Generative Adversarial Networks and Image Synthesis

Derniers papiers

• MixFlow Training: Alleviating Exposure Bias with Slowed Interpolation Mixture

  Hui Li, Fu-Yun Wang, Haoyuan Xia, Jiayue Lyu, Kaihui Cheng, Siyu Zhu, Jingdong Wang · 14 juillet 2026

  This paper studies the training-testing discrepancy (a.k.a. exposure bias) problem for improving the diffusion models. During training, the input of a prediction network at one training timestep is the corresponding ground-truth noisy data that is an interpolation of the noise and the data, and duri…

• Xiaomi-Robotics-U0: Unified Embodied Synthesis with World Foundation Model

  Xinghang Li, Jun Guo, Qiwei Li, Long Qian, Hang Lai, Yueze Wang, Hongyu Yan, Jiahang Cao, Xi Chen, Jingen Qu, Jiaxi Song, Nan Sun, Hanye Zhao, Futeng Liu, Wanli Peng, Heyun Wang, Yunhong Wang, Caoyu Xia, Jack Zhao, Diyun Xiang, Hangjun Ye, Heng Qu, Huaping Liu, Jason Li · 14 juillet 2026

  Recent foundation image and video generation models offer strong generalization and controllability, but their direct application to embodied scenarios is limited by requirements for multi-view consistency, geometric coherence, and robot embodiment constraints. Existing methods typically adapt found…

• Learning from Noise: Effective-Rank Collapse and Out-of-Distribution Rejection in Restricted Boltzmann Machines

  Oshada Rathnayake, Nikhil Shukla · 14 juillet 2026

  Restricted Boltzmann machines (RBMs) represent data by shaping an energy landscape over visible and hidden configurations, but their discriminative use is fragile under out-of-distribution (OOD) inputs: samples outside the training distribution can be absorbed into one of the learned class basins ra…

• Diachronic Sample Integration: Robust Tail-Risk Estimation with Generative Models

  Shuning Zhao, Patrick Wong, Leran Zhang, Xiaolin Hu · 14 juillet 2026

  Deep generative models are increasingly used as simulators for downstream decision-making under data scarcity, but in risk-sensitive applications their usefulness depends on rare adverse scenarios rather than typical samples. Standard generative objectives prioritize bulk distributional fidelity, le…

• Controlling Motion Transfer in Diffusion Transformers via Attention Heads

  Sunyoung Jung, Jiwoo Park, Yoonseok Choi, Kyobin Choo, Ming-Hsuan Yang, Seong Jae Hwang · 14 juillet 2026

  Diffusion Transformers (DiTs) have advanced video generation with high-quality, temporally coherent results. However, extending them to motion transfer, which requires following reference motion while aligning with a target prompt, remains challenging due to limited understanding of motion and struc…

• Unified Backbone Refinement for Diffusion Models via Internal-Latent Analysis

  Haksoo Lim, Myeongjin Lee, Wonjoon Chang, Jaesik Choi · 14 juillet 2026

  Diffusion models have achieved remarkable success across diverse domains, with performance closely related to the denoising backbones that parameterize the score function. In this paper, we present a systematic, phase-aware analysis of diffusion components and show that abrupt, early-stage fluctuati…

• The Singularity Space: A Generative Diffusion Framework for Signal Representation

  Eli Bar-Yosef, Amir Averbuch, Eli Turkel · 14 juillet 2026

  Generative models often represent signals as dense grids of amplitudes, blurring sharp transients that are crucial for the correctness of physical signals. We introduce Singularity Space, a generative framework that represents signals through complex-plane singularities, rooted in the classical pole…

• DiffUE: Enhancing Utility-Unlearnability Trade-off of Unlearnable Examples via Diffusion Autoencoders

  Syed Irfan Ali Meerza, Oktay Ozturk, Amir Sadovnik, Jian Liu · 14 juillet 2026

  AI models are increasingly trained on personal images scraped from social media and public platforms, often without consent, leading to serious privacy violations, such as unauthorized facial recognition and targeted advertising. To counter this, researchers have developed unlearnable examples (UEs)…

