Generative Adversarial Networks and Image Synthesis

Neueste Paper

• 2K-Characters-10K-Stories: A Quality-Gated Stylized Narrative Dataset with Disentangled Control and Sequence Consistency

  Xingxi Yin, Yicheng Li, Gong Yan, Chenglin Li, Jian Zhao, Cong Huang, Yue Deng, Yin Zhang · 8. Dezember 2025

  Sequential identity consistency under precise transient attribute control remains a long-standing challenge in controllable visual storytelling. Existing datasets lack sufficient fidelity and fail to disentangle stable identities from transient attributes, limiting structured control over pose, expr…

• Invariance Co-training for Robot Visual Generalization

  Jonathan Yang, Chelsea Finn, Dorsa Sadigh · 8. Dezember 2025

  Reasoning from diverse observations is a fundamental capability for generalist robot policies to operate in a wide range of environments. Despite recent advancements, many large-scale robotic policies still remain sensitive to key sources of observational variation such as changes in camera perspect…

• Real-Time Execution of Action Chunking Flow Policies

  Kevin Black, Manuel Y. Galliker, Sergey Levine · 8. Dezember 2025

  Modern AI systems, especially those interacting with the physical world, increasingly require real-time performance. However, the high latency of state-of-the-art generalist models, including recent vision-language action models (VLAs), poses a significant challenge. While action chunking has enable…

• SustainDiffusion: Optimising the Social and Environmental Sustainability of Stable Diffusion Models

  Giordano d'Aloisio, Tosin Fadahunsi, Jay Choy, Rebecca Moussa, Federica Sarro · 8. Dezember 2025

  Background: Text-to-image generation models are widely used across numerous domains. Among these models, Stable Diffusion (SD) - an open-source text-to-image generation model - has become the most popular, producing over 12 billion images annually. However, the widespread use of these models raises …

• Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders

  David Chanin, Adri\`a Garriga-Alonso · 8. Dezember 2025

  Sparse Autoencoders (SAEs) extract features from LLM internal activations, meant to correspond to interpretable concepts. A core SAE training hyperparameter is L0: how many SAE features should fire per token on average. Existing work compares SAE algorithms using sparsity-reconstruction tradeoff plo…

• InverseCrafter: Efficient Video ReCapture as a Latent Domain Inverse Problem

  Yeobin Hong, Suhyeon Lee, Hyungjin Chung, Jong Chul Ye · 8. Dezember 2025

  Recent approaches to controllable 4D video generation often rely on fine-tuning pre-trained Video Diffusion Models (VDMs). This dominant paradigm is computationally expensive, requiring large-scale datasets and architectural modifications, and frequently suffers from catastrophic forgetting of the m…

• World Models That Know When They Don't Know: Controllable Video Generation with Calibrated Uncertainty

  Zhiting Mei, Tenny Yin, Micah Baker, Ola Shorinwa, Anirudha Majumdar · 8. Dezember 2025

  Recent advances in generative video models have led to significant breakthroughs in high-fidelity video synthesis, specifically in controllable video generation where the generated video is conditioned on text and action inputs, e.g., in instruction-guided video editing and world modeling in robotic…

• Your Latent Mask is Wrong: Pixel-Equivalent Latent Compositing for Diffusion Models

  Rowan Bradbury, Dazhi Zhong · 8. Dezember 2025

  Latent inpainting in diffusion models still relies almost universally on linearly interpolating VAE latents under a downsampled mask. We propose a key principle for compositing image latents: Pixel-Equivalent Latent Compositing (PELC). An equivalent latent compositor should be the same as compositin…

• InvarDiff: Cross-Scale Invariance Caching for Accelerated Diffusion Models

  Zihao Wu · 8. Dezember 2025

  Diffusion models deliver high-fidelity synthesis but remain slow due to iterative sampling. We empirically observe there exists feature invariance in deterministic sampling, and present InvarDiff, a training-free acceleration method that exploits the relative temporal invariance across timestep-scal…

• Dynamical Properties of Tokens in Self-Attention and Effects of Positional Encoding

  Duy-Tung Pham, An The Nguyen, Viet-Hoang Tran, Nhan-Phu Chung, Xin T. Tong, Tan M. Nguyen, Thieu N. Vo · 4. Dezember 2025

  This paper investigates the dynamical properties of tokens in pre-trained Transformer models and explores their application to improving Transformers. To this end, we analyze the dynamical system governing the continuous-time limit of the pre-trained model and characterize the asymptotic behavior of…

• Density-Informed VAE (DiVAE): Reliable Log-Prior Probability via Density Alignment Regularization

  Michele Alessi, Alessio Ansuini, Alex Rodriguez · 4. Dezember 2025

  We introduce Density-Informed VAE (DiVAE), a lightweight, data-driven regularizer that aligns the VAE log-prior probability $\log p_Z(z)$ with a log-density estimated from data. Standard VAEs match latents to a simple prior, overlooking density structure in the data-space. DiVAE encourages the encod…

• Optical Context Compression Is Just (Bad) Autoencoding

  Ivan Yee Lee, Cheng Yang, Taylor Berg-Kirkpatrick · 4. Dezember 2025

  DeepSeek-OCR demonstrates that rendered text can be reconstructed with high fidelity from a small number of vision tokens. This finding has sparked excitement about vision-based context compression for language models. But the evaluation stops at reconstruction; whether these representations help la…

• Towards Irreversible Machine Unlearning for Diffusion Models

  Xun Yuan, Zilong Zhao, Jiayu Li, Aryan Pasikhani, Prosanta Gope, Biplab Sikdar · 4. Dezember 2025

  Diffusion models are renowned for their state-of-the-art performance in generating synthetic images. However, concerns related to safety, privacy, and copyright highlight the need for machine unlearning, which can make diffusion models forget specific training data and prevent the generation of sens…

