Generative Adversarial Networks and Image Synthesis

Últimos artículos

• EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation

  Songlin Yang, Haobin Zhong, Ruilin Zhang, Xiaotong Zhao, Shuai Li, Kai Zheng, Xuyi Yang, Zhe Wang, Zhenchen Tang, Yang Li, Bohai Gu, Zhengwei Peng, Yidan Huang, Mengzhou Luo, Yihang Bo, Dalu Feng, Yujia Zhang, Juntao Ma, Ruiqi Wang, Lvmin Zhang, Yuwei Guo, Frank Guan, Maneesh Agrawala, Hongbo Fu, Alan Zhao, Anyi Rao · 25 de mayo de 2026

  The rapid evolution of generative video foundation models has propelled the field toward professional-grade cinematic synthesis. To achieve such demanding quality, the community transitions towards Reinforcement Learning (RL) and agentic workflows. However, reliable evaluation has emerged as a criti…

• Contrastive Distribution Matching for Amortized Sequential Monte Carlo in Discrete Diffusion

  Jaihoon Kim, Taehoon Yoon, Prin Phunyaphibarn, Seungjun Kim, Morteza Mardani, Minhyuk Sung · 25 de mayo de 2026

  Discrete diffusion models have emerged as powerful frameworks for generating structured categorical data. However, efficiently sampling from reward-tilted distributions remains a fundamental challenge. While Twisted Sequential Monte Carlo (SMC) offers asymptotic exactness for this task, estimating t…

• Diffusion Domain Expansion: Learning to Coordinate Pre-trained Diffusion Models

  Egor Lifar, Semyon Savkin, Timur Garipov, Shangyuan Tong, Tommi Jaakkola · 25 de mayo de 2026

  In this paper, we propose Diffusion Domain Expansion (DDE), a method that efficiently extends pre-trained diffusion models to generate larger objects and handle more complex conditioning beyond their original capabilities. Our method employs a compact trainable network designed to coordinate the den…

• World Machine: Towards Generative World Modeling for Time-Series

  Elton Cardoso do Nascimento, Alexandre da Silva Sim\~oes, Esther Luna Colombini, Ricardo Ribeiro Gudwin, Paula Dornhofer Paro Costa · 25 de mayo de 2026

  World models represent a paradigm shift in generative AI, pursuing predictive understanding and controllable simulation of environments in a structured and generalizable way. We present World Machine, a generative world-modeling architecture for time series. It is a transformer-based architecture wi…

• Learned Relay Representations for Forward-Thinking Discrete Diffusion Models

  Benjamin Rozonoyer, Jacopo Minniti, Dhruvesh Patel, Neil Band, Avishek Joey Bose, Tim G. J. Rudner, Andrew McCallum · 25 de mayo de 2026

  When Masked Diffusion Models (MDMs) generate sequences through iterative refinement, the rich internal computation over masked positions is discarded, forcing every subsequent refinement step to recompute the valuable internal information stored as model representations. To avoid a hard reset betwee…

• The TIME Machine: On The Power of Motion for Efficient Perception

  Mantas Skackauskas, Xinyue Hao, Laura Sevilla-Lara · 25 de mayo de 2026

  Video representation learning has seen tremendous progress in recent years. This has been driven by many factors, including the scale of training and the success of visual models trained contrastively with language. While these factors have pushed the boundaries of what video models can do, they als…

• Precise: SDE-Consistent Stochastic Sampling for RL Post-Training of Flow-Matching Models

  Jade Zou, Tao Huang, Weijie Kong, Junzhe Li, Yue Wu, Qi Tian, Jiangfeng Xiong, Jianwei Zhang, Liefeng Bo, Zhao Zhong · 25 de mayo de 2026

  Reinforcement learning (RL) has become an effective way to improve prompt alignment and perceptual quality in diffusion and flow-matching generators. A critical step for applying online RL to flow matching is turning the deterministic sampling trajectory into a stochastic policy, typically by replac…

• SimInsert: Seamless Video Object Insertion via Regional Sparse Attention Fusion

  Xinyu Chen, Yuyi Qian, Jiang Lin, Shenyi Wang, Gao Wang, Zhiqiu Zhang, Jizhi Zhang, Mingjie Wang, Qiang Tang, Qian Wang, Song Wu, Zili Yi · 25 de mayo de 2026