• Conservation Laws for Diffusion Models

  Ziv Aharoni, Henry D. Pfister · 14 juillet 2026

  While autoregressive models optimize the exact data likelihood via the chain rule, diffusion models are typically trained with denoising objectives. We develop conservation laws based on generalized extrinsic information transfer (GEXIT) functions for a broad class of memoryless noise processes, sho…

• OmniSCS: Omni Safety-Critical Scenario Synthesis for Autonomous Driving via a Fully Editable Driving World

  Xiaoyun Dong, Qian Xu, Yang Lu, Yang Lou, Yung-Hui Li, Jianping Wang · 14 juillet 2026

  The synthesis of safety-critical scenarios (SCS) and their evaluation through closed-loop simulations are crucial for developing robust autonomous driving systems. A key aspect of this process involves editing agent states in both appearance and trajectory levels within existing scenes. However, cur…

• EmoStyle: Affective Conditioning of Style-Specialist Experts for Emotional Image Generation

  Dexiang Hong, Yijie Guo, Weidong Chen, Xinyan Liu, Zixuan Zou, Zhendong Mao, Yongdong Zhang · 14 juillet 2026

  Emotion-aware artistic image generation requires an image to match the input prompt, follow the specified artistic style, and convey the target emotion. In this challenge, the main difficulty is that the visual and affective attributes available in the training data are not explicitly provided at te…

• Next-Dense-Stride Prediction for Multimodal Autoregressive Visual Modeling

  Chicago Y. Park, Jialin Mao, Xiaojian Xu, Taha Kass-Hout, Ulugbek S. Kamilov, Cao Xiao · 14 juillet 2026

  We introduce DenseAR, a new generative paradigm that reformulates autoregressive image generation as coarse-to-fine next-dense-stride prediction using a compact single-scale tokenizer. Our key insight is that traversing a single-scale latent grid with progressively denser strides naturally captures …

• Sticky Jump Diffusions: A Unifying View of Masked, Continuous, and Hybrid Diffusion

  Pascal Jutras-Dub\'e, Patrick Pynadath, Jeremy Lu, Yuan Gao, Ruqi Zhang · 14 juillet 2026

  We introduce Sticky Jump Diffusions (SJDs), continuous-time Markov processes on $\mathbb R^d$ whose discrete anchors are token embeddings. In forward time, anchors release their mass at a hazard rate and the released mass diffuses in the continuous ambient space; time reversal couples a score-driven…

• Imaging-101: Benchmarking LLM Coding Agents on Scientific Computational Imaging

  Siyi Chen, Jiahe Ying, Yixuan Jia, Yuxuan Gu, Enze Ye, Weimin Bai, Zhijun Zeng, Shaochi Ren, Binhong Gao, Yubing Li, Tianhan Zhang, He Sun · 14 juillet 2026

  Computational imaging, which recovers hidden signals from indirect, noisy measurements, underpins quantitative discovery across scientific disciplines, yet building a correct reconstruction pipeline demands deep domain expertise and remains laborious even for domain scientists. We introduce Imaging-…

• Conditional Optimal Bridge for Riemannian Activation Steering

  Seyed Arshan Dalili, Ajay Narayanan Sridhar, Vijaykrishnan Narayanan, Mehrdad Mahdavi · 14 juillet 2026

  Activation steering offers a lightweight alternative to fine-tuning for controlling large language models at inference time. While many existing methods implicitly optimize a log-density-ratio objective between desired and undesired activation distributions, they do so heuristically rather than deri…

• When Does Depth Survive Composition? Compute--Quality Regimes in Latent World Models

  Achyuthan Sivasankar · 14 juillet 2026

  Adaptive-compute world models -- early-exit or mixture-of-depths predictors that spend variable depth per step -- assume depth buys better predictions and can be routed adaptively. In autoregressive rollouts, the first assumption requires depth's per-step precision to survive composition. We test th…

• Prompt Compression in Diffusion Large Language Models: Evaluating LLMLingua-2 on LLaDA

  Sterling Huang, Abigayle Brown, Jiyoo Noh, Jiakang Xu, Wantong Huo, Kaung Myat Kyaw, Jonathan Chan · 14 juillet 2026

