Generative Adversarial Networks and Image Synthesis

Derniers papiers

• Structured Nonparametric Variational Inference for Dependent Latent Modeling

  Yuda Shao, Zhiling Gu, Shan Yu · 16 juin 2026

  Variational inference (VI) is a core engine of modern AI, enabling scalable approximate Bayesian learning and uncertainty-aware training of large probabilistic and generative models. In this paper, we propose Structured Nonparametric Variational Inference (SN-VI), a novel framework for modeling comp…

• SPRI: SVD-Partitioned Residual Initialization for Data-Constrained MoE Upcycling

  Weiqiao Shan, Ruixiang Mao, Yuang Li, Yuhao Zhang, Yingfeng Luo, Tong Zheng, Chen Xu, Yucheng Qiao, Chunxiang Jin, Yi Yuan, Jingdong Chen, Tong Xiao, Jingbo Zhu · 16 juin 2026

  Mixture-of-Experts (MoE) models enable efficient scaling, but training them from scratch remains prohibitively expensive. MoE upcycling mitigates this cost by converting pretrained dense models into sparse MoE models. However, existing upcycling methods typically rely on large-scale continued traini…

• Probabilistic Signature Inversion: Learning Conditional Distributions from Truncated Signatures

  Junoh Kang, Kiseop Lee, Bohyung Han · 16 juin 2026

  The signature transform is a principled feature map for continuous-time paths, valued for its uniqueness and universality. Recovering a path from its truncated signature is, however, structurally ill-posed because the truncated signature map is not injective. We therefore reframe truncated signature…

• Exact Posterior Score Estimation for Solving Linear Inverse Problems

  Abbas Mammadov, Ozgur Kara, Kaan Oktay, Iskander Azangulov, Adil Kaan Akan, Hyungjin Chung, James Matthew Rehg, Yee Whye Teh · 16 juin 2026

  Diffusion and flow-based models learn powerful data priors by training a denoiser to reverse Gaussian corruption. To use this prior to solve a linear inverse problem, one needs to sample from the posterior, but the score that the prior provides is the unconditional score, not the posterior score. Ex…

• Distilling Drifting Transformers with Representation Autoencoders

  Jiawei Zhang, Mengfei Xia, Gen Li, Yuantao Gu · 16 juin 2026

  Representation Autoencoders (RAEs) have improved diffusion and flow models by semantically richer latent space owing to the strongly label-wise clustered DINO features in the pretrained encoders. Yet in the distillation stage, the severe anisotropy and large curvatures caused by the rich semantic re…

• RealityBridge: Bridging Editable 3D Gaussian Splatting Driving Simulations and Real-World Videos

  Zhenhua Wu, Yun Pang, Mingkun Chang, Yuwei Ning, Liangzhi Wang, Yi Xiao, Guanbin Li · 16 juin 2026

  Long-tail hazardous scenarios are essential for safety-oriented autonomous driving, yet they are difficult to collect and reproduce at scale. Editable 3D Gaussian Splatting (3DGS) simulation offers a promising alternative by reconstructing real driving scenes and supporting controllable scene editin…

• Towards a Unified Generative Model for Scarce Time Series with Domain Experts

  Zihao Yao, Qi Zheng, Jiankai Zuo, Yaying Zhang · 16 juin 2026

  Synthesizing realistic time series with generative models has wide-ranging applications in real-world scenarios. Despite recent progress, most existing methods are trained under the assumption of abundant training data, which substantially limits their effectiveness in data-scarce settings. In this …

• Temporal Difference Learning for Diffusion Models

  Qizhen Ying, Yangchen Pan, Victor Adrian Prisacariu, Junfeng Wen · 16 juin 2026

  Diffusion models are typically trained with objectives that focus on local denoising targets at individual time steps (or adjacent pairs), which do not enforce consistency between predictions along the denoising trajectory. This lack of cross-time consistency can degrade performance, especially for …

