga · 28 April 2026

  Adaptation of blackbox generative models has been widely studied recently through the exploration of several methods including generator fine-tuning, latent space searches, leveraging singular value decomposition, and so on. However, adapting large-scale generative AI tools to specific use cases con…

• VS-DDPM: Efficient Low-Cost Diffusion Model for Medical Modality Translation

  Nikoo Moradi, Gijs Luijten, Behrus Hinrichs-Puladi, Jens Kleesiek, Victor Alves, Jan Egger, Andr\'e Ferreira · 28 April 2026

  Diffusion models produce high-quality synthetic data but suffer from slow inference. We propose 3D Variable-Step Denoising Diffusion Probabilistic Model (VS-DDPM) a framework engineered to maintain generative quality while accelerating inference by several factors. We tested our approach on four tas…

• V-GRPO: Online Reinforcement Learning for Denoising Generative Models Is Easier than You Think

  Bingda Tang, Yuhui Zhang, Xiaohan Wang, Jiayuan Mao, Ludwig Schmidt, Serena Yeung-Levy · 28 April 2026

  Aligning denoising generative models with human preferences or verifiable rewards remains a key challenge. While policy-gradient online reinforcement learning (RL) offers a principled post-training framework, its direct application is hindered by the intractable likelihoods of these models. Prior wo…

• What Drives Compositional Generalization? The Importance of Continuous Training Objectives in Visual Generative Models

  Karim Farid, Rajat Sahay, Yumna Ali Alnaggar, Simon Schrodi, Volker Fischer, Cordelia Schmid, Thomas Brox · 28 April 2026

  Compositional generalization, the ability to generate novel combinations of known concepts, is a key ingredient for visual generative models. Yet, not all mechanisms that enable or inhibit it are fully understood. In this work, we conduct a systematic study of how various design choices influence co…

• HubRouter: A Pluggable Sub-Quadratic Routing Primitive for Hybrid Sequence Models

  Abhinaba Basu · 27 April 2026

  We introduce HubRouter, a pluggable module that replaces O(n^2) attention layers with O(nM) hub-mediated routing, where M << n is a small number of learned hub tokens. We demonstrate it in two from-scratch architectures: a Jamba-style hybrid and a 12-layer Transformer; retrofit into pretrained model…

• Towards Adaptive Continual Model Merging via Manifold-Aware Expert Evolution

  Haiyun Qiu, Xingyu Wu, Kay Chen Tan · 27 April 2026

  Continual Model Merging (CMM) sequentially integrates task-specific models into a unified architecture without intensive retraining. However, existing CMM methods are hindered by a fundamental saturation-redundancy dilemma: backbone-centric approaches face parameter saturation and representation int…

• GenMatter: Perceiving Physical Objects with Generative Matter Models

  Eric Li, Arijit Dasgupta, Yoni Friedman, Mathieu Huot, Vikash Mansinghka, Thomas O'Connell, William T. Freeman, Joshua B. Tenenbaum · 27 April 2026

  Human visual perception offers valuable insights for understanding computational principles of motion-based scene interpretation. Humans robustly detect and segment moving entities that constitute independently moveable chunks of matter, whether observing sparse moving dots, textured surfaces, or na…

• Absorber LLM: Harnessing Causal Synchronization for Test-Time Training

  Zhixin Zhang, Shabo Zhang, Chengcan Wu, Zeming Wei, Meng Sun · 24 April 2026

  Transformers suffer from a high computational cost that grows with sequence length for self-attention, making inference in long streams prohibited by memory consumption. Constant-memory alternatives such as RNNs and SSMs compress history into states with fixed size and thus lose long-tail dependenci…