  Prompt compression reduces inference cost and context length in large language models, but prior evaluations focus mainly on autoregressive architectures. This study examines whether LLMLingua-2 transfers effectively to diffusion large language models (DLLMs), specifically LLaDA-8B-Instruct. We eval…

• M4V: Multimodal Mamba for Efficient Text-to-Video Generation

  Jiancheng Huang, Gengwei Zhang, Zequn Jie, Siyu Jiao, Yinlong Qian, Ling Chen, Yunchao Wei, Lin Ma · 13 juillet 2026

  Text-to-video generation has significantly enriched content creation and holds the potential to evolve into powerful world simulators. However, modeling the vast spatiotemporal space remains computationally demanding, particularly when employing Transformers, which incur quadratic complexity in sequ…

• IB-Flow: Information Bottleneck-Guided CFG Distillation for Few-Step Text-to-Image Generation

  Yiting Wang, Jingyi Zhang, Wenhu Zhang, Ke Chao, Yves Liang, Kun Cheng, Kang Zhao · 13 juillet 2026

  While large-scale text-to-image generative models have achieved unprecedented visual performance, their inherent reliance on multi-step iterative solvers incurs severe inference latency. Few-step distillation targeting the Classifier-Free Guidance (CFG) trajectory has emerged as the prevalent dual-d…

• CtrlVTON: Controllable Virtual Try-On via Visual-Instance-Prompt Segmentation

  Seungyong Lee, Hyun Jun Jang, Sangoh Kim, Sungjoon Park · 13 juillet 2026

  Virtual try-on (VTO) has made significant progress in realistically transferring garments onto a target person. Yet most systems give the user little control over how a garment should be worn -- its size (loose or fitted), style (e.g., tucked in or untucked, open or closed), and spatial placement on…

• ArtMine: Discovering and Formalizing Artistic Processes

  Kaustubh Kumar, Ashutosh Ranjan, Vivek Srivastava, Blessin Varkey, Shirish Karande · 10 juillet 2026

  Understanding how artworks are created requires reasoning about the iterative decisions, material operations, and contextual influences that shape artistic production. While recent generative AI systems can synthesize artworks with high fidelity, they primarily model distributions over finished arti…

• AutoAnchor: Stable Diffusion Unlearning Using Cross-Attention as a Manifold Surrogate

  Siyuan Wen, Jiahao Zeng, Ningning Ding · 10 juillet 2026

  Diffusion unlearning is essential for mitigating the generation of harmful or copyrighted content in text-to-image models. Current diffusion unlearning techniques determine the model update direction by either using alternatives of the target concept as an anchor or using empty prompts. The anchor-b…

• CASL-VAE: Learning Structured Latent Variables from Unpaired Data for Semi-supervised Clustering and Paired Sample Generation

  Sai Spandana Chintapalli, Pratik Chaudhari, Christos Davatzikos · 10 juillet 2026

  Quantifying variability in a target population relative to a reference population is central to many scientific and clinical problems (e.g., diseased vs. healthy). Yet, without paired data and in the presence of heterogeneous target variation, existing methods struggle to separate multiple modes of …

• An exact information theory of generalization phase transitions in Bayesian diffusion models

  Henry Hunt, Mason Kamb, Surya Ganguli · 10 juillet 2026

  How diffusion models circumvent the curse of dimensionality to learn complex distributions over high dimensional spaces from a finite training set, instead of memorizing it, remains a fundamental mystery. To address this, we introduce analytically tractable Bayesian information restricted diffusion …

• Imputation Meets Clustering: Exploiting Latent Subgroup Structure for Missing Data Recovery

  Chuyao Zhang, E Li, Taochen Chen, Yiqun Zhang, Yuzhu Ji, Shuping Zhao, Peng Liu, Yiu-ming Cheung · 9 juillet 2026

  Missing data is prevalent in practical applications, making effective imputation an essential preprocessing step for downstream analysis. Real-world datasets often exhibit complex latent structures composed of multiple subgroups with distinct distributions. However, existing methods often overlook s…