• Stop the Sampler! Classifier-Based Adaptive Stopping for Sampling Kernels

  Kirill Korolev, Nikita Morozov, Stepan Pavlenko, Esmeralda S. Whitammer, Sergey Samsonov · 16 juin 2026

  Sampling from complex, unnormalized probability densities is a fundamental challenge in Bayesian inference and probabilistic modeling. While Markov chain Monte Carlo (MCMC) methods provide asymptotic guarantees, they often suffer from slow mixing and high computational costs due to fixed or manually…

• PhysGuard: Fisher-Guided Gradient Projection for Sim-to-Real Neural PDE Surrogates

  Changjian Zhou, Junfeng Fang, Negin Yousefpour, Peng Wu, Bin Yan, Guillermo A Narsilio · 16 juin 2026

  Neural operator models trained on simulation data often lose accuracy when applied to experimental measurements due to the sim-to-real gap. Standard fine-tuning with limited real data can reduce this gap, but it may also damage the core physics-relevant representations learned during pretraining. Al…

• Temporally Consistent and Controllable Video Generation of 2D Cine CMR via Latent Space Motion Modeling

  Yiheng Cao (SyCoIA - IMT Mines Al\`es), Gustavo Andrade-Miranda (SyCoIA - IMT Mines Al\`es), Jiatian Zhang, Guillaume Sall\'e, Xin Gao · 16 juin 2026

  Cine cardiac magnetic resonance is the gold standard for assessing cardiac function, but the scarcity of public datasets limits the development of advanced data-driven models. To address this limitation, we propose a generative method for synthesizing temporally coherent and anatomically consistent …

• Selective Synergistic Learning for Video Object-Centric Learning

  WonJun Moon, Jae-Pil Heo · 16 juin 2026

  Typical video object-centric learning (VOCL) approaches employ slot-based frameworks that rely on reconstruction-driven encoder-decoder architectures, where learning is mediated by two spatial maps: attention maps from the encoder and object maps from the decoder. As these two distinct maps exhibit …

• DifFRACT: Diffusion Feature Reconstruction and Attribution for Circuit Tracing

  Artyom Mazur, Nina Konovalova, Aibek Alanov · 16 juin 2026

  Mechanistic interpretability seeks to explain neural network behavior by decomposing model computations into interpretable features and circuits. While transcoder-based circuit tracing has recently enabled detailed causal analyses of large language models, multimodal diffusion transformers for image…

• Quantifying the Impact of Lossy Compression on Neural Generative Surrogate Modeling

  Zhimin Li, Harshitha Menon, Charles Jekel, Valerio Pascucci, Peter Lindstrom · 16 juin 2026

  Neural networks are used as generative surrogate models for scientific discovery, which are trainable approximations of scientific simulations. These models enable users to replace time-consuming numerical simulations with learned alternatives, providing quick solutions. However, high-fidelity gener…

• Teacher-Student Structure for Domain Adaptation in Ensemble Audio-Visual Video Deepfake Detection

  Elham Abolhasani, Maryam Ramezani, Hamid R. Rabiee · 16 juin 2026

  The rapid advancement of generative AI models is leading to more realistic deepfake media, encompassing the manipulation of audio, video, or both. This raises severe privacy and societal concerns. Numerous studies in this area have yielded promising intra-domain results; however, these models freque…

• Sub-Semantic Image Segmentation

  Aviad Cohen Zada, Nadav Orenstein, Shai Avidan, Gal Oren · 16 juin 2026

  Images can be segmented based on visual cues (i.e., texture segmentation) or into objects (i.e., semantic segmentation). We propose a new category of sub-semantic image segmentation that blurs the line between the two. In sub-semantic image segmentation, language is not used to name whole objects. I…