  Video object insertion requires ensuring spatio-temporal coherence and interactive realism, extending far beyond simple content placement. However, current approaches are often hindered by a reliance on explicit motion engineering or resource-intensive retraining, restricting their flexibility and g…

• EM-Vid: Training-Free Entity-Centric Memory for Efficient and Consistent Multi-Shot Video Generation

  Jente Vandersanden, Matheus Gadelha, Chun-Hao P. Huang, Hyeonho Jeong, Yulia Gryaditskaya · 25 de mayo de 2026

  Multi-shot video generation requires maintaining a consistent appearance of recurring entities across shots while remaining faithful to shot-specific text prompts. Recent autoregressive methods reuse previously generated frames as memory. However, full-frame storage entangles persistent entity infor…

• DrawVideo: Generating Long Video from Storyboard Keyframe Sketches

  Chuanzhi Xu, Huiqi Liang, Bang Shi, Huiming Zhang, Yifan Xiao, Guangcheng Lin, Haodong Chen, Qiang Qu, Zhicheng Lu, Weidong Cai · 25 de mayo de 2026

  Long video generation requires high-fidelity synthesis, coherent narrative structure, and user control over extended time spans. Existing text-to-video methods often rely on a single long prompt, limiting control over pose, composition, layout, and motion. We propose DrawVideo, a sketch-guided, stor…

• One-Forcing: Towards Stable One-Step Autoregressive Video Generation

  Jiaqi Feng, Justin Cui, Yuanhao Ban, Cho-Jui Hsieh · 25 de mayo de 2026

  Recent advances have substantially improved real-time interactive video generation in the autoregressive regime. However, most existing few-step autoregressive video generation methods, often distilled from a corresponding many-step teacher, default to a 4-step sampling configuration, which still in…

• Human-Centered Learning Mechanics: A Dynamical Framework for Entropy-Regulated Representation Learning

  Kim Phuc Tran · 25 de mayo de 2026

  Deep learning is increasingly viewed as a dynamical process in parameter space, yet many existing theories still treat training as a closed optimization system. This view is limited for real-world AI, where models operate under uncertainty, resource constraints, distribution shift, downstream decisi…

• Complete-muE: Optimal Hyperparameter Transfer and Scaling for MoE Models

  Hongwu Peng, Ohiremen Dibua, Yuanjun Xiong, Yifan Gong, Jianming Zhang, Yan Kang · 25 de mayo de 2026

  We propose Complete-muE, a framework which targets hyperparameter transfer across dense FFN and any Mixture-of-Experts (MoE) setups in transformer blocks. Existing tools such as $\mu$P (requires fixed architectue) or SDE (requires fixed per-step token count) cannot directly solve the hyperparameter …

• OmniVL-Guard Pro: A Tool-Augmented Agent for Omnibus Vision-Language Forensics

  Jinjie Shen, Zheng Huang, Yuchen Zhang, Yujiao Wu, Yaxiong Wang, Lechao Cheng, Shengeng Tang, Tianrui Hui, Nan Pu, Zhun Zhong · 22 de mayo de 2026

  Existing vision-language forgery detection and grounding methods operate under a closed-world paradigm, assuming verification can be completed by the model alone. However, self-contained MLLMs are constrained by finite parametric knowledge, static training corpora, and limited perceptual resolution,…

• Pareto-Enhanced Portrait Generation: Vision-Aligned Text Supervision for Alignment, Realism, and Aesthetics

  Yunlong Wang, Jinjin Shi, Wenbin Gao, Xuran Xu, Runyu Shi, Ying Huang · 22 de mayo de 2026

  Text-to-image diffusion models often face a severe trilemma in human portrait generation: text-image alignment, photorealism, and human-perceived aesthetics inherently inhibit one another. Supervised Fine-Tuning (SFT) is an effective method for enhancing the photorealism of image generation. However…

• Rethinking Cross-Layer Information Routing in Diffusion Transformers

  Chao Xu, Maohua Li, Qirui Li, Yixuan Xu, Yanke Zhou, Yunhe Li, Cuifeng Shen, Hanlin Tang, Kan Liu, Tao Lan, Lin Qu, Shao-Qun Zhang · 22 de mayo de 2026

  Diffusion Transformers (DiTs) have become a de facto backbone of modern visual generation, and nearly every major axis of their design -- tokenization, attention, conditioning, objectives, and latent autoencoders -- has been extensively revisited. The residual stream that governs how information acc…

• Tiny-Engram: Trigger-Indexed Concept Tables for Generative Vision

  Runyuan Cai, Yiming Wang, Yu Lin, Xiaodong Zeng · 22 de mayo de 2026

  Current personalization methods for generative vision models typically encode new concepts through continuous adapters or weight updates, yet provide limited control over whether and when a concept should be retrieved. In this work, we introduce Tiny-Engram, a compact trigger-indexed concept table t…

• FullFlow: Upgrading Text-to-Image Flow Matching Models for Bidirectional Vision--Language Generation

  Eric Tillmann Bill, Enis Simsar, Alessio Tonioni, Thomas Hofmann · 22 de mayo de 2026

  Modern text-to-image diffusion models encode rich visual priors, but expose them only through one-way text-conditioned generation. Existing unified vision--language models derived from them recover bidirectional capability through large-scale joint pretraining or substantial retraining of the text p…

• Letting Trajectories Spread: Quality-Preserving Control for Diverse Flow Matching

  Jingxuan Wu, Zhenglin Wan, Xingrui Yu, Yuzhe Yang, Bo An, Ivor Tsang, Yang You · 22 de mayo de 2026

  Flow-based text-to-image models follow deterministic trajectories, making it costly to explore diverse modes under limited sampling budgets. Existing approaches to improving diversity often rely on retraining or degrade image fidelity. To address this limitation, we present a training-free, inferenc…

• CAdam: Context-Adaptive Moment Estimation for 3D Gaussian Densification in Generative Distillation

  SeungJeh Chung, Geonho Park, Misong Kim, HyeongYeop Kang · 21 de mayo de 2026

  Adaptive densification is the engine of 3D Gaussian Splatting (3DGS). However, when transposed to the optimization-based Generative Distillation paradigm, this reconstruction-native mechanism reveals fundamental limitations, resulting in inefficient representations cluttered with redundant primitive…

• Disentangling Generation and Regression in Stochastic Interpolants for Controllable Image Restoration

  Yi Liu, Jia Ma, Wengen Li, Jihong Guan, Shuigeng Zhou, Yichao Zhang · 21 de mayo de 2026

  Recent advances in Image Restoration (IR) have been largely driven by generative methods such as Diffusion Models and Flow Matching, which excel in synthesizing realistic textures while suffering from slow multi-step inference and compromised pixel fidelity. In contrast, classical regression-based I…

• Variance Reduction for Expectations with Diffusion Teachers

  Jesse Bettencourt, Xindi Wu, Matan Atzmon, James Lucas, Jonathan Lorraine · 21 de mayo de 2026

  Pretrained diffusion models serve as frozen teachers feeding downstream pipelines such as text-to-3D, single-step distillation, and data attribution. The teacher gradients these pipelines consume are Monte Carlo (MC) expectations over noise levels and Gaussian noise samples; their estimator variance…

• Oracle Supervision Transfers for Hyperparameter Prediction in Model-Based Image Denoising

  Jianmin Liao, Lixin Shen, Yuesheng Xu · 21 de mayo de 2026

  Hyperparameter prediction is a critical practical bottleneck for model-based image denoisers, ranging from classical TV/TGV variational solvers to modern diffusion-based models such as DiffPIR. While existing learned predictors can achieve near-oracle performance, this approach scales poorly: each n…

• Mechanisms of Misgeneralization in Physical Sequence Modeling

  Kento Nishi, Raphael Tang, Karun Kumar, Core Francisco Park, Hidenori Tanaka · 21 de mayo de 2026

  Generative sequence models are often trained to plan motion in physical domains, from robotics to mechanical simulations. When constructing a dataset to train such a model, engineers may curate demonstrations to specify how trajectories should be distributed over a physical quantity like travel dist…

• Accelerating Video Inverse Problem Solvers with Autoregressive Diffusion Models

  Taesung Kwon, Jonghyun Park, Hyungjin Chung, Jong Chul Ye · 21 de mayo de 2026

  Diffusion models provide powerful priors for zero-shot video inverse problems, but their real-time deployment is hindered by two inefficiencies: high initial latency caused by holistic video restoration, and low throughput resulting from multiple VAE passes to enforce measurement consistency in pixe…