• Universal Multi-Domain Translation via Diffusion Routers

  Duc Kieu, Kien Do, Tuan Hoang, Thao Minh Le, Tung Kieu, Dang Nguyen, Thin Nguyen · 4. Dezember 2025

  Multi-domain translation (MDT) aims to learn translations between multiple domains, yet existing approaches either require fully aligned tuples or can only handle domain pairs seen in training, limiting their practicality and excluding many cross-domain mappings. We introduce universal MDT (UMDT), a…

• GalaxyDiT: Efficient Video Generation with Guidance Alignment and Adaptive Proxy in Diffusion Transformers

  Zhiye Song, Steve Dai, Ben Keller, Brucek Khailany · 4. Dezember 2025

  Diffusion models have revolutionized video generation, becoming essential tools in creative content generation and physical simulation. Transformer-based architectures (DiTs) and classifier-free guidance (CFG) are two cornerstones of this success, enabling strong prompt adherence and realistic video…

• Rethinking Prompt Design for Inference-time Scaling in Text-to-Visual Generation

  Subin Kim, Sangwoo Mo, Mamshad Nayeem Rizve, Yiran Xu, Difan Liu, Jinwoo Shin, Tobias Hinz · 4. Dezember 2025

  Achieving precise alignment between user intent and generated visuals remains a central challenge in text-to-visual generation, as a single attempt often fails to produce the desired output. To handle this, prior approaches mainly scale the visual generation process (e.g., increasing sampling steps …

• CookAnything: A Framework for Flexible and Consistent Multi-Step Recipe Image Generation

  Ruoxuan Zhang, Bin Wen, Hongxia Xie, Yi Yao, Songhan Zuo, Jian-Yu Jiang-Lin, Hong-Han Shuai, Wen-Huang Cheng · 4. Dezember 2025

  Cooking is a sequential and visually grounded activity, where each step such as chopping, mixing, or frying carries both procedural logic and visual semantics. While recent diffusion models have shown strong capabilities in text-to-image generation, they struggle to handle structured multi-step scen…

• Dynamically Scaled Activation Steering

  Alex Ferrando, Xavier Suau, Jordi Gonz\`alez, Pau Rodriguez · 4. Dezember 2025

  Activation steering has emerged as a powerful method for guiding the behavior of generative models towards desired outcomes such as toxicity mitigation. However, most existing methods apply interventions uniformly across all inputs, degrading model performance when steering is unnecessary. We introd…

• Highly Efficient Test-Time Scaling for T2I Diffusion Models with Text Embedding Perturbation

  Hang Xu, Linjiang Huang, Feng Zhao · 4. Dezember 2025

  Test-time scaling (TTS) aims to achieve better results by increasing random sampling and evaluating samples based on rules and metrics. However, in text-to-image(T2I) diffusion models, most related works focus on search strategies and reward models, yet the impact of the stochastic characteristic of…

• Fast & Efficient Normalizing Flows and Applications of Image Generative Models

  Sandeep Nagar · 4. Dezember 2025

  This thesis presents novel contributions in two primary areas: advancing the efficiency of generative models, particularly normalizing flows, and applying generative models to solve real-world computer vision challenges. The first part introduce significant improvements to normalizing flow architect…

• ERF-BA-TFD+: A Multimodal Model for Audio-Visual Deepfake Detection

  Xin Zhang, Jiaming Chu, Jian Zhao, Yuchu Jiang, Xu Yang, Lei Jin, Chi Zhang, Xuelong Li · 4. Dezember 2025

  Deepfake detection is a critical task in identifying manipulated multimedia content. In real-world scenarios, deepfake content can manifest across multiple modalities, including audio and video. To address this challenge, we present ERF-BA-TFD+, a novel multimodal deepfake detection model that combi…

• Delta Sampling: Data-Free Knowledge Transfer Across Diffusion Models

  Zhidong Gao, Zimeng Pan, Yuhang Yao, Chenyue Xie, Wei Wei · 4. Dezember 2025

  Diffusion models like Stable Diffusion (SD) drive a vibrant open-source ecosystem including fully fine-tuned checkpoints and parameter-efficient adapters such as LoRA, LyCORIS, and ControlNet. However, these adaptation components are tightly coupled to a specific base model, making them difficult to…

• Technical Report on Text Dataset Distillation

  Keith Ando Ogawa, Bruno Lopes Yamamoto, Lucas Lauton de Alcantara, Victor Zacarias, Edson Bollis, Lucas Pellicer, Rosimeire Pereira Costa, Anna Helena Reali Costa, Artur Jordao · 4. Dezember 2025

  In the vision domain, dataset distillation arises as a technique to condense a large dataset into a smaller synthetic one that exhibits a similar result in the training process. While image data presents an extensive literature of distillation methods, text dataset distillation has fewer works in co…

• LumiX: Structured and Coherent Text-to-Intrinsic Generation

  Xu Han, Biao Zhang, Xiangjun Tang, Xianzhi Li, Peter Wonka · 3. Dezember 2025

  We present LumiX, a structured diffusion framework for coherent text-to-intrinsic generation. Conditioned on text prompts, LumiX jointly generates a comprehensive set of intrinsic maps (e.g., albedo, irradiance, normal, depth, and final color), providing a structured and physically consistent descri…

• Are Detectors Fair to Indian IP-AIGC? A Cross-Generator Study

  Vishal Dubey, Pallavi Tyagi · 3. Dezember 2025

  Modern image editors can produce identity-preserving AIGC (IP-AIGC), where the same person appears with new attire, background, or lighting. The robustness and fairness of current detectors in this regime remain unclear, especially for under-represented populations. We present what we believe is the…