• Efficient Flow Matching using Latent Variables

  Anirban Samaddar, Yixuan Sun, Viktor Nilsson, Sandeep Madireddy · 16 juin 2026

  Flow matching models have shown great potential in image generation tasks among probabilistic generative models. However, most flow matching models in the literature do not explicitly utilize the underlying clustering structure in the target data when learning the flow from a simple source distribut…

• Prediction Bottlenecks Don't Discover Causal Structure (But Here's What They Actually Do)

  Ankit Hemant Lade, Sai Krishna Jasti, Indar Kumar, Aman Chadha · 16 juin 2026

  A Mamba state-space model trained only for next-step prediction appears to recover Granger-causal structure through a simple readout $S = |W_{out} W_{in}|$, with early experiments suggesting the phenomenon generalized across architectures and benefited from interventional data at $p < 10^{-5}$. We p…

• Pixel-TTS: Image based Text Rendering for Robust Text-to-Speech

  Adarsh Arigala, Arjun Gangwar, S Umesh, Yova Kementchedjhieva · 16 juin 2026

  Recent advances in pixel-based text modeling show that representing text as images enables models to exploit visual cues for language understanding. Grounding text in its visual form allows structurally similar characters with different Unicode encodings to produce similar embeddings, benefiting cro…

• The Information-Theoretic Benefit of Shared Representations under Orthogonality Constraints

  Thomas Dittrich, Oliver Potocki, Philipp Grohs · 16 juin 2026

  Modern deep learning architectures are increasingly multi-task and multi-modal, using a pretrained foundation model combined with task-specific, fine-tuned models. Empirically, exploiting similarity across different problems, instead of solving them individually, can significantly improve overall pe…

• MA-SBI: Misspecification-Aware Simulation-Based Inference via Side-Channel Guidance

  Arunkumar V, Manoranjan Gandhudi, Gangadharan G. R., Arun Prakash, S. Senthilkumar · 16 juin 2026

  Simulation-based inference (SBI) of latent parameters is often hindered by simulator misspecification, the mismatch between simulated and real-world observations caused by inherent modeling simplifications. RoPE, the recent state-of-the-art for robust SBI, addresses this through optimal transport be…

• BRICKS-WM: Building Reusability via Interface Composition Kinetics for Structured World Models

  Shaowei Zhang, Jiahan Cao, Xunlan Zhou, Shenghua Wan, De-Chuan Zhan · 16 juin 2026

  Model-based Reinforcement Learning (MBRL) has achieved remarkable success in continuous control by leveraging latent world models. However, prevailing approaches typically rely on monolithic latent dynamics, entangling environment dynamics into a coupled process. This coupling severely limits reusab…

• Where Does Texture Evidence Live in SAM? Features, Proposal Masks, and Texture Segmentation

  Nadav Orenstein, Aviad Cohen Zada, Shai Avidan, Gal Oren · 16 juin 2026

  Texture segmentation stresses foundation segmentation because meaningful regions are defined by material or repeated appearance rather than object identity. Segment Anything Models (SAMs) often fail by default on such texture-defined partitions, but this failure is ambiguous: the texture evidence ma…

• Divide-and-Denoise: A Game-Theoretic Method for Fairly Composing Diffusion Models

  Abhi Gupta, Polina Barabanshchikova, Vikas Garg, Samuel Kaski, Tommi Jaakkola · 16 juin 2026

  The abundance of pre-trained diffusion models provides an opportunity for composition. Combining several models, however, runs the risk of one model dominating or models disagreeing with each other. Here, we propose Divide-and-Denoise, a method for coordinating multiple pre-trained diffusion models …

• Shift-and-Sum Quantization for Visual Autoregressive Models

  Jaehyeon Moon, Bumsub Ham · 16 juin 2026

  Post-training quantization (PTQ) enables efficient deployment of deep networks using a small set of data. Its application to visual autoregressive models (VAR), however, remains relatively unexplored. We identify two key challenges for applying PTQ to VAR: (i) large reconstruction errors in